This is page 114 of 145. Use http://codebase.md/microsoft/semanticworkbench?lines=true&page={x} to view the full context.
# Directory Structure
```
├── .devcontainer
│ ├── .vscode
│ │ └── settings.json
│ ├── devcontainer.json
│ ├── OPTIMIZING_FOR_CODESPACES.md
│ ├── POST_SETUP_README.md
│ └── README.md
├── .dockerignore
├── .gitattributes
├── .github
│ ├── policheck.yml
│ └── workflows
│ ├── assistants-codespace-assistant.yml
│ ├── assistants-document-assistant.yml
│ ├── assistants-explorer-assistant.yml
│ ├── assistants-guided-conversation-assistant.yml
│ ├── assistants-knowledge-transfer-assistant.yml
│ ├── assistants-navigator-assistant.yml
│ ├── assistants-project-assistant.yml
│ ├── assistants-prospector-assistant.yml
│ ├── assistants-skill-assistant.yml
│ ├── libraries.yml
│ ├── mcp-server-giphy.yml
│ ├── mcp-server-memory-filesystem-edit.yml
│ ├── mcp-server-memory-user-bio.yml
│ ├── mcp-server-memory-whiteboard.yml
│ ├── mcp-server-open-deep-research-clone.yml
│ ├── mcp-server-web-research.yml
│ ├── workbench-app.yml
│ └── workbench-service.yml
├── .gitignore
├── .multi-root-tools
│ ├── Makefile
│ └── README.md
├── .vscode
│ ├── extensions.json
│ ├── launch.json
│ └── settings.json
├── ai_context
│ └── generated
│ ├── ASPIRE_ORCHESTRATOR.md
│ ├── ASSISTANT_CODESPACE.md
│ ├── ASSISTANT_DOCUMENT.md
│ ├── ASSISTANT_NAVIGATOR.md
│ ├── ASSISTANT_PROJECT.md
│ ├── ASSISTANT_PROSPECTOR.md
│ ├── ASSISTANTS_OTHER.md
│ ├── ASSISTANTS_OVERVIEW.md
│ ├── CONFIGURATION.md
│ ├── DOTNET_LIBRARIES.md
│ ├── EXAMPLES.md
│ ├── MCP_SERVERS.md
│ ├── PYTHON_LIBRARIES_AI_CLIENTS.md
│ ├── PYTHON_LIBRARIES_CORE.md
│ ├── PYTHON_LIBRARIES_EXTENSIONS.md
│ ├── PYTHON_LIBRARIES_SKILLS.md
│ ├── PYTHON_LIBRARIES_SPECIALIZED.md
│ ├── TOOLS.md
│ ├── WORKBENCH_FRONTEND.md
│ └── WORKBENCH_SERVICE.md
├── aspire-orchestrator
│ ├── .editorconfig
│ ├── Aspire.AppHost
│ │ ├── .gitignore
│ │ ├── appsettings.json
│ │ ├── Aspire.AppHost.csproj
│ │ ├── Program.cs
│ │ └── Properties
│ │ └── launchSettings.json
│ ├── Aspire.Extensions
│ │ ├── Aspire.Extensions.csproj
│ │ ├── Dashboard.cs
│ │ ├── DockerFileExtensions.cs
│ │ ├── PathNormalizer.cs
│ │ ├── UvAppHostingExtensions.cs
│ │ ├── UvAppResource.cs
│ │ ├── VirtualEnvironment.cs
│ │ └── WorkbenchServiceHostingExtensions.cs
│ ├── Aspire.ServiceDefaults
│ │ ├── Aspire.ServiceDefaults.csproj
│ │ └── Extensions.cs
│ ├── README.md
│ ├── run.sh
│ ├── SemanticWorkbench.Aspire.sln
│ └── SemanticWorkbench.Aspire.sln.DotSettings
├── assistants
│ ├── codespace-assistant
│ │ ├── .claude
│ │ │ └── settings.local.json
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── extensions.json
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── assets
│ │ │ │ ├── icon_context_transfer.svg
│ │ │ │ └── icon.svg
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── helpers.py
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── completion_handler.py
│ │ │ │ ├── models.py
│ │ │ │ ├── request_builder.py
│ │ │ │ ├── response.py
│ │ │ │ ├── step_handler.py
│ │ │ │ └── utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── abbreviations.py
│ │ │ │ ├── formatting_utils.py
│ │ │ │ ├── message_utils.py
│ │ │ │ └── openai_utils.py
│ │ │ ├── text_includes
│ │ │ │ ├── card_content_context_transfer.md
│ │ │ │ ├── card_content.md
│ │ │ │ ├── codespace_assistant_info.md
│ │ │ │ ├── context_transfer_assistant_info.md
│ │ │ │ ├── guardrails_prompt.txt
│ │ │ │ ├── guidance_prompt_context_transfer.txt
│ │ │ │ ├── guidance_prompt.txt
│ │ │ │ ├── instruction_prompt_context_transfer.txt
│ │ │ │ └── instruction_prompt.txt
│ │ │ └── whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── _inspector.py
│ │ │ └── _whiteboard.py
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── document-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── assets
│ │ │ │ └── icon.svg
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── context_management
│ │ │ │ ├── __init__.py
│ │ │ │ └── inspector.py
│ │ │ ├── filesystem
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _convert.py
│ │ │ │ ├── _file_sources.py
│ │ │ │ ├── _filesystem.py
│ │ │ │ ├── _inspector.py
│ │ │ │ ├── _model.py
│ │ │ │ ├── _prompts.py
│ │ │ │ └── _tasks.py
│ │ │ ├── guidance
│ │ │ │ ├── __init__.py
│ │ │ │ ├── dynamic_ui_inspector.py
│ │ │ │ ├── guidance_config.py
│ │ │ │ ├── guidance_prompts.py
│ │ │ │ └── README.md
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── completion_handler.py
│ │ │ │ ├── models.py
│ │ │ │ ├── prompts.py
│ │ │ │ ├── responder.py
│ │ │ │ └── utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── formatting_utils.py
│ │ │ │ ├── message_utils.py
│ │ │ │ ├── openai_utils.py
│ │ │ │ ├── tokens_tiktoken.py
│ │ │ │ └── workbench_messages.py
│ │ │ ├── text_includes
│ │ │ │ └── document_assistant_info.md
│ │ │ ├── types.py
│ │ │ └── whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── _inspector.py
│ │ │ └── _whiteboard.py
│ │ ├── assistant.code-workspace
│ │ ├── CLAUDE.md
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── __init__.py
│ │ │ ├── test_convert.py
│ │ │ └── test_data
│ │ │ ├── blank_image.png
│ │ │ ├── Formatting Test.docx
│ │ │ ├── sample_data.csv
│ │ │ ├── sample_data.xlsx
│ │ │ ├── sample_page.html
│ │ │ ├── sample_presentation.pptx
│ │ │ └── simple_pdf.pdf
│ │ └── uv.lock
│ ├── explorer-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── helpers.py
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── model.py
│ │ │ │ ├── response_anthropic.py
│ │ │ │ ├── response_openai.py
│ │ │ │ └── response.py
│ │ │ └── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── guided-conversation-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agents
│ │ │ │ ├── guided_conversation
│ │ │ │ │ ├── config.py
│ │ │ │ │ ├── definition.py
│ │ │ │ │ └── definitions
│ │ │ │ │ ├── er_triage.py
│ │ │ │ │ ├── interview.py
│ │ │ │ │ ├── patient_intake.py
│ │ │ │ │ └── poem_feedback.py
│ │ │ │ └── guided_conversation_agent.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ └── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── knowledge-transfer-assistant
│ │ ├── .claude
│ │ │ └── settings.local.json
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agentic
│ │ │ │ ├── __init__.py
│ │ │ │ ├── analysis.py
│ │ │ │ ├── coordinator_support.py
│ │ │ │ └── team_welcome.py
│ │ │ ├── assets
│ │ │ │ ├── icon-knowledge-transfer.svg
│ │ │ │ └── icon.svg
│ │ │ ├── assistant.py
│ │ │ ├── common.py
│ │ │ ├── config.py
│ │ │ ├── conversation_clients.py
│ │ │ ├── conversation_share_link.py
│ │ │ ├── data.py
│ │ │ ├── domain
│ │ │ │ ├── __init__.py
│ │ │ │ ├── audience_manager.py
│ │ │ │ ├── information_request_manager.py
│ │ │ │ ├── knowledge_brief_manager.py
│ │ │ │ ├── knowledge_digest_manager.py
│ │ │ │ ├── learning_objectives_manager.py
│ │ │ │ └── share_manager.py
│ │ │ ├── files.py
│ │ │ ├── logging.py
│ │ │ ├── notifications.py
│ │ │ ├── respond.py
│ │ │ ├── storage_models.py
│ │ │ ├── storage.py
│ │ │ ├── string_utils.py
│ │ │ ├── text_includes
│ │ │ │ ├── assistant_info.md
│ │ │ │ ├── card_content.md
│ │ │ │ ├── coordinator_instructions.txt
│ │ │ │ ├── coordinator_role.txt
│ │ │ │ ├── knowledge_digest_instructions.txt
│ │ │ │ ├── knowledge_digest_prompt.txt
│ │ │ │ ├── share_information_request_detection.txt
│ │ │ │ ├── team_instructions.txt
│ │ │ │ ├── team_role.txt
│ │ │ │ └── welcome_message_generation.txt
│ │ │ ├── tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── base.py
│ │ │ │ ├── information_requests.py
│ │ │ │ ├── learning_objectives.py
│ │ │ │ ├── learning_outcomes.py
│ │ │ │ ├── progress_tracking.py
│ │ │ │ └── share_setup.py
│ │ │ ├── ui_tabs
│ │ │ │ ├── __init__.py
│ │ │ │ ├── brief.py
│ │ │ │ ├── common.py
│ │ │ │ ├── debug.py
│ │ │ │ ├── learning.py
│ │ │ │ └── sharing.py
│ │ │ └── utils.py
│ │ ├── CLAUDE.md
│ │ ├── docs
│ │ │ ├── design
│ │ │ │ ├── actions.md
│ │ │ │ └── inference.md
│ │ │ ├── DEV_GUIDE.md
│ │ │ ├── how-kta-works.md
│ │ │ ├── JTBD.md
│ │ │ ├── knowledge-transfer-goals.md
│ │ │ ├── learning_assistance.md
│ │ │ ├── notable_claude_conversations
│ │ │ │ ├── clarifying_quad_modal_design.md
│ │ │ │ ├── CLAUDE_PROMPTS.md
│ │ │ │ ├── transfer_state.md
│ │ │ │ └── trying_the_context_agent.md
│ │ │ └── opportunities-of-knowledge-transfer.md
│ │ ├── knowledge-transfer-assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── __init__.py
│ │ │ ├── test_artifact_loading.py
│ │ │ ├── test_inspector.py
│ │ │ ├── test_share_manager.py
│ │ │ ├── test_share_storage.py
│ │ │ ├── test_share_tools.py
│ │ │ └── test_team_mode.py
│ │ └── uv.lock
│ ├── Makefile
│ ├── navigator-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── assets
│ │ │ │ ├── card_content.md
│ │ │ │ └── icon.svg
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── helpers.py
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── completion_handler.py
│ │ │ │ ├── completion_requestor.py
│ │ │ │ ├── local_tool
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── add_assistant_to_conversation.py
│ │ │ │ │ ├── list_assistant_services.py
│ │ │ │ │ └── model.py
│ │ │ │ ├── models.py
│ │ │ │ ├── prompt.py
│ │ │ │ ├── request_builder.py
│ │ │ │ ├── response.py
│ │ │ │ ├── step_handler.py
│ │ │ │ └── utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── formatting_utils.py
│ │ │ │ ├── message_utils.py
│ │ │ │ ├── openai_utils.py
│ │ │ │ └── tools.py
│ │ │ ├── text_includes
│ │ │ │ ├── guardrails_prompt.md
│ │ │ │ ├── guidance_prompt.md
│ │ │ │ ├── instruction_prompt.md
│ │ │ │ ├── navigator_assistant_info.md
│ │ │ │ └── semantic_workbench_features.md
│ │ │ └── whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── _inspector.py
│ │ │ └── _whiteboard.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── project-assistant
│ │ ├── .cspell
│ │ │ └── custom-dictionary-workspace.txt
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agentic
│ │ │ │ ├── __init__.py
│ │ │ │ ├── act.py
│ │ │ │ ├── coordinator_next_action.py
│ │ │ │ ├── create_invitation.py
│ │ │ │ ├── detect_audience_and_takeaways.py
│ │ │ │ ├── detect_coordinator_actions.py
│ │ │ │ ├── detect_information_request_needs.py
│ │ │ │ ├── detect_knowledge_package_gaps.py
│ │ │ │ ├── focus.py
│ │ │ │ ├── respond.py
│ │ │ │ ├── team_welcome.py
│ │ │ │ └── update_digest.py
│ │ │ ├── assets
│ │ │ │ ├── icon-knowledge-transfer.svg
│ │ │ │ └── icon.svg
│ │ │ ├── assistant.py
│ │ │ ├── common.py
│ │ │ ├── config.py
│ │ │ ├── conversation_clients.py
│ │ │ ├── data.py
│ │ │ ├── domain
│ │ │ │ ├── __init__.py
│ │ │ │ ├── audience_manager.py
│ │ │ │ ├── conversation_preferences_manager.py
│ │ │ │ ├── information_request_manager.py
│ │ │ │ ├── knowledge_brief_manager.py
│ │ │ │ ├── knowledge_digest_manager.py
│ │ │ │ ├── learning_objectives_manager.py
│ │ │ │ ├── share_manager.py
│ │ │ │ ├── tasks_manager.py
│ │ │ │ └── transfer_manager.py
│ │ │ ├── errors.py
│ │ │ ├── files.py
│ │ │ ├── logging.py
│ │ │ ├── notifications.py
│ │ │ ├── prompt_utils.py
│ │ │ ├── storage.py
│ │ │ ├── string_utils.py
│ │ │ ├── text_includes
│ │ │ │ ├── actor_instructions.md
│ │ │ │ ├── assistant_info.md
│ │ │ │ ├── card_content.md
│ │ │ │ ├── coordinator_instructions copy.md
│ │ │ │ ├── coordinator_instructions.md
│ │ │ │ ├── create_invitation.md
│ │ │ │ ├── detect_audience.md
│ │ │ │ ├── detect_coordinator_actions.md
│ │ │ │ ├── detect_information_request_needs.md
│ │ │ │ ├── detect_knowledge_package_gaps.md
│ │ │ │ ├── focus.md
│ │ │ │ ├── knowledge_digest_instructions.txt
│ │ │ │ ├── team_instructions.txt
│ │ │ │ ├── to_do.md
│ │ │ │ ├── update_knowledge_brief.md
│ │ │ │ ├── update_knowledge_digest.md
│ │ │ │ └── welcome_message_generation.txt
│ │ │ ├── tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── base.py
│ │ │ │ ├── conversation_preferences.py
│ │ │ │ ├── information_requests.py
│ │ │ │ ├── learning_objectives.py
│ │ │ │ ├── learning_outcomes.py
│ │ │ │ ├── progress_tracking.py
│ │ │ │ ├── share_setup.py
│ │ │ │ ├── system_reminders.py
│ │ │ │ ├── tasks.py
│ │ │ │ └── todo.py
│ │ │ ├── ui_tabs
│ │ │ │ ├── __init__.py
│ │ │ │ ├── brief.py
│ │ │ │ ├── common.py
│ │ │ │ ├── debug.py
│ │ │ │ ├── learning.py
│ │ │ │ └── sharing.py
│ │ │ └── utils.py
│ │ ├── CLAUDE.md
│ │ ├── docs
│ │ │ ├── design
│ │ │ │ ├── actions.md
│ │ │ │ ├── control_options.md
│ │ │ │ ├── design.md
│ │ │ │ ├── inference.md
│ │ │ │ └── PXL_20250814_190140267.jpg
│ │ │ ├── DEV_GUIDE.md
│ │ │ ├── how-kta-works.md
│ │ │ ├── JTBD.md
│ │ │ ├── knowledge-transfer-goals.md
│ │ │ ├── learning_assistance.md
│ │ │ ├── notable_claude_conversations
│ │ │ │ ├── clarifying_quad_modal_design.md
│ │ │ │ ├── CLAUDE_PROMPTS.md
│ │ │ │ ├── transfer_state.md
│ │ │ │ └── trying_the_context_agent.md
│ │ │ └── opportunities-of-knowledge-transfer.md
│ │ ├── knowledge-transfer-assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── __init__.py
│ │ │ ├── test_artifact_loading.py
│ │ │ ├── test_inspector.py
│ │ │ ├── test_share_manager.py
│ │ │ ├── test_share_storage.py
│ │ │ └── test_team_mode.py
│ │ └── uv.lock
│ ├── prospector-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agents
│ │ │ │ ├── artifact_agent.py
│ │ │ │ ├── document
│ │ │ │ │ ├── config.py
│ │ │ │ │ ├── gc_draft_content_feedback_config.py
│ │ │ │ │ ├── gc_draft_outline_feedback_config.py
│ │ │ │ │ ├── guided_conversation.py
│ │ │ │ │ └── state.py
│ │ │ │ └── document_agent.py
│ │ │ ├── artifact_creation_extension
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _llm.py
│ │ │ │ ├── config.py
│ │ │ │ ├── document.py
│ │ │ │ ├── extension.py
│ │ │ │ ├── store.py
│ │ │ │ ├── test
│ │ │ │ │ ├── conftest.py
│ │ │ │ │ ├── evaluation.py
│ │ │ │ │ ├── test_completion_with_tools.py
│ │ │ │ │ └── test_extension.py
│ │ │ │ └── tools.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── form_fill_extension
│ │ │ │ ├── __init__.py
│ │ │ │ ├── config.py
│ │ │ │ ├── extension.py
│ │ │ │ ├── inspector.py
│ │ │ │ ├── state.py
│ │ │ │ └── steps
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _guided_conversation.py
│ │ │ │ ├── _llm.py
│ │ │ │ ├── acquire_form_step.py
│ │ │ │ ├── extract_form_fields_step.py
│ │ │ │ ├── fill_form_step.py
│ │ │ │ └── types.py
│ │ │ ├── helpers.py
│ │ │ ├── legacy.py
│ │ │ └── text_includes
│ │ │ ├── artifact_agent_enabled.md
│ │ │ ├── guardrails_prompt.txt
│ │ │ ├── guided_conversation_agent_enabled.md
│ │ │ └── skills_agent_enabled.md
│ │ ├── assistant.code-workspace
│ │ ├── gc_learnings
│ │ │ ├── gc_learnings.md
│ │ │ └── images
│ │ │ ├── gc_conversation_plan_fcn.png
│ │ │ ├── gc_conversation_plan_template.png
│ │ │ ├── gc_execute_plan_callstack.png
│ │ │ ├── gc_functions.png
│ │ │ ├── gc_generate_plan_callstack.png
│ │ │ ├── gc_get_resource_instructions.png
│ │ │ ├── gc_get_termination_instructions.png
│ │ │ ├── gc_kernel_arguments.png
│ │ │ ├── gc_plan_calls.png
│ │ │ ├── gc_termination_instructions.png
│ │ │ ├── sk_get_chat_message_contents.png
│ │ │ ├── sk_inner_get_chat_message_contents.png
│ │ │ ├── sk_send_request_prep.png
│ │ │ └── sk_send_request.png
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ └── skill-assistant
│ ├── .env.example
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── assistant
│ │ ├── __init__.py
│ │ ├── config.py
│ │ ├── logging.py
│ │ ├── skill_assistant.py
│ │ ├── skill_engine_registry.py
│ │ ├── skill_event_mapper.py
│ │ ├── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ └── workbench_helpers.py
│ ├── assistant.code-workspace
│ ├── Makefile
│ ├── pyproject.toml
│ ├── README.md
│ ├── tests
│ │ └── test_setup.py
│ └── uv.lock
├── CLAUDE.md
├── CODE_OF_CONDUCT.md
├── CONTRIBUTING.md
├── docs
│ ├── .vscode
│ │ └── settings.json
│ ├── ASSISTANT_CONFIG.md
│ ├── ASSISTANT_DEVELOPMENT_GUIDE.md
│ ├── CUSTOM_APP_REGISTRATION.md
│ ├── HOSTED_ASSISTANT_WITH_LOCAL_MCP_SERVERS.md
│ ├── images
│ │ ├── architecture-animation.gif
│ │ ├── configure_assistant.png
│ │ ├── conversation_canvas_open.png
│ │ ├── conversation_duplicate.png
│ │ ├── conversation_export.png
│ │ ├── conversation_share_dialog.png
│ │ ├── conversation_share_link.png
│ │ ├── dashboard_configured_view.png
│ │ ├── dashboard_view.png
│ │ ├── license_agreement.png
│ │ ├── message_bar.png
│ │ ├── message_inspection.png
│ │ ├── message_link.png
│ │ ├── new_prospector_assistant_dialog.png
│ │ ├── open_conversation_canvas.png
│ │ ├── prospector_example.png
│ │ ├── readme1.png
│ │ ├── readme2.png
│ │ ├── readme3.png
│ │ ├── rewind.png
│ │ ├── signin_page.png
│ │ └── splash_screen.png
│ ├── LOCAL_ASSISTANT_WITH_REMOTE_WORKBENCH.md
│ ├── SETUP_DEV_ENVIRONMENT.md
│ └── WORKBENCH_APP.md
├── examples
│ ├── dotnet
│ │ ├── .editorconfig
│ │ ├── dotnet-01-echo-bot
│ │ │ ├── appsettings.json
│ │ │ ├── dotnet-01-echo-bot.csproj
│ │ │ ├── MyAgent.cs
│ │ │ ├── MyAgentConfig.cs
│ │ │ ├── MyWorkbenchConnector.cs
│ │ │ ├── Program.cs
│ │ │ └── README.md
│ │ ├── dotnet-02-message-types-demo
│ │ │ ├── appsettings.json
│ │ │ ├── ConnectorExtensions.cs
│ │ │ ├── docs
│ │ │ │ ├── abc.png
│ │ │ │ ├── code.png
│ │ │ │ ├── config.png
│ │ │ │ ├── echo.png
│ │ │ │ ├── markdown.png
│ │ │ │ ├── mermaid.png
│ │ │ │ ├── reverse.png
│ │ │ │ └── safety-check.png
│ │ │ ├── dotnet-02-message-types-demo.csproj
│ │ │ ├── MyAgent.cs
│ │ │ ├── MyAgentConfig.cs
│ │ │ ├── MyWorkbenchConnector.cs
│ │ │ ├── Program.cs
│ │ │ └── README.md
│ │ └── dotnet-03-simple-chatbot
│ │ ├── appsettings.json
│ │ ├── ConnectorExtensions.cs
│ │ ├── dotnet-03-simple-chatbot.csproj
│ │ ├── MyAgent.cs
│ │ ├── MyAgentConfig.cs
│ │ ├── MyWorkbenchConnector.cs
│ │ ├── Program.cs
│ │ └── README.md
│ ├── Makefile
│ └── python
│ ├── python-01-echo-bot
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── chat.py
│ │ │ └── config.py
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── python-02-simple-chatbot
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ └── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ └── python-03-multimodel-chatbot
│ ├── .env.example
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── assistant
│ │ ├── __init__.py
│ │ ├── chat.py
│ │ ├── config.py
│ │ ├── model_adapters.py
│ │ └── text_includes
│ │ └── guardrails_prompt.txt
│ ├── assistant.code-workspace
│ ├── Makefile
│ ├── pyproject.toml
│ ├── README.md
│ └── uv.lock
├── KNOWN_ISSUES.md
├── libraries
│ ├── dotnet
│ │ ├── .editorconfig
│ │ ├── pack.sh
│ │ ├── README.md
│ │ ├── SemanticWorkbench.sln
│ │ ├── SemanticWorkbench.sln.DotSettings
│ │ └── WorkbenchConnector
│ │ ├── AgentBase.cs
│ │ ├── AgentConfig
│ │ │ ├── AgentConfigBase.cs
│ │ │ ├── AgentConfigPropertyAttribute.cs
│ │ │ └── ConfigUtils.cs
│ │ ├── Constants.cs
│ │ ├── IAgentBase.cs
│ │ ├── icon.png
│ │ ├── Models
│ │ │ ├── Command.cs
│ │ │ ├── Conversation.cs
│ │ │ ├── ConversationEvent.cs
│ │ │ ├── DebugInfo.cs
│ │ │ ├── Insight.cs
│ │ │ ├── Message.cs
│ │ │ ├── MessageMetadata.cs
│ │ │ ├── Participant.cs
│ │ │ ├── Sender.cs
│ │ │ └── ServiceInfo.cs
│ │ ├── Storage
│ │ │ ├── AgentInfo.cs
│ │ │ ├── AgentServiceStorage.cs
│ │ │ └── IAgentServiceStorage.cs
│ │ ├── StringLoggingExtensions.cs
│ │ ├── Webservice.cs
│ │ ├── WorkbenchConfig.cs
│ │ ├── WorkbenchConnector.cs
│ │ └── WorkbenchConnector.csproj
│ ├── Makefile
│ └── python
│ ├── anthropic-client
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── anthropic_client
│ │ │ ├── __init__.py
│ │ │ ├── client.py
│ │ │ ├── config.py
│ │ │ └── messages.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── assistant-data-gen
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant_data_gen
│ │ │ ├── __init__.py
│ │ │ ├── assistant_api.py
│ │ │ ├── config.py
│ │ │ ├── gce
│ │ │ │ ├── __init__.py
│ │ │ │ ├── gce_agent.py
│ │ │ │ └── prompts.py
│ │ │ └── pydantic_ai_utils.py
│ │ ├── configs
│ │ │ └── document_assistant_example_config.yaml
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── scripts
│ │ │ ├── gce_simulation.py
│ │ │ └── generate_scenario.py
│ │ └── uv.lock
│ ├── assistant-drive
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── extensions.json
│ │ │ └── settings.json
│ │ ├── assistant_drive
│ │ │ ├── __init__.py
│ │ │ ├── drive.py
│ │ │ └── tests
│ │ │ └── test_basic.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── pytest.ini
│ │ ├── README.md
│ │ ├── usage.ipynb
│ │ └── uv.lock
│ ├── assistant-extensions
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── assistant_extensions
│ │ │ ├── __init__.py
│ │ │ ├── ai_clients
│ │ │ │ └── config.py
│ │ │ ├── artifacts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _artifacts.py
│ │ │ │ ├── _inspector.py
│ │ │ │ └── _model.py
│ │ │ ├── attachments
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _attachments.py
│ │ │ │ ├── _convert.py
│ │ │ │ ├── _model.py
│ │ │ │ ├── _shared.py
│ │ │ │ └── _summarizer.py
│ │ │ ├── chat_context_toolkit
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _config.py
│ │ │ │ ├── archive
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── _archive.py
│ │ │ │ │ └── _summarizer.py
│ │ │ │ ├── message_history
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── _history.py
│ │ │ │ │ └── _message.py
│ │ │ │ └── virtual_filesystem
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _archive_file_source.py
│ │ │ │ └── _attachments_file_source.py
│ │ │ ├── dashboard_card
│ │ │ │ ├── __init__.py
│ │ │ │ └── _dashboard_card.py
│ │ │ ├── document_editor
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _extension.py
│ │ │ │ ├── _inspector.py
│ │ │ │ └── _model.py
│ │ │ ├── mcp
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _assistant_file_resource_handler.py
│ │ │ │ ├── _client_utils.py
│ │ │ │ ├── _devtunnel.py
│ │ │ │ ├── _model.py
│ │ │ │ ├── _openai_utils.py
│ │ │ │ ├── _sampling_handler.py
│ │ │ │ ├── _tool_utils.py
│ │ │ │ └── _workbench_file_resource_handler.py
│ │ │ ├── navigator
│ │ │ │ ├── __init__.py
│ │ │ │ └── _navigator.py
│ │ │ └── workflows
│ │ │ ├── __init__.py
│ │ │ ├── _model.py
│ │ │ ├── _workflows.py
│ │ │ └── runners
│ │ │ └── _user_proxy.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── test
│ │ │ └── attachments
│ │ │ └── test_attachments.py
│ │ └── uv.lock
│ ├── chat-context-toolkit
│ │ ├── .claude
│ │ │ └── settings.local.json
│ │ ├── .env.sample
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── assets
│ │ │ ├── archive_v1.png
│ │ │ ├── history_v1.png
│ │ │ └── vfs_v1.png
│ │ ├── chat_context_toolkit
│ │ │ ├── __init__.py
│ │ │ ├── archive
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _archive_reader.py
│ │ │ │ ├── _archive_task_queue.py
│ │ │ │ ├── _state.py
│ │ │ │ ├── _types.py
│ │ │ │ └── summarization
│ │ │ │ ├── __init__.py
│ │ │ │ └── _summarizer.py
│ │ │ ├── history
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _budget.py
│ │ │ │ ├── _decorators.py
│ │ │ │ ├── _history.py
│ │ │ │ ├── _prioritize.py
│ │ │ │ ├── _types.py
│ │ │ │ └── tool_abbreviations
│ │ │ │ ├── __init__.py
│ │ │ │ └── _tool_abbreviations.py
│ │ │ └── virtual_filesystem
│ │ │ ├── __init__.py
│ │ │ ├── _types.py
│ │ │ ├── _virtual_filesystem.py
│ │ │ ├── README.md
│ │ │ └── tools
│ │ │ ├── __init__.py
│ │ │ ├── _ls_tool.py
│ │ │ ├── _tools.py
│ │ │ └── _view_tool.py
│ │ ├── CLAUDE.md
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── test
│ │ │ ├── archive
│ │ │ │ └── test_archive_reader.py
│ │ │ ├── history
│ │ │ │ ├── test_abbreviate_messages.py
│ │ │ │ ├── test_history.py
│ │ │ │ ├── test_pair_and_order_tool_messages.py
│ │ │ │ ├── test_prioritize.py
│ │ │ │ └── test_truncate_messages.py
│ │ │ └── virtual_filesystem
│ │ │ ├── test_virtual_filesystem.py
│ │ │ └── tools
│ │ │ ├── test_ls_tool.py
│ │ │ ├── test_tools.py
│ │ │ └── test_view_tool.py
│ │ └── uv.lock
│ ├── content-safety
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── content_safety
│ │ │ ├── __init__.py
│ │ │ ├── evaluators
│ │ │ │ ├── __init__.py
│ │ │ │ ├── azure_content_safety
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── config.py
│ │ │ │ │ └── evaluator.py
│ │ │ │ ├── config.py
│ │ │ │ ├── evaluator.py
│ │ │ │ └── openai_moderations
│ │ │ │ ├── __init__.py
│ │ │ │ ├── config.py
│ │ │ │ └── evaluator.py
│ │ │ └── README.md
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── events
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── events
│ │ │ ├── __init__.py
│ │ │ └── events.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── guided-conversation
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── guided_conversation
│ │ │ ├── __init__.py
│ │ │ ├── functions
│ │ │ │ ├── __init__.py
│ │ │ │ ├── conversation_plan.py
│ │ │ │ ├── execution.py
│ │ │ │ └── final_update_plan.py
│ │ │ ├── guided_conversation_agent.py
│ │ │ ├── plugins
│ │ │ │ ├── __init__.py
│ │ │ │ ├── agenda.py
│ │ │ │ └── artifact.py
│ │ │ └── utils
│ │ │ ├── __init__.py
│ │ │ ├── base_model_llm.py
│ │ │ ├── conversation_helpers.py
│ │ │ ├── openai_tool_calling.py
│ │ │ ├── plugin_helpers.py
│ │ │ └── resources.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── llm-client
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── llm_client
│ │ │ ├── __init__.py
│ │ │ └── model.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── Makefile
│ ├── mcp-extensions
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_extensions
│ │ │ ├── __init__.py
│ │ │ ├── _client_session.py
│ │ │ ├── _model.py
│ │ │ ├── _sampling.py
│ │ │ ├── _server_extensions.py
│ │ │ ├── _tool_utils.py
│ │ │ ├── llm
│ │ │ │ ├── __init__.py
│ │ │ │ ├── chat_completion.py
│ │ │ │ ├── helpers.py
│ │ │ │ ├── llm_types.py
│ │ │ │ ├── mcp_chat_completion.py
│ │ │ │ └── openai_chat_completion.py
│ │ │ └── server
│ │ │ ├── __init__.py
│ │ │ └── storage.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_tool_utils.py
│ │ └── uv.lock
│ ├── mcp-tunnel
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_tunnel
│ │ │ ├── __init__.py
│ │ │ ├── _devtunnel.py
│ │ │ ├── _dir.py
│ │ │ └── _main.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── openai-client
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── openai_client
│ │ │ ├── __init__.py
│ │ │ ├── chat_driver
│ │ │ │ ├── __init__.py
│ │ │ │ ├── chat_driver.ipynb
│ │ │ │ ├── chat_driver.py
│ │ │ │ ├── message_history_providers
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── in_memory_message_history_provider.py
│ │ │ │ │ ├── local_message_history_provider.py
│ │ │ │ │ ├── message_history_provider.py
│ │ │ │ │ └── tests
│ │ │ │ │ └── formatted_instructions_test.py
│ │ │ │ └── README.md
│ │ │ ├── client.py
│ │ │ ├── completion.py
│ │ │ ├── config.py
│ │ │ ├── errors.py
│ │ │ ├── logging.py
│ │ │ ├── messages.py
│ │ │ ├── tokens.py
│ │ │ └── tools.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── test_command_parsing.py
│ │ │ ├── test_formatted_messages.py
│ │ │ ├── test_messages.py
│ │ │ └── test_tokens.py
│ │ └── uv.lock
│ ├── semantic-workbench-api-model
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── semantic_workbench_api_model
│ │ │ ├── __init__.py
│ │ │ ├── assistant_model.py
│ │ │ ├── assistant_service_client.py
│ │ │ ├── workbench_model.py
│ │ │ └── workbench_service_client.py
│ │ └── uv.lock
│ ├── semantic-workbench-assistant
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── semantic_workbench_assistant
│ │ │ ├── __init__.py
│ │ │ ├── assistant_app
│ │ │ │ ├── __init__.py
│ │ │ │ ├── assistant.py
│ │ │ │ ├── config.py
│ │ │ │ ├── content_safety.py
│ │ │ │ ├── context.py
│ │ │ │ ├── error.py
│ │ │ │ ├── export_import.py
│ │ │ │ ├── protocol.py
│ │ │ │ └── service.py
│ │ │ ├── assistant_service.py
│ │ │ ├── auth.py
│ │ │ ├── canonical.py
│ │ │ ├── command.py
│ │ │ ├── config.py
│ │ │ ├── logging_config.py
│ │ │ ├── settings.py
│ │ │ ├── start.py
│ │ │ └── storage.py
│ │ ├── tests
│ │ │ ├── conftest.py
│ │ │ ├── test_assistant_app.py
│ │ │ ├── test_canonical.py
│ │ │ ├── test_config.py
│ │ │ └── test_storage.py
│ │ └── uv.lock
│ └── skills
│ ├── .vscode
│ │ └── settings.json
│ ├── Makefile
│ ├── README.md
│ └── skill-library
│ ├── .vscode
│ │ └── settings.json
│ ├── docs
│ │ └── vs-recipe-tool.md
│ ├── Makefile
│ ├── pyproject.toml
│ ├── README.md
│ ├── skill_library
│ │ ├── __init__.py
│ │ ├── chat_driver_helpers.py
│ │ ├── cli
│ │ │ ├── azure_openai.py
│ │ │ ├── conversation_history.py
│ │ │ ├── README.md
│ │ │ ├── run_routine.py
│ │ │ ├── settings.py
│ │ │ └── skill_logger.py
│ │ ├── engine.py
│ │ ├── llm_info.txt
│ │ ├── logging.py
│ │ ├── README.md
│ │ ├── routine_stack.py
│ │ ├── skill.py
│ │ ├── skills
│ │ │ ├── common
│ │ │ │ ├── __init__.py
│ │ │ │ ├── common_skill.py
│ │ │ │ └── routines
│ │ │ │ ├── bing_search.py
│ │ │ │ ├── consolidate.py
│ │ │ │ ├── echo.py
│ │ │ │ ├── gather_context.py
│ │ │ │ ├── get_content_from_url.py
│ │ │ │ ├── gpt_complete.py
│ │ │ │ ├── select_user_intent.py
│ │ │ │ └── summarize.py
│ │ │ ├── eval
│ │ │ │ ├── __init__.py
│ │ │ │ ├── eval_skill.py
│ │ │ │ └── routines
│ │ │ │ └── eval.py
│ │ │ ├── fabric
│ │ │ │ ├── __init__.py
│ │ │ │ ├── fabric_skill.py
│ │ │ │ ├── patterns
│ │ │ │ │ ├── agility_story
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── ai
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_answers
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_candidates
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_cfp_submission
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_claims
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_comments
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_debate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_email_headers
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_incident
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_interviewer_techniques
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_logs
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_malware
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_military_strategy
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_mistakes
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_paper
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_patent
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_personality
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_presentation
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_product_feedback
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_proposition
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_prose
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_prose_json
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_prose_pinker
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_risk
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_sales_call
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_spiritual_text
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_tech_impact
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_threat_report
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_threat_report_cmds
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_threat_report_trends
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── answer_interview_question
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── ask_secure_by_design_questions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── ask_uncle_duke
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── capture_thinkers_work
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── check_agreement
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── clean_text
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── coding_master
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── compare_and_contrast
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── convert_to_markdown
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_5_sentence_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_academic_paper
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_ai_jobs_analysis
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_aphorisms
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_art_prompt
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_better_frame
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_coding_project
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_command
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_cyber_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_design_document
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_diy
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_formal_email
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_git_diff_commit
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_graph_from_input
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_hormozi_offer
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_idea_compass
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_investigation_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_keynote
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_logo
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_markmap_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_mermaid_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_mermaid_visualization_for_github
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_micro_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_network_threat_landscape
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_newsletter_entry
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_npc
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_pattern
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_prd
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_prediction_block
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_quiz
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_reading_plan
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_recursive_outline
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_report_finding
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_rpg_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_security_update
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_show_intro
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_sigma_rules
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_story_explanation
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_stride_threat_model
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_tags
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_threat_scenarios
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_ttrc_graph
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_ttrc_narrative
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_upgrade_pack
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_user_story
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_video_chapters
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── dialog_with_socrates
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── enrich_blog_post
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── explain_code
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── explain_docs
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── explain_math
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── explain_project
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── explain_terms
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── export_data_as_csv
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_algorithm_update_recommendations
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_article_wisdom
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── extract_wisdom-1.0.0
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_book_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_book_recommendations
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_business_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_controversial_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_core_message
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_ctf_writeup
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_domains
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_extraordinary_claims
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_insights
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_insights_dm
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_instructions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_jokes
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_latest_video
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_main_idea
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_most_redeeming_thing
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_patterns
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_poc
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_predictions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_primary_problem
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_primary_solution
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_product_features
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── extract_wisdom-1.0.0
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_questions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_recipe
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_recommendations
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_references
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_skills
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_song_meaning
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_sponsors
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_videoid
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_wisdom
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── extract_wisdom-1.0.0
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_wisdom_agents
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_wisdom_dm
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_wisdom_nometa
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── find_hidden_message
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── find_logical_fallacies
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── get_wow_per_minute
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── get_youtube_rss
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── humanize
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_distinctions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_perspectives
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_relationships
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_systems
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_job_stories
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── improve_academic_writing
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── improve_prompt
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── improve_report_finding
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── improve_writing
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── judge_output
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── label_and_rate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── loaded
│ │ │ │ │ ├── md_callout
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── official_pattern_template
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── pattern_explanations.md
│ │ │ │ │ ├── prepare_7s_strategy
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── provide_guidance
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── rate_ai_response
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── rate_ai_result
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── rate_content
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── rate_value
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── raw_query
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── raycast
│ │ │ │ │ │ ├── capture_thinkers_work
│ │ │ │ │ │ ├── create_story_explanation
│ │ │ │ │ │ ├── extract_primary_problem
│ │ │ │ │ │ ├── extract_wisdom
│ │ │ │ │ │ └── yt
│ │ │ │ │ ├── recommend_artists
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── recommend_pipeline_upgrades
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── recommend_talkpanel_topics
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── refine_design_document
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── review_design
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── sanitize_broken_html_to_markdown
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── show_fabric_options_markmap
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── solve_with_cot
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── stringify
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── suggest_pattern
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── summarize
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_debate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_git_changes
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_git_diff
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_lecture
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_legislation
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_meeting
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_micro
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_newsletter
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_paper
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_prompt
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_pull-requests
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_rpg_session
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_analyze_challenge_handling
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_check_metrics
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_create_h3_career
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_create_opening_sentences
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_describe_life_outlook
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_extract_intro_sentences
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_extract_panel_topics
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_find_blindspots
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_find_negative_thinking
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_find_neglected_goals
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_give_encouragement
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_red_team_thinking
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_threat_model_plans
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_visualize_mission_goals_projects
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_year_in_review
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── to_flashcards
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── transcribe_minutes
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── translate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── tweet
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_essay
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_hackerone_report
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_latex
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_micro_essay
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_nuclei_template_rule
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── write_pull-request
│ │ │ │ │ │ └── system.md
│ │ │ │ │ └── write_semgrep_rule
│ │ │ │ │ ├── system.md
│ │ │ │ │ └── user.md
│ │ │ │ └── routines
│ │ │ │ ├── list.py
│ │ │ │ ├── run.py
│ │ │ │ └── show.py
│ │ │ ├── guided_conversation
│ │ │ │ ├── __init__.py
│ │ │ │ ├── agenda.py
│ │ │ │ ├── artifact_helpers.py
│ │ │ │ ├── chat_completions
│ │ │ │ │ ├── fix_agenda_error.py
│ │ │ │ │ ├── fix_artifact_error.py
│ │ │ │ │ ├── generate_agenda.py
│ │ │ │ │ ├── generate_artifact_updates.py
│ │ │ │ │ ├── generate_final_artifact.py
│ │ │ │ │ └── generate_message.py
│ │ │ │ ├── conversation_guides
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── acrostic_poem.py
│ │ │ │ │ ├── er_triage.py
│ │ │ │ │ ├── interview.py
│ │ │ │ │ └── patient_intake.py
│ │ │ │ ├── guide.py
│ │ │ │ ├── guided_conversation_skill.py
│ │ │ │ ├── logging.py
│ │ │ │ ├── message.py
│ │ │ │ ├── resources.py
│ │ │ │ ├── routines
│ │ │ │ │ └── guided_conversation.py
│ │ │ │ └── tests
│ │ │ │ ├── conftest.py
│ │ │ │ ├── test_artifact_helpers.py
│ │ │ │ ├── test_generate_agenda.py
│ │ │ │ ├── test_generate_artifact_updates.py
│ │ │ │ ├── test_generate_final_artifact.py
│ │ │ │ └── test_resource.py
│ │ │ ├── meta
│ │ │ │ ├── __init__.py
│ │ │ │ ├── meta_skill.py
│ │ │ │ ├── README.md
│ │ │ │ └── routines
│ │ │ │ └── generate_routine.py
│ │ │ ├── posix
│ │ │ │ ├── __init__.py
│ │ │ │ ├── posix_skill.py
│ │ │ │ ├── routines
│ │ │ │ │ ├── append_file.py
│ │ │ │ │ ├── cd.py
│ │ │ │ │ ├── ls.py
│ │ │ │ │ ├── make_home_dir.py
│ │ │ │ │ ├── mkdir.py
│ │ │ │ │ ├── mv.py
│ │ │ │ │ ├── pwd.py
│ │ │ │ │ ├── read_file.py
│ │ │ │ │ ├── rm.py
│ │ │ │ │ ├── touch.py
│ │ │ │ │ └── write_file.py
│ │ │ │ └── sandbox_shell.py
│ │ │ ├── README.md
│ │ │ ├── research
│ │ │ │ ├── __init__.py
│ │ │ │ ├── README.md
│ │ │ │ ├── research_skill.py
│ │ │ │ └── routines
│ │ │ │ ├── answer_question_about_content.py
│ │ │ │ ├── evaluate_answer.py
│ │ │ │ ├── generate_research_plan.py
│ │ │ │ ├── generate_search_query.py
│ │ │ │ ├── update_research_plan.py
│ │ │ │ ├── web_research.py
│ │ │ │ └── web_search.py
│ │ │ ├── research2
│ │ │ │ ├── __init__.py
│ │ │ │ ├── README.md
│ │ │ │ ├── research_skill.py
│ │ │ │ └── routines
│ │ │ │ ├── facts.py
│ │ │ │ ├── make_final_report.py
│ │ │ │ ├── research.py
│ │ │ │ ├── search_plan.py
│ │ │ │ ├── search.py
│ │ │ │ └── visit_pages.py
│ │ │ └── web_research
│ │ │ ├── __init__.py
│ │ │ ├── README.md
│ │ │ ├── research_skill.py
│ │ │ └── routines
│ │ │ ├── facts.py
│ │ │ ├── make_final_report.py
│ │ │ ├── research.py
│ │ │ ├── search_plan.py
│ │ │ ├── search.py
│ │ │ └── visit_pages.py
│ │ ├── tests
│ │ │ ├── test_common_skill.py
│ │ │ ├── test_integration.py
│ │ │ ├── test_routine_stack.py
│ │ │ ├── tst_skill
│ │ │ │ ├── __init__.py
│ │ │ │ └── routines
│ │ │ │ ├── __init__.py
│ │ │ │ └── a_routine.py
│ │ │ └── utilities
│ │ │ ├── test_find_template_vars.py
│ │ │ ├── test_make_arg_set.py
│ │ │ ├── test_paramspec.py
│ │ │ ├── test_parse_command_string.py
│ │ │ └── test_to_string.py
│ │ ├── types.py
│ │ ├── usage.py
│ │ └── utilities.py
│ └── uv.lock
├── LICENSE
├── Makefile
├── mcp-servers
│ ├── ai-assist-content
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── mcp-example-brave-search.md
│ │ ├── mcp-fastmcp-typescript-README.md
│ │ ├── mcp-llms-full.txt
│ │ ├── mcp-metadata-tips.md
│ │ ├── mcp-python-sdk-README.md
│ │ ├── mcp-typescript-sdk-README.md
│ │ ├── pydanticai-documentation.md
│ │ ├── pydanticai-example-question-graph.md
│ │ ├── pydanticai-example-weather.md
│ │ ├── pydanticai-tutorial.md
│ │ └── README.md
│ ├── Makefile
│ ├── mcp-server-bing-search
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_bing_search
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── prompts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── clean_website.py
│ │ │ │ └── filter_links.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ ├── tools.py
│ │ │ ├── types.py
│ │ │ ├── utils.py
│ │ │ └── web
│ │ │ ├── __init__.py
│ │ │ ├── get_content.py
│ │ │ ├── llm_processing.py
│ │ │ ├── process_website.py
│ │ │ └── search_bing.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_tools.py
│ │ └── uv.lock
│ ├── mcp-server-bundle
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_bundle
│ │ │ ├── __init__.py
│ │ │ └── main.py
│ │ ├── pyinstaller.spec
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-filesystem
│ │ ├── .env.example
│ │ ├── .github
│ │ │ └── workflows
│ │ │ └── ci.yml
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_filesystem
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_filesystem.py
│ │ └── uv.lock
│ ├── mcp-server-filesystem-edit
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── data
│ │ │ ├── attachments
│ │ │ │ ├── Daily Game Ideas.txt
│ │ │ │ ├── Frontend Framework Proposal.txt
│ │ │ │ ├── ReDoodle.txt
│ │ │ │ └── Research Template.tex
│ │ │ ├── test_cases.yaml
│ │ │ └── transcripts
│ │ │ ├── transcript_research_simple.md
│ │ │ ├── transcript_Startup_Idea_1_202503031513.md
│ │ │ ├── transcript_Startup_Idea_2_202503031659.md
│ │ │ └── transcript_Web_Frontends_202502281551.md
│ │ ├── Makefile
│ │ ├── mcp_server_filesystem_edit
│ │ │ ├── __init__.py
│ │ │ ├── app_handling
│ │ │ │ ├── __init__.py
│ │ │ │ ├── excel.py
│ │ │ │ ├── miktex.py
│ │ │ │ ├── office_common.py
│ │ │ │ ├── powerpoint.py
│ │ │ │ └── word.py
│ │ │ ├── config.py
│ │ │ ├── evals
│ │ │ │ ├── __init__.py
│ │ │ │ ├── common.py
│ │ │ │ ├── run_comments.py
│ │ │ │ ├── run_edit.py
│ │ │ │ └── run_ppt_edit.py
│ │ │ ├── prompts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── add_comments.py
│ │ │ │ ├── analyze_comments.py
│ │ │ │ ├── latex_edit.py
│ │ │ │ ├── markdown_draft.py
│ │ │ │ ├── markdown_edit.py
│ │ │ │ └── powerpoint_edit.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ ├── tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── add_comments.py
│ │ │ │ ├── edit_adapters
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── common.py
│ │ │ │ │ ├── latex.py
│ │ │ │ │ └── markdown.py
│ │ │ │ ├── edit.py
│ │ │ │ └── helpers.py
│ │ │ └── types.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── app_handling
│ │ │ │ ├── test_excel.py
│ │ │ │ ├── test_miktext.py
│ │ │ │ ├── test_office_common.py
│ │ │ │ ├── test_powerpoint.py
│ │ │ │ └── test_word.py
│ │ │ ├── conftest.py
│ │ │ └── tools
│ │ │ └── edit_adapters
│ │ │ ├── test_latex.py
│ │ │ └── test_markdown.py
│ │ └── uv.lock
│ ├── mcp-server-fusion
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── AddInIcon.svg
│ │ ├── config.py
│ │ ├── FusionMCPServerAddIn.manifest
│ │ ├── FusionMCPServerAddIn.py
│ │ ├── mcp_server_fusion
│ │ │ ├── __init__.py
│ │ │ ├── fusion_mcp_server.py
│ │ │ ├── fusion_utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── event_utils.py
│ │ │ │ ├── general_utils.py
│ │ │ │ └── tool_utils.py
│ │ │ ├── mcp_tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── fusion_3d_operation.py
│ │ │ │ ├── fusion_geometry.py
│ │ │ │ ├── fusion_pattern.py
│ │ │ │ └── fusion_sketch.py
│ │ │ └── vendor
│ │ │ └── README.md
│ │ ├── README.md
│ │ └── requirements.txt
│ ├── mcp-server-giphy
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── giphy_search.py
│ │ │ ├── sampling.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ └── utils.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-memory-user-bio
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_memory_user_bio
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-memory-whiteboard
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_memory_whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-office
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── build.sh
│ │ ├── data
│ │ │ ├── attachments
│ │ │ │ ├── Daily Game Ideas.txt
│ │ │ │ ├── Frontend Framework Proposal.txt
│ │ │ │ └── ReDoodle.txt
│ │ │ └── word
│ │ │ ├── test_cases.yaml
│ │ │ └── transcripts
│ │ │ ├── transcript_Startup_Idea_1_202503031513.md
│ │ │ ├── transcript_Startup_Idea_2_202503031659.md
│ │ │ └── transcript_Web_Frontends_202502281551.md
│ │ ├── Makefile
│ │ ├── mcp_server
│ │ │ ├── __init__.py
│ │ │ ├── app_interaction
│ │ │ │ ├── __init__.py
│ │ │ │ ├── excel_editor.py
│ │ │ │ ├── powerpoint_editor.py
│ │ │ │ └── word_editor.py
│ │ │ ├── config.py
│ │ │ ├── constants.py
│ │ │ ├── evals
│ │ │ │ ├── __init__.py
│ │ │ │ ├── common.py
│ │ │ │ ├── run_comment_analysis.py
│ │ │ │ ├── run_feedback.py
│ │ │ │ └── run_markdown_edit.py
│ │ │ ├── helpers.py
│ │ │ ├── markdown_edit
│ │ │ │ ├── __init__.py
│ │ │ │ ├── comment_analysis.py
│ │ │ │ ├── feedback_step.py
│ │ │ │ ├── markdown_edit.py
│ │ │ │ └── utils.py
│ │ │ ├── prompts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── comment_analysis.py
│ │ │ │ ├── feedback.py
│ │ │ │ ├── markdown_draft.py
│ │ │ │ └── markdown_edit.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ └── types.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_word_editor.py
│ │ └── uv.lock
│ ├── mcp-server-open-deep-research
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── libs
│ │ │ │ └── open_deep_research
│ │ │ │ ├── cookies.py
│ │ │ │ ├── mdconvert.py
│ │ │ │ ├── run_agents.py
│ │ │ │ ├── text_inspector_tool.py
│ │ │ │ ├── text_web_browser.py
│ │ │ │ └── visual_qa.py
│ │ │ ├── open_deep_research.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-open-deep-research-clone
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_open_deep_research_clone
│ │ │ ├── __init__.py
│ │ │ ├── azure_openai.py
│ │ │ ├── config.py
│ │ │ ├── logging.py
│ │ │ ├── sampling.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ ├── utils.py
│ │ │ └── web_research.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── test
│ │ │ └── test_open_deep_research_clone.py
│ │ └── uv.lock
│ ├── mcp-server-template
│ │ ├── .taplo.toml
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── copier.yml
│ │ ├── README.md
│ │ └── template
│ │ └── {{ project_slug }}
│ │ ├── .env.example.jinja
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json.jinja
│ │ │ └── settings.json
│ │ ├── {{ module_name }}
│ │ │ ├── __init__.py
│ │ │ ├── config.py.jinja
│ │ │ ├── server.py.jinja
│ │ │ └── start.py.jinja
│ │ ├── Makefile.jinja
│ │ ├── pyproject.toml.jinja
│ │ └── README.md.jinja
│ ├── mcp-server-vscode
│ │ ├── .eslintrc.cjs
│ │ ├── .gitignore
│ │ ├── .npmrc
│ │ ├── .vscode
│ │ │ ├── extensions.json
│ │ │ ├── launch.json
│ │ │ ├── settings.json
│ │ │ └── tasks.json
│ │ ├── .vscode-test.mjs
│ │ ├── .vscodeignore
│ │ ├── ASSISTANT_BOOTSTRAP.md
│ │ ├── eslint.config.mjs
│ │ ├── images
│ │ │ └── icon.png
│ │ ├── LICENSE
│ │ ├── Makefile
│ │ ├── out
│ │ │ ├── extension.d.ts
│ │ │ ├── extension.js
│ │ │ ├── test
│ │ │ │ ├── extension.test.d.ts
│ │ │ │ └── extension.test.js
│ │ │ ├── tools
│ │ │ │ ├── code_checker.d.ts
│ │ │ │ ├── code_checker.js
│ │ │ │ ├── debug_tools.d.ts
│ │ │ │ ├── debug_tools.js
│ │ │ │ ├── focus_editor.d.ts
│ │ │ │ ├── focus_editor.js
│ │ │ │ ├── search_symbol.d.ts
│ │ │ │ └── search_symbol.js
│ │ │ └── utils
│ │ │ ├── port.d.ts
│ │ │ └── port.js
│ │ ├── package.json
│ │ ├── pnpm-lock.yaml
│ │ ├── prettier.config.cjs
│ │ ├── README.md
│ │ ├── src
│ │ │ ├── extension.d.ts
│ │ │ ├── extension.ts
│ │ │ ├── test
│ │ │ │ ├── extension.test.d.ts
│ │ │ │ └── extension.test.ts
│ │ │ ├── tools
│ │ │ │ ├── code_checker.d.ts
│ │ │ │ ├── code_checker.ts
│ │ │ │ ├── debug_tools.d.ts
│ │ │ │ ├── debug_tools.ts
│ │ │ │ ├── focus_editor.d.ts
│ │ │ │ ├── focus_editor.ts
│ │ │ │ ├── search_symbol.d.ts
│ │ │ │ └── search_symbol.ts
│ │ │ └── utils
│ │ │ ├── port.d.ts
│ │ │ └── port.ts
│ │ ├── tsconfig.json
│ │ ├── tsconfig.tsbuildinfo
│ │ ├── vsc-extension-quickstart.md
│ │ └── webpack.config.js
│ └── mcp-server-web-research
│ ├── .env.example
│ ├── .gitignore
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── Makefile
│ ├── mcp_server_web_research
│ │ ├── __init__.py
│ │ ├── azure_openai.py
│ │ ├── config.py
│ │ ├── logging.py
│ │ ├── sampling.py
│ │ ├── server.py
│ │ ├── start.py
│ │ ├── utils.py
│ │ └── web_research.py
│ ├── pyproject.toml
│ ├── README.md
│ ├── test
│ │ └── test_web_research.py
│ └── uv.lock
├── README.md
├── RESPONSIBLE_AI_FAQ.md
├── ruff.toml
├── SECURITY.md
├── semantic-workbench.code-workspace
├── SUPPORT.md
├── tools
│ ├── build_ai_context_files.py
│ ├── collect_files.py
│ ├── docker
│ │ ├── azure_website_sshd.conf
│ │ ├── docker-entrypoint.sh
│ │ ├── Dockerfile.assistant
│ │ └── Dockerfile.mcp-server
│ ├── makefiles
│ │ ├── docker-assistant.mk
│ │ ├── docker-mcp-server.mk
│ │ ├── docker.mk
│ │ ├── python.mk
│ │ ├── recursive.mk
│ │ └── shell.mk
│ ├── reset-service-data.ps1
│ ├── reset-service-data.sh
│ ├── run-app.ps1
│ ├── run-app.sh
│ ├── run-canonical-agent.ps1
│ ├── run-canonical-agent.sh
│ ├── run-dotnet-examples-with-aspire.sh
│ ├── run-python-example1.sh
│ ├── run-python-example2.ps1
│ ├── run-python-example2.sh
│ ├── run-service.ps1
│ ├── run-service.sh
│ ├── run-workbench-chatbot.ps1
│ └── run-workbench-chatbot.sh
├── workbench-app
│ ├── .dockerignore
│ ├── .env.example
│ ├── .eslintrc.cjs
│ ├── .gitignore
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── docker-entrypoint.sh
│ ├── Dockerfile
│ ├── docs
│ │ ├── APP_DEV_GUIDE.md
│ │ ├── MESSAGE_METADATA.md
│ │ ├── MESSAGE_TYPES.md
│ │ ├── README.md
│ │ └── STATE_INSPECTORS.md
│ ├── index.html
│ ├── Makefile
│ ├── nginx.conf
│ ├── package.json
│ ├── pnpm-lock.yaml
│ ├── prettier.config.cjs
│ ├── public
│ │ └── assets
│ │ ├── background-1-upscaled.jpg
│ │ ├── background-1-upscaled.png
│ │ ├── background-1.jpg
│ │ ├── background-1.png
│ │ ├── background-2.jpg
│ │ ├── background-2.png
│ │ ├── experimental-feature.jpg
│ │ ├── favicon.svg
│ │ ├── workflow-designer-1.jpg
│ │ ├── workflow-designer-outlets.jpg
│ │ ├── workflow-designer-states.jpg
│ │ └── workflow-designer-transitions.jpg
│ ├── README.md
│ ├── run.sh
│ ├── src
│ │ ├── components
│ │ │ ├── App
│ │ │ │ ├── AppFooter.tsx
│ │ │ │ ├── AppHeader.tsx
│ │ │ │ ├── AppMenu.tsx
│ │ │ │ ├── AppView.tsx
│ │ │ │ ├── CodeLabel.tsx
│ │ │ │ ├── CommandButton.tsx
│ │ │ │ ├── ConfirmLeave.tsx
│ │ │ │ ├── ContentExport.tsx
│ │ │ │ ├── ContentImport.tsx
│ │ │ │ ├── CopyButton.tsx
│ │ │ │ ├── DialogControl.tsx
│ │ │ │ ├── DynamicIframe.tsx
│ │ │ │ ├── ErrorListFromAppState.tsx
│ │ │ │ ├── ErrorMessageBar.tsx
│ │ │ │ ├── ExperimentalNotice.tsx
│ │ │ │ ├── FormWidgets
│ │ │ │ │ ├── BaseModelEditorWidget.tsx
│ │ │ │ │ ├── CustomizedArrayFieldTemplate.tsx
│ │ │ │ │ ├── CustomizedFieldTemplate.tsx
│ │ │ │ │ ├── CustomizedObjectFieldTemplate.tsx
│ │ │ │ │ └── InspectableWidget.tsx
│ │ │ │ ├── LabelWithDescription.tsx
│ │ │ │ ├── Loading.tsx
│ │ │ │ ├── MenuItemControl.tsx
│ │ │ │ ├── MiniControl.tsx
│ │ │ │ ├── MyAssistantServiceRegistrations.tsx
│ │ │ │ ├── MyItemsManager.tsx
│ │ │ │ ├── OverflowMenu.tsx
│ │ │ │ ├── PresenceMotionList.tsx
│ │ │ │ ├── ProfileSettings.tsx
│ │ │ │ └── TooltipWrapper.tsx
│ │ │ ├── Assistants
│ │ │ │ ├── ApplyConfigButton.tsx
│ │ │ │ ├── AssistantAdd.tsx
│ │ │ │ ├── AssistantConfigExportButton.tsx
│ │ │ │ ├── AssistantConfigImportButton.tsx
│ │ │ │ ├── AssistantConfiguration.tsx
│ │ │ │ ├── AssistantConfigure.tsx
│ │ │ │ ├── AssistantCreate.tsx
│ │ │ │ ├── AssistantDelete.tsx
│ │ │ │ ├── AssistantDuplicate.tsx
│ │ │ │ ├── AssistantExport.tsx
│ │ │ │ ├── AssistantImport.tsx
│ │ │ │ ├── AssistantRemove.tsx
│ │ │ │ ├── AssistantRename.tsx
│ │ │ │ ├── AssistantServiceInfo.tsx
│ │ │ │ ├── AssistantServiceMetadata.tsx
│ │ │ │ └── MyAssistants.tsx
│ │ │ ├── AssistantServiceRegistrations
│ │ │ │ ├── AssistantServiceRegistrationApiKey.tsx
│ │ │ │ ├── AssistantServiceRegistrationApiKeyReset.tsx
│ │ │ │ ├── AssistantServiceRegistrationCreate.tsx
│ │ │ │ └── AssistantServiceRegistrationRemove.tsx
│ │ │ ├── Conversations
│ │ │ │ ├── Canvas
│ │ │ │ │ ├── AssistantCanvas.tsx
│ │ │ │ │ ├── AssistantCanvasList.tsx
│ │ │ │ │ ├── AssistantInspector.tsx
│ │ │ │ │ ├── AssistantInspectorList.tsx
│ │ │ │ │ └── ConversationCanvas.tsx
│ │ │ │ ├── ChatInputPlugins
│ │ │ │ │ ├── ClearEditorPlugin.tsx
│ │ │ │ │ ├── LexicalMenu.ts
│ │ │ │ │ ├── ParticipantMentionsPlugin.tsx
│ │ │ │ │ ├── TypeaheadMenuPlugin.css
│ │ │ │ │ └── TypeaheadMenuPlugin.tsx
│ │ │ │ ├── ContentRenderers
│ │ │ │ │ ├── CodeContentRenderer.tsx
│ │ │ │ │ ├── ContentListRenderer.tsx
│ │ │ │ │ ├── ContentRenderer.tsx
│ │ │ │ │ ├── DiffRenderer.tsx
│ │ │ │ │ ├── HtmlContentRenderer.tsx
│ │ │ │ │ ├── JsonSchemaContentRenderer.tsx
│ │ │ │ │ ├── MarkdownContentRenderer.tsx
│ │ │ │ │ ├── MarkdownEditorRenderer.tsx
│ │ │ │ │ ├── MermaidContentRenderer.tsx
│ │ │ │ │ ├── MusicABCContentRenderer.css
│ │ │ │ │ └── MusicABCContentRenderer.tsx
│ │ │ │ ├── ContextWindow.tsx
│ │ │ │ ├── ConversationCreate.tsx
│ │ │ │ ├── ConversationDuplicate.tsx
│ │ │ │ ├── ConversationExport.tsx
│ │ │ │ ├── ConversationFileIcon.tsx
│ │ │ │ ├── ConversationRemove.tsx
│ │ │ │ ├── ConversationRename.tsx
│ │ │ │ ├── ConversationShare.tsx
│ │ │ │ ├── ConversationShareCreate.tsx
│ │ │ │ ├── ConversationShareList.tsx
│ │ │ │ ├── ConversationShareView.tsx
│ │ │ │ ├── ConversationsImport.tsx
│ │ │ │ ├── ConversationTranscript.tsx
│ │ │ │ ├── DebugInspector.tsx
│ │ │ │ ├── FileItem.tsx
│ │ │ │ ├── FileList.tsx
│ │ │ │ ├── InputAttachmentList.tsx
│ │ │ │ ├── InputOptionsControl.tsx
│ │ │ │ ├── InteractHistory.tsx
│ │ │ │ ├── InteractInput.tsx
│ │ │ │ ├── Message
│ │ │ │ │ ├── AttachmentSection.tsx
│ │ │ │ │ ├── ContentRenderer.tsx
│ │ │ │ │ ├── ContentSafetyNotice.tsx
│ │ │ │ │ ├── InteractMessage.tsx
│ │ │ │ │ ├── MessageActions.tsx
│ │ │ │ │ ├── MessageBase.tsx
│ │ │ │ │ ├── MessageBody.tsx
│ │ │ │ │ ├── MessageContent.tsx
│ │ │ │ │ ├── MessageFooter.tsx
│ │ │ │ │ ├── MessageHeader.tsx
│ │ │ │ │ ├── NotificationAccordion.tsx
│ │ │ │ │ └── ToolResultMessage.tsx
│ │ │ │ ├── MessageDelete.tsx
│ │ │ │ ├── MessageLink.tsx
│ │ │ │ ├── MyConversations.tsx
│ │ │ │ ├── MyShares.tsx
│ │ │ │ ├── ParticipantAvatar.tsx
│ │ │ │ ├── ParticipantAvatarGroup.tsx
│ │ │ │ ├── ParticipantItem.tsx
│ │ │ │ ├── ParticipantList.tsx
│ │ │ │ ├── ParticipantStatus.tsx
│ │ │ │ ├── RewindConversation.tsx
│ │ │ │ ├── ShareRemove.tsx
│ │ │ │ ├── SpeechButton.tsx
│ │ │ │ └── ToolCalls.tsx
│ │ │ └── FrontDoor
│ │ │ ├── Chat
│ │ │ │ ├── AssistantDrawer.tsx
│ │ │ │ ├── CanvasDrawer.tsx
│ │ │ │ ├── Chat.tsx
│ │ │ │ ├── ChatCanvas.tsx
│ │ │ │ ├── ChatControls.tsx
│ │ │ │ └── ConversationDrawer.tsx
│ │ │ ├── Controls
│ │ │ │ ├── AssistantCard.tsx
│ │ │ │ ├── AssistantSelector.tsx
│ │ │ │ ├── AssistantServiceSelector.tsx
│ │ │ │ ├── ConversationItem.tsx
│ │ │ │ ├── ConversationList.tsx
│ │ │ │ ├── ConversationListOptions.tsx
│ │ │ │ ├── NewConversationButton.tsx
│ │ │ │ ├── NewConversationForm.tsx
│ │ │ │ └── SiteMenuButton.tsx
│ │ │ ├── GlobalContent.tsx
│ │ │ └── MainContent.tsx
│ │ ├── Constants.ts
│ │ ├── global.d.ts
│ │ ├── index.css
│ │ ├── libs
│ │ │ ├── AppStorage.ts
│ │ │ ├── AuthHelper.ts
│ │ │ ├── EventSubscriptionManager.ts
│ │ │ ├── Theme.ts
│ │ │ ├── useAssistantCapabilities.ts
│ │ │ ├── useChatCanvasController.ts
│ │ │ ├── useConversationEvents.ts
│ │ │ ├── useConversationUtility.ts
│ │ │ ├── useCreateConversation.ts
│ │ │ ├── useDebugComponentLifecycle.ts
│ │ │ ├── useDragAndDrop.ts
│ │ │ ├── useEnvironment.ts
│ │ │ ├── useExportUtility.ts
│ │ │ ├── useHistoryUtility.ts
│ │ │ ├── useKeySequence.ts
│ │ │ ├── useMediaQuery.ts
│ │ │ ├── useMicrosoftGraph.ts
│ │ │ ├── useNotify.tsx
│ │ │ ├── useParticipantUtility.tsx
│ │ │ ├── useSiteUtility.ts
│ │ │ ├── useWorkbenchEventSource.ts
│ │ │ ├── useWorkbenchService.ts
│ │ │ └── Utility.ts
│ │ ├── main.tsx
│ │ ├── models
│ │ │ ├── Assistant.ts
│ │ │ ├── AssistantCapability.ts
│ │ │ ├── AssistantServiceInfo.ts
│ │ │ ├── AssistantServiceRegistration.ts
│ │ │ ├── Config.ts
│ │ │ ├── Conversation.ts
│ │ │ ├── ConversationFile.ts
│ │ │ ├── ConversationMessage.ts
│ │ │ ├── ConversationMessageDebug.ts
│ │ │ ├── ConversationParticipant.ts
│ │ │ ├── ConversationShare.ts
│ │ │ ├── ConversationShareRedemption.ts
│ │ │ ├── ConversationState.ts
│ │ │ ├── ConversationStateDescription.ts
│ │ │ ├── ServiceEnvironment.ts
│ │ │ └── User.ts
│ │ ├── redux
│ │ │ ├── app
│ │ │ │ ├── hooks.ts
│ │ │ │ ├── rtkQueryErrorLogger.ts
│ │ │ │ └── store.ts
│ │ │ └── features
│ │ │ ├── app
│ │ │ │ ├── appSlice.ts
│ │ │ │ └── AppState.ts
│ │ │ ├── chatCanvas
│ │ │ │ ├── chatCanvasSlice.ts
│ │ │ │ └── ChatCanvasState.ts
│ │ │ ├── localUser
│ │ │ │ ├── localUserSlice.ts
│ │ │ │ └── LocalUserState.ts
│ │ │ └── settings
│ │ │ ├── settingsSlice.ts
│ │ │ └── SettingsState.ts
│ │ ├── Root.tsx
│ │ ├── routes
│ │ │ ├── AcceptTerms.tsx
│ │ │ ├── AssistantEditor.tsx
│ │ │ ├── AssistantServiceRegistrationEditor.tsx
│ │ │ ├── Dashboard.tsx
│ │ │ ├── ErrorPage.tsx
│ │ │ ├── FrontDoor.tsx
│ │ │ ├── Login.tsx
│ │ │ ├── Settings.tsx
│ │ │ ├── ShareRedeem.tsx
│ │ │ └── Shares.tsx
│ │ ├── services
│ │ │ └── workbench
│ │ │ ├── assistant.ts
│ │ │ ├── assistantService.ts
│ │ │ ├── conversation.ts
│ │ │ ├── file.ts
│ │ │ ├── index.ts
│ │ │ ├── participant.ts
│ │ │ ├── share.ts
│ │ │ ├── state.ts
│ │ │ └── workbench.ts
│ │ └── vite-env.d.ts
│ ├── tools
│ │ └── filtered-ts-prune.cjs
│ ├── tsconfig.json
│ └── vite.config.ts
└── workbench-service
├── .env.example
├── .vscode
│ ├── extensions.json
│ ├── launch.json
│ └── settings.json
├── alembic.ini
├── devdb
│ ├── docker-compose.yaml
│ └── postgresql-init.sh
├── Dockerfile
├── Makefile
├── migrations
│ ├── env.py
│ ├── README
│ ├── script.py.mako
│ └── versions
│ ├── 2024_09_19_000000_69dcda481c14_init.py
│ ├── 2024_09_19_190029_dffb1d7e219a_file_version_filename.py
│ ├── 2024_09_20_204130_b29524775484_share.py
│ ├── 2024_10_30_231536_039bec8edc33_index_message_type.py
│ ├── 2024_11_04_204029_5149c7fb5a32_conversationmessagedebug.py
│ ├── 2024_11_05_015124_245baf258e11_double_check_debugs.py
│ ├── 2024_11_25_191056_a106de176394_drop_workflow.py
│ ├── 2025_03_19_140136_aaaf792d4d72_set_user_title_set.py
│ ├── 2025_03_21_153250_3763629295ad_add_assistant_template_id.py
│ ├── 2025_05_19_163613_b2f86e981885_delete_context_transfer_assistants.py
│ └── 2025_06_18_174328_503c739152f3_delete_knowlege_transfer_assistants.py
├── pyproject.toml
├── README.md
├── semantic_workbench_service
│ ├── __init__.py
│ ├── api.py
│ ├── assistant_api_key.py
│ ├── auth.py
│ ├── azure_speech.py
│ ├── config.py
│ ├── controller
│ │ ├── __init__.py
│ │ ├── assistant_service_client_pool.py
│ │ ├── assistant_service_registration.py
│ │ ├── assistant.py
│ │ ├── conversation_share.py
│ │ ├── conversation.py
│ │ ├── convert.py
│ │ ├── exceptions.py
│ │ ├── export_import.py
│ │ ├── file.py
│ │ ├── participant.py
│ │ └── user.py
│ ├── db.py
│ ├── event.py
│ ├── files.py
│ ├── logging_config.py
│ ├── middleware.py
│ ├── query.py
│ ├── service_user_principals.py
│ ├── service.py
│ └── start.py
├── tests
│ ├── __init__.py
│ ├── conftest.py
│ ├── docker-compose.yaml
│ ├── test_assistant_api_key.py
│ ├── test_files.py
│ ├── test_integration.py
│ ├── test_middleware.py
│ ├── test_migrations.py
│ ├── test_workbench_service.py
│ └── types.py
└── uv.lock
```
# Files
--------------------------------------------------------------------------------
/libraries/python/skills/skill-library/skill_library/skills/fabric/patterns/pattern_explanations.md:
--------------------------------------------------------------------------------
```markdown
1 | Brief one-line summary from AI analysis of what each pattern does.
2 |
3 | - Key pattern to use: **suggest_pattern**, suggests appropriate fabric patterns or commands based on user input.**
4 |
5 | 1. **agility_story**: Generate a user story and acceptance criteria in JSON format based on the given topic.
6 | 2. **ai**: Interpret questions deeply and provide concise, insightful answers in Markdown bullet points.
7 | 3. **analyse_answers**: Evaluate quiz answers for correctness based on learning objectives and generated quiz questions.
8 | 4. **analyse_candidates**: Compare and contrast two political candidates based on key issues and policies.
9 | 5. **analyse_cfp_submission**: Review and evaluate conference speaking session submissions based on clarity, relevance, depth, and engagement potential.
10 | 6. **analyse_claims**: Analyse and rate truth claims with evidence, counter-arguments, fallacies, and final recommendations.
11 | 7. **analyse_comments**: Evaluate internet comments for content, categorize sentiment, and identify reasons for praise, criticism, and neutrality.
12 | 8. **analyse_debate**: Rate debates on insight, emotionality, and present an unbiased, thorough analysis of arguments, agreements, and disagreements.
13 | 9. **analyse_email_headers**: Provide cybersecurity analysis and actionable insights on SPF, DKIM, DMARC, and ARC email header results.
14 | 10. **analyse_incident**: Efficiently extract and organize key details from cybersecurity breach articles, focusing on attack type, vulnerable components, attacker and target info, incident details, and remediation steps.
15 | 11. **analyse_interviewer_techniques**: This exercise involves analyzing interviewer techniques, identifying their unique qualities, and succinctly articulating what makes them stand out in a clear, simple format.
16 | 12. **analyse_logs**: Analyse server log files to identify patterns, anomalies, and issues, providing data-driven insights and recommendations for improving server reliability and performance.
17 | 13. **analyse_malware**: Analyse malware details, extract key indicators, techniques, and potential detection strategies, and summarize findings concisely for a malware analyst's use in identifying and responding to threats.
18 | 14. **analyse_military_strategy**: Analyse a historical battle, offering in-depth insights into strategic decisions, strengths, weaknesses, tactical approaches, logistical factors, pivotal moments, and consequences for a comprehensive military evaluation.
19 | 15. **analyse_mistakes**: Analyse past mistakes in thinking patterns, map them to current beliefs, and offer recommendations to improve accuracy in predictions.
20 | 16. **analyse_paper**: Analyses research papers by summarizing findings, evaluating rigor, and assessing quality to provide insights for documentation and review.
21 | 17. **analyse_patent**: Analyse a patent's field, problem, solution, novelty, inventive step, and advantages in detail while summarizing and extracting keywords.
22 | 18. **analyze_personality**: Performs a deep psychological analysis of a person in the input, focusing on their behavior, language, and psychological traits.
23 | 19. **analyze_presentation**: Reviews and critiques presentations by analyzing the content, speaker's underlying goals, self-focus, and entertainment value.
24 | 20. **analyze_product_feedback**: A prompt for analyzing and organizing user feedback by identifying themes, consolidating similar comments, and prioritizing them based on usefulness.
25 | 21. **analyze_proposition**: Analyzes a ballot proposition by identifying its purpose, impact, arguments for and against, and relevant background information.
26 | 22. **analyze_prose**: Evaluates writing for novelty, clarity, and prose, providing ratings, improvement recommendations, and an overall score.
27 | 23. **analyze_prose_json**: Evaluates writing for novelty, clarity, prose, and provides ratings, explanations, improvement suggestions, and an overall score in a JSON format.
28 | 24. **analyze_prose_pinker**: Evaluates prose based on Steven Pinker's The Sense of Style, analyzing writing style, clarity, and bad writing elements.
29 | 25. **analyze_risk**: Conducts a risk assessment of a third-party vendor, assigning a risk score and suggesting security controls based on analysis of provided documents and vendor website.
30 | 26. **analyze_sales_call**: Rates sales call performance across multiple dimensions, providing scores and actionable feedback based on transcript analysis.
31 | 27. **analyze_spiritual_text**: Compares and contrasts spiritual texts by analyzing claims and differences with the King James Bible.
32 | 28. **analyze_tech_impact**: Analyzes the societal impact, ethical considerations, and sustainability of technology projects, evaluating their outcomes and benefits.
33 | 29. **analyze_threat_report**: Extracts surprising insights, trends, statistics, quotes, references, and recommendations from cybersecurity threat reports, summarizing key findings and providing actionable information.
34 | 30. **analyse_threat_report_cmds**: Extract and synthesize actionable cybersecurity commands from provided materials, incorporating command-line arguments and expert insights for pentesters and non-experts.
35 | 31. **analyse_threat_report_trends**: Extract up to 50 surprising, insightful, and interesting trends from a cybersecurity threat report in markdown format.
36 | 32. **answer_interview_question**: Generates concise, tailored responses to technical interview questions, incorporating alternative approaches and evidence to demonstrate the candidate's expertise and experience.
37 | 33. **ask_secure_by_design_questions**: Generates a set of security-focused questions to ensure a project is built securely by design, covering key components and considerations.
38 | 34. **ask_uncle_duke**: Coordinates a team of AI agents to research and produce multiple software development solutions based on provided specifications, and conducts detailed code reviews to ensure adherence to best practices.
39 | 35. **capture_thinkers_work**: Analyze philosophers or philosophies and provide detailed summaries about their teachings, background, works, advice, and related concepts in a structured template.
40 | 36. **check_agreement**: Analyze contracts and agreements to identify important stipulations, issues, and potential gotchas, then summarize them in Markdown.
41 | 37. **clean_text**: Fix broken or malformatted text by correcting line breaks, punctuation, capitalization, and paragraphs without altering content or spelling.
42 | 38. **coding_master**: Explain a coding concept to a beginner, providing examples, and formatting code in markdown with specific output sections like ideas, recommendations, facts, and insights.
43 | 39. **compare_and_contrast**: Compare and contrast a list of items in a markdown table, with items on the left and topics on top.
44 | 40. **convert_to_markdown**: Convert content to clean, complete Markdown format, preserving all original structure, formatting, links, and code blocks without alterations.
45 | 41. **create_5_sentence_summary**: Create concise summaries or answers to input at 5 different levels of depth, from 5 words to 1 word.
46 | 42. **create_academic_paper**: Generate a high-quality academic paper in LaTeX format with clear concepts, structured content, and a professional layout.
47 | 43. **create_ai_jobs_analysis**: Analyze job categories' susceptibility to automation, identify resilient roles, and provide strategies for personal adaptation to AI-driven changes in the workforce.
48 | 44. **create_aphorisms**: Find and generate a list of brief, witty statements.
49 | 45. **create_art_prompt**: Generates a detailed, compelling visual description of a concept, including stylistic references and direct AI instructions for creating art.
50 | 46. **create_better_frame**: Identifies and analyzes different frames of interpreting reality, emphasizing the power of positive, productive lenses in shaping outcomes.
51 | 47. **create_coding_project**: Generate wireframes and starter code for any coding ideas that you have.
52 | 48. **create_command**: Helps determine the correct parameters and switches for penetration testing tools based on a brief description of the objective.
53 | 49. create_cyber_summary: Summarizes cybersecurity threats, vulnerabilities, incidents, and malware with a 25-word summary and categorized bullet points, after thoroughly analyzing and mapping the provided input.
54 | 50. **create_design_document**: Creates a detailed design document for a system using the C4 model, addressing business and security postures, and including a system context diagram.
55 | 51. **create_diy**: Creates structured "Do It Yourself" tutorial patterns by analyzing prompts, organizing requirements, and providing step-by-step instructions in Markdown format.
56 | 52. **create_formal_email**: Crafts professional, clear, and respectful emails by analyzing context, tone, and purpose, ensuring proper structure and formatting.
57 | 53. **create_git_diff_commit**: Generates Git commands and commit messages for reflecting changes in a repository, using conventional commits and providing concise shell commands for updates.
58 | 54. **create_graph_from_input**: Generates a CSV file with progress-over-time data for a security program, focusing on relevant metrics and KPIs.
59 | 55. **create_hormozi_offer**: Creates a customized business offer based on principles from Alex Hormozi's book, "$100M Offers."
60 | 56. **create_idea_compass**: Organizes and structures ideas by exploring their definition, evidence, sources, and related themes or consequences.
61 | 57. **create_investigation_visualization**: Creates detailed Graphviz visualizations of complex input, highlighting key aspects and providing clear, well-annotated diagrams for investigative analysis and conclusions.
62 | 58. **create_keynote**: Creates TED-style keynote presentations with a clear narrative, structured slides, and speaker notes, emphasizing impactful takeaways and cohesive flow.
63 | 59. **create_logo**: Creates simple, minimalist company logos without text, generating AI prompts for vector graphic logos based on input.
64 | 60. **create_markmap_visualization**: Transforms complex ideas into clear visualizations using MarkMap syntax, simplifying concepts into diagrams with relationships, boxes, arrows, and labels.
65 | 61. **create_mermaid_visualization**: Creates detailed, standalone visualizations of concepts using Mermaid (Markdown) syntax, ensuring clarity and coherence in diagrams.
66 | 62. **create_mermaid_visualization_for_github**: Creates standalone, detailed visualizations using Mermaid (Markdown) syntax to effectively explain complex concepts, ensuring clarity and precision.
67 | 63. **create_micro_summary**: Summarizes content into a concise, 20-word summary with main points and takeaways, formatted in Markdown.
68 | 64. **create_network_threat_landscape**: Analyzes open ports and services from a network scan and generates a comprehensive, insightful, and detailed security threat report in Markdown.
69 | 65. **create_newsletter_entry**: Condenses provided article text into a concise, objective, newsletter-style summary with a title in the style of Frontend Weekly.
70 | 66. **create_npc**: Generates a detailed D&D 5E NPC, including background, flaws, stats, appearance, personality, goals, and more in Markdown format.
71 | 67. **create_pattern**: Extracts, organizes, and formats LLM/AI prompts into structured sections, detailing the AI’s role, instructions, output format, and any provided examples for clarity and accuracy.
72 | 68. **create_prd**: Creates a precise Product Requirements Document (PRD) in Markdown based on input.
73 | 69. **create_prediction_block**: Extracts and formats predictions from input into a structured Markdown block for a blog post.
74 | 70. **create_quiz**: Creates a three-phase reading plan based on an author or topic to help the user become significantly knowledgeable, including core, extended, and supplementary readings.
75 | 71. **create_reading_plan**: Generates review questions based on learning objectives from the input, adapted to the specified student level, and outputs them in a clear markdown format.
76 | 72. **create_recursive_outline**: Breaks down complex tasks or projects into manageable, hierarchical components with recursive outlining for clarity and simplicity.
77 | 73. **create_report_finding**: Creates a detailed, structured security finding report in markdown, including sections on Description, Risk, Recommendations, References, One-Sentence-Summary, and Quotes.
78 | 74. **create_rpg_summary**: Summarizes an in-person RPG session with key events, combat details, player stats, and role-playing highlights in a structured format.
79 | 75. **create_security_update**: Creates concise security updates for newsletters, covering stories, threats, advisories, vulnerabilities, and a summary of key issues.
80 | 76. **create_show_intro**: Creates compelling short intros for podcasts, summarizing key topics and themes discussed in the episode.
81 | 77. **create_sigma_rules**: Extracts Tactics, Techniques, and Procedures (TTPs) from security news and converts them into Sigma detection rules for host-based detections.
82 | 78. **create_story_explanation**: Summarizes complex content in a clear, approachable story format that makes the concepts easy to understand.
83 | 79. **create_stride_threat_model**: Create a STRIDE-based threat model for a system design, identifying assets, trust boundaries, data flows, and prioritizing threats with mitigations.
84 | 80. **create_summary**: Summarizes content into a 20-word sentence, 10 main points (16 words max), and 5 key takeaways in Markdown format.
85 | 81. **create_tags**: Identifies at least 5 tags from text content for mind mapping tools, including authors and existing tags if present.
86 | 82. **create_threat_scenarios**: Identifies likely attack methods for any system by providing a narrative-based threat model, balancing risk and opportunity.
87 | 83. **create_ttrc_graph**: Creates a CSV file showing the progress of Time to Remediate Critical Vulnerabilities over time using given data.
88 | 84. **create_ttrc_narrative**: Creates a persuasive narrative highlighting progress in reducing the Time to Remediate Critical Vulnerabilities metric over time.
89 | 85. **create_upgrade_pack**: Extracts world model and task algorithm updates from content, providing beliefs about how the world works and task performance.
90 | 86. **create_user_story**: Writes concise and clear technical user stories for new features in complex software programs, formatted for all stakeholders.
91 | 87. **create_video_chapters**: Extracts interesting topics and timestamps from a transcript, providing concise summaries of key moments.
92 | 88. **create_visualization**: Transforms complex ideas into visualizations using intricate ASCII art, simplifying concepts where necessary.
93 | 89. **dialog_with_socrates**: Engages in deep, meaningful dialogues to explore and challenge beliefs using the Socratic method.
94 | 90. **enrich_blog_post**: Enhances Markdown blog files by applying instructions to improve structure, visuals, and readability for HTML rendering.
95 | 91. **explain_code**: Explains code, security tool output, configuration text, and answers questions based on the provided input.
96 | 92. **explain_docs**: Improves and restructures tool documentation into clear, concise instructions, including overviews, usage, use cases, and key features.
97 | 93. **explain_math**: Helps you understand mathematical concepts in a clear and engaging way.
98 | 94. **explain_project**: Summarizes project documentation into clear, concise sections covering the project, problem, solution, installation, usage, and examples.
99 | 95. **explain_terms**: Produces a glossary of advanced terms from content, providing a definition, analogy, and explanation of why each term matters.
100 | 96. **export_data_as_csv**: Extracts and outputs all data structures from the input in properly formatted CSV data.
101 | 97. **extract_algorithm_update_recommendations**: Extracts concise, practical algorithm update recommendations from the input and outputs them in a bulleted list.
102 | 98. **extract_article_wisdom**: Extracts surprising, insightful, and interesting information from content, categorizing it into sections like summary, ideas, quotes, facts, references, and recommendations.
103 | 99. **extract_book_ideas**: Extracts and outputs 50 to 100 of the most surprising, insightful, and interesting ideas from a book's content.
104 | 100. **extract_book_recommendations**: Extracts and outputs 50 to 100 practical, actionable recommendations from a book's content.
105 | 101. **extract_business_ideas**: Extracts top business ideas from content and elaborates on the best 10 with unique differentiators.
106 | 102. **extract_controversial_ideas**: Extracts and outputs controversial statements and supporting quotes from the input in a structured Markdown list.
107 | 103. **extract_core_message**: Extracts and outputs a clear, concise sentence that articulates the core message of a given text or body of work.
108 | 104. **extract_ctf_writeup**: Extracts a short writeup from a warstory-like text about a cyber security engagement.
109 | 105. **extract_extraordinary_claims**: Extracts and outputs a list of extraordinary claims from conversations, focusing on scientifically disputed or false statements.
110 | 106. **extract_ideas**: Extracts and outputs all the key ideas from input, presented as 15-word bullet points in Markdown.
111 | 107. **extract_insights**: Extracts and outputs the most powerful and insightful ideas from text, formatted as 16-word bullet points in the INSIGHTS section, also IDEAS section.
112 | 108. **extract_insights_dm**: Extracts and outputs all valuable insights and a concise summary of the content, including key points and topics discussed.
113 | 109. **extract_instructions**: Extracts clear, actionable step-by-step instructions and main objectives from instructional video transcripts, organizing them into a concise list.
114 | 110. **extract_jokes**: Extracts jokes from text content, presenting each joke with its punchline in separate bullet points.
115 | 111. **extract_latest_video**: Extracts the latest video URL from a YouTube RSS feed and outputs the URL only.
116 | 112. **extract_main_idea**: Extracts the main idea and key recommendation from the input, summarizing them in 15-word sentences.
117 | 113. **extract_most_redeeming_thing**: Extracts the most redeeming aspect from an input, summarizing it in a single 15-word sentence.
118 | 114. **extract_patterns**: Extracts and analyzes recurring, surprising, and insightful patterns from input, providing detailed analysis and advice for builders.
119 | 115. **extract_poc**: Extracts proof of concept URLs and validation methods from security reports, providing the URL and command to run.
120 | 116. **extract_predictions**: Extracts predictions from input, including specific details such as date, confidence level, and verification method.
121 | 117. **extract_primary_problem**: Extracts the primary problem with the world as presented in a given text or body of work.
122 | 118. **extract_primary_solution**: Extracts the primary solution for the world as presented in a given text or body of work.
123 | 119. **extract_product_features**: Extracts and outputs a list of product features from the provided input in a bulleted format.
124 | 120. **extract_questions**: Extracts and outputs all questions asked by the interviewer in a conversation or interview.
125 | 121. **extract_recipe**: Extracts and outputs a recipe with a short meal description, ingredients with measurements, and preparation steps.
126 | 122. **extract_recommendations**: Extracts and outputs concise, practical recommendations from a given piece of content in a bulleted list.
127 | 123. **extract_references**: Extracts and outputs a bulleted list of references to art, stories, books, literature, and other sources from content.
128 | 124. **extract_skills**: Extracts and classifies skills from a job description into a table, separating each skill and classifying it as either hard or soft.
129 | 125. **extract_song_meaning**: Analyzes a song to provide a summary of its meaning, supported by detailed evidence from lyrics, artist commentary, and fan analysis.
130 | 126. **extract_sponsors** Extracts and lists official sponsors and potential sponsors from a provided transcript.
131 | 127. **extract_videoid**: Extracts and outputs the video ID from any given URL.
132 | 128. **extract_wisdom**: Extracts surprising, insightful, and interesting information from text on topics like human flourishing, AI, learning, and more.
133 | 129. **extract_wisdom_agents**: Extracts valuable insights, ideas, quotes, and references from content, emphasizing topics like human flourishing, AI, learning, and technology.
134 | 130. **extract_wisdom_dm**: Extracts all valuable, insightful, and thought-provoking information from content, focusing on topics like human flourishing, AI, learning, and technology.
135 | 131. **extract_wisdom_nometa**: Extracts insights, ideas, quotes, habits, facts, references, and recommendations from content, focusing on human flourishing, AI, technology, and related topics.
136 | 132. **find_hidden_message**: Extracts overt and hidden political messages, justifications, audience actions, and a cynical analysis from content.
137 | 133. **find_logical_fallacies**: Identifies and analyzes fallacies in arguments, classifying them as formal or informal with detailed reasoning.
138 | 134. **get_wow_per_minute**: Determines the wow-factor of content per minute based on surprise, novelty, insight, value, and wisdom, measuring how rewarding the content is for the viewer.
139 | 135. **get_youtube_rss**: Returns the RSS URL for a given YouTube channel based on the channel ID or URL.
140 | 136. **humanize**: Rewrites AI-generated text to sound natural, conversational, and easy to understand, maintaining clarity and simplicity.
141 | 137. **identify_dsrp_distinctions**: Encourages creative, systems-based thinking by exploring distinctions, boundaries, and their implications, drawing on insights from prominent systems thinkers.
142 | 138. **identify_dsrp_perspectives**: Explores the concept of distinctions in systems thinking, focusing on how boundaries define ideas, influence understanding, and reveal or obscure insights.
143 | 139. **identify_dsrp_relationships**: Encourages exploration of connections, distinctions, and boundaries between ideas, inspired by systems thinkers to reveal new insights and patterns in complex systems.
144 | 140. **identify_dsrp_systems**: Encourages organizing ideas into systems of parts and wholes, inspired by systems thinkers to explore relationships and how changes in organization impact meaning and understanding.
145 | 141. **identify_job_stories**: Identifies key job stories or requirements for roles.
146 | 142. **improve_academic_writing**: Refines text into clear, concise academic language while improving grammar, coherence, and clarity, with a list of changes.
147 | 143. **improve_prompt**: Improves an LLM/AI prompt by applying expert prompt writing strategies for better results and clarity.
148 | 144. **improve_report_finding**: Improves a penetration test security finding by providing detailed descriptions, risks, recommendations, references, quotes, and a concise summary in markdown format.
149 | 145. **improve_writing**: Refines text by correcting grammar, enhancing style, improving clarity, and maintaining the original meaning. skills.
150 | 146. **judge_output**: Evaluates Honeycomb queries by judging their effectiveness, providing critiques and outcomes based on language nuances and analytics relevance.
151 | 147. **label_and_rate**: Labels content with up to 20 single-word tags and rates it based on idea count and relevance to human meaning, AI, and other related themes, assigning a tier (S, A, B, C, D) and a quality score.
152 | 148. **md_callout**: Classifies content and generates a markdown callout based on the provided text, selecting the most appropriate type.
153 | 149. **official_pattern_template**: Template to use if you want to create new fabric patterns.
154 | 150. **prepare_7s_strategy**: Prepares a comprehensive briefing document from 7S's strategy capturing organizational profile, strategic elements, and market dynamics with clear, concise, and organized content.
155 | 151. **provide_guidance**: Provides psychological and life coaching advice, including analysis, recommendations, and potential diagnoses, with a compassionate and honest tone.
156 | 152. **rate_ai_response**: Rates the quality of AI responses by comparing them to top human expert performance, assigning a letter grade, reasoning, and providing a 1-100 score based on the evaluation.
157 | 153. **rate_ai_result**: Assesses the quality of AI/ML/LLM work by deeply analyzing content, instructions, and output, then rates performance based on multiple dimensions, including coverage, creativity, and interdisciplinary thinking.
158 | 154. **rate_content**: Labels content with up to 20 single-word tags and rates it based on idea count and relevance to human meaning, AI, and other related themes, assigning a tier (S, A, B, C, D) and a quality score.
159 | 155. **rate_value**: Produces the best possible output by deeply analyzing and understanding the input and its intended purpose.
160 | 156. **raw_query**: Fully digests and contemplates the input to produce the best possible result based on understanding the sender's intent.
161 | 157. **raycast**: Some scripts for Raycast, but think u need pro Raycast AI to use it
162 | 158. **recommend_artists**: Recommends a personalized festival schedule with artists aligned to your favorite styles and interests, including rationale.
163 | 159. **recommend_pipeline_upgrades**: Optimizes vulnerability-checking pipelines by incorporating new information and improving their efficiency, with detailed explanations of changes.
164 | 160. **recommend_talkpanel_topics**: Produces a clean set of proposed talks or panel talking points for a person based on their interests and goals, formatted for submission to a conference organizer.
165 | 161. **refine_design_document**: Refines a design document based on a design review by analyzing, mapping concepts, and implementing changes using valid Markdown.
166 | 162. **review_design**: Reviews and analyzes architecture design, focusing on clarity, component design, system integrations, security, performance, scalability, and data management.
167 | 163. **sanitize_broken_html_to_markdown**: Converts messy HTML into clean, properly formatted Markdown, applying custom styling and ensuring compatibility with Vite.
168 | 164. **show_fabric_options_markmap**: Visualizes the functionality of the Fabric framework by representing its components, commands, and features based on the provided input.
169 | 165. **solve_with_cot**: Provides detailed, step-by-step responses with chain of thought reasoning, using structured thinking, reflection, and output sections.
170 | 166. **suggest_pattern**: Suggests appropriate fabric patterns or commands based on user input, providing clear explanations and options for users.
171 | 167. **summarize**: Summarizes content into a 20-word sentence, main points, and takeaways, formatted with numbered lists in Markdown.
172 | 168. **summarize_debate**: Summarizes debates, identifies primary disagreement, extracts arguments, and provides analysis of evidence and argument strength to predict outcomes.
173 | 169. **summarize_git_changes**: Summarizes recent project updates from the last 7 days, focusing on key changes with enthusiasm.
174 | 170. **summarize_git_diff**: Summarizes and organizes Git diff changes with clear, succinct commit messages and bullet points.
175 | 171. **summarize_lecture**: Extracts relevant topics, definitions, and tools from lecture transcripts, providing structured summaries with timestamps and key takeaways.
176 | 172. **summarize_legislation**: Summarizes complex political proposals and legislation by analyzing key points, proposed changes, and providing balanced, positive, and cynical characterizations.
177 | 173. **summarize_meeting**: Analyzes meeting transcripts to extract a structured summary, including an overview, key points, tasks, decisions, challenges, timeline, references, and next steps.
178 | 174. **summarize_micro**: Summarizes content into a 20-word sentence, 3 main points, and 3 takeaways, formatted in clear, concise Markdown.
179 | 175. **summarize_newsletter**: Extracts the most meaningful, interesting, and useful content from a newsletter, summarizing key sections such as content, opinions, tools, companies, and follow-up items in clear, structured Markdown.
180 | 176. **summarize_paper**: Summarizes an academic paper by detailing its title, authors, technical approach, distinctive features, experimental setup, results, advantages, limitations, and conclusion in a clear, structured format using human-readable Markdown.
181 | 177. **summarize_prompt**: Summarizes AI chat prompts by describing the primary function, unique approach, and expected output in a concise paragraph. The summary is focused on the prompt's purpose without unnecessary details or formatting.
182 | 178. **summarize_pull-requests**: Summarizes pull requests for a coding project by providing a summary and listing the top PRs with human-readable descriptions.
183 | 179. **summarize_rpg_session**: Summarizes a role-playing game session by extracting key events, combat stats, character changes, quotes, and more.
184 | 180. **t_analyse_challenge_handling**: Provides 8-16 word bullet points evaluating how well challenges are being addressed, calling out any lack of effort.
185 | 181. **t_check_metrics**: Analyzes deep context from the TELOS file and input instruction, then provides a wisdom-based output while considering metrics and KPIs to assess recent improvements.
186 | 182. **t_create_h3_career**: Summarizes context and produces wisdom-based output by deeply analyzing both the TELOS File and the input instruction, considering the relationship between the two.
187 | 183. **t_create_opening_sentences**: Describes from TELOS file the person’s identity, goals, and actions in 4 concise, 32-word bullet points, humbly.
188 | 184. **t_describe_life_outlook**: Describes from TELOS file a person's life outlook in 5 concise, 16-word bullet points.
189 | 185. **t_extract_intro_sentences**: Summarizes from TELOS file a person's identity, work, and current projects in 5 concise and grounded bullet points.
190 | 186. **t_extract_panel_topics**: Creates 5 panel ideas with titles and descriptions based on deep context from a TELOS file and input.
191 | 187. **t_find_blindspots**: Identify potential blindspots in thinking, frames, or models that may expose the individual to error or risk.
192 | 188. **t_find_negative_thinking**: Analyze a TELOS file and input to identify negative thinking in documents or journals, followed by tough love encouragement.
193 | 189. **t_find_neglected_goals**: Analyze a TELOS file and input instructions to identify goals or projects that have not been worked on recently.
194 | 190. **t_give_encouragement**: Analyze a TELOS file and input instructions to evaluate progress, provide encouragement, and offer recommendations for continued effort.
195 | 191. **t_red_team_thinking**: Analyze a TELOS file and input instructions to red-team thinking, models, and frames, then provide recommendations for improvement.
196 | 192. **t_threat_model_plans**: Analyze a TELOS file and input instructions to create threat models for a life plan and recommend improvements.
197 | 193. **t_visualize_mission_goals_projects**: Analyze a TELOS file and input instructions to create an ASCII art diagram illustrating the relationship of missions, goals, and projects.
198 | 194. **t_year_in_review**: Analyze a TELOS file to create insights about a person or entity, then summarize accomplishments and visualizations in bullet points.
199 | 195. **to_flashcards**: Create Anki flashcards from a given text, focusing on concise, optimized questions and answers without external context.
200 | 196. **transcribe_minutes**: Extracts (from meeting transcription) meeting minutes, identifying actionables, insightful ideas, decisions, challenges, and next steps in a structured format.
201 | 197. **translate**: Translates sentences or documentation into the specified language code while maintaining the original formatting and tone.
202 | 198. **tweet**: Provides a step-by-step guide on crafting engaging tweets with emojis, covering Twitter basics, account creation, features, and audience targeting.
203 | 199. **write_essay**: Writes concise, clear essays in the style of Paul Graham, focusing on simplicity, clarity, and illumination of the provided topic.
204 | 200. **write_hackerone_report**: Generates concise, clear, and reproducible bug bounty reports, detailing vulnerability impact, steps to reproduce, and exploit details for triagers.
205 | 201. **write_latex**: Generates syntactically correct LaTeX code for a new.tex document, ensuring proper formatting and compatibility with pdflatex.
206 | 202. **write_micro_essay**: Writes concise, clear, and illuminating essays on the given topic in the style of Paul Graham.
207 | 203. **write_nuclei_template_rule**: Generates Nuclei YAML templates for detecting vulnerabilities using HTTP requests, matchers, extractors, and dynamic data extraction.
208 | 204. **write_pull-request**: Drafts detailed pull request descriptions, explaining changes, providing reasoning, and identifying potential bugs from the git diff command output.
209 | 205. **write_semgrep_rule**: Creates accurate and working Semgrep rules based on input, following syntax guidelines and specific language considerations.
210 |
```
--------------------------------------------------------------------------------
/libraries/python/skills/skill-library/skill_library/skills/fabric/patterns/improve_prompt/system.md:
--------------------------------------------------------------------------------
```markdown
1 | # IDENTITY and PURPOSE
2 |
3 | You are an expert LLM prompt writing service. You take an LLM/AI prompt as input and output a better prompt based on your prompt writing expertise and the knowledge below.
4 |
5 | START PROMPT WRITING KNOWLEDGE
6 |
7 | Prompt engineering
8 | This guide shares strategies and tactics for getting better results from large language models (sometimes referred to as GPT models) like GPT-4. The methods described here can sometimes be deployed in combination for greater effect. We encourage experimentation to find the methods that work best for you.
9 |
10 | Some of the examples demonstrated here currently work only with our most capable model, gpt-4. In general, if you find that a model fails at a task and a more capable model is available, it's often worth trying again with the more capable model.
11 |
12 | You can also explore example prompts which showcase what our models are capable of:
13 |
14 | Prompt examples
15 | Explore prompt examples to learn what GPT models can do
16 | Six strategies for getting better results
17 | Write clear instructions
18 | These models can’t read your mind. If outputs are too long, ask for brief replies. If outputs are too simple, ask for expert-level writing. If you dislike the format, demonstrate the format you’d like to see. The less the model has to guess at what you want, the more likely you’ll get it.
19 |
20 | Tactics:
21 |
22 | Include details in your query to get more relevant answers
23 | Ask the model to adopt a persona
24 | Use delimiters to clearly indicate distinct parts of the input
25 | Specify the steps required to complete a task
26 | Provide examples
27 | Specify the desired length of the output
28 | Provide reference text
29 | Language models can confidently invent fake answers, especially when asked about esoteric topics or for citations and URLs. In the same way that a sheet of notes can help a student do better on a test, providing reference text to these models can help in answering with fewer fabrications.
30 |
31 | Tactics:
32 |
33 | Instruct the model to answer using a reference text
34 | Instruct the model to answer with citations from a reference text
35 | Split complex tasks into simpler subtasks
36 | Just as it is good practice in software engineering to decompose a complex system into a set of modular components, the same is true of tasks submitted to a language model. Complex tasks tend to have higher error rates than simpler tasks. Furthermore, complex tasks can often be re-defined as a workflow of simpler tasks in which the outputs of earlier tasks are used to construct the inputs to later tasks.
37 |
38 | Tactics:
39 |
40 | Use intent classification to identify the most relevant instructions for a user query
41 | For dialogue applications that require very long conversations, summarize or filter previous dialogue
42 | Summarize long documents piecewise and construct a full summary recursively
43 | Give the model time to "think"
44 | If asked to multiply 17 by 28, you might not know it instantly, but can still work it out with time. Similarly, models make more reasoning errors when trying to answer right away, rather than taking time to work out an answer. Asking for a "chain of thought" before an answer can help the model reason its way toward correct answers more reliably.
45 |
46 | Tactics:
47 |
48 | Instruct the model to work out its own solution before rushing to a conclusion
49 | Use inner monologue or a sequence of queries to hide the model's reasoning process
50 | Ask the model if it missed anything on previous passes
51 | Use external tools
52 | Compensate for the weaknesses of the model by feeding it the outputs of other tools. For example, a text retrieval system (sometimes called RAG or retrieval augmented generation) can tell the model about relevant documents. A code execution engine like OpenAI's Code Interpreter can help the model do math and run code. If a task can be done more reliably or efficiently by a tool rather than by a language model, offload it to get the best of both.
53 |
54 | Tactics:
55 |
56 | Use embeddings-based search to implement efficient knowledge retrieval
57 | Use code execution to perform more accurate calculations or call external APIs
58 | Give the model access to specific functions
59 | Test changes systematically
60 | Improving performance is easier if you can measure it. In some cases a modification to a prompt will achieve better performance on a few isolated examples but lead to worse overall performance on a more representative set of examples. Therefore to be sure that a change is net positive to performance it may be necessary to define a comprehensive test suite (also known an as an "eval").
61 |
62 | Tactic:
63 |
64 | Evaluate model outputs with reference to gold-standard answers
65 | Tactics
66 | Each of the strategies listed above can be instantiated with specific tactics. These tactics are meant to provide ideas for things to try. They are by no means fully comprehensive, and you should feel free to try creative ideas not represented here.
67 |
68 | Strategy: Write clear instructions
69 | Tactic: Include details in your query to get more relevant answers
70 | In order to get a highly relevant response, make sure that requests provide any important details or context. Otherwise you are leaving it up to the model to guess what you mean.
71 |
72 | Worse Better
73 | How do I add numbers in Excel? How do I add up a row of dollar amounts in Excel? I want to do this automatically for a whole sheet of rows with all the totals ending up on the right in a column called "Total".
74 | Who’s president? Who was the president of Mexico in 2021, and how frequently are elections held?
75 | Write code to calculate the Fibonacci sequence. Write a TypeScript function to efficiently calculate the Fibonacci sequence. Comment the code liberally to explain what each piece does and why it's written that way.
76 | Summarize the meeting notes. Summarize the meeting notes in a single paragraph. Then write a markdown list of the speakers and each of their key points. Finally, list the next steps or action items suggested by the speakers, if any.
77 | Tactic: Ask the model to adopt a persona
78 | The system message can be used to specify the persona used by the model in its replies.
79 |
80 | SYSTEM
81 | When I ask for help to write something, you will reply with a document that contains at least one joke or playful comment in every paragraph.
82 | USER
83 | Write a thank you note to my steel bolt vendor for getting the delivery in on time and in short notice. This made it possible for us to deliver an important order.
84 |
85 | Tactic: Use delimiters to clearly indicate distinct parts of the input
86 | Delimiters like triple quotation marks, XML tags, section titles, etc. can help demarcate sections of text to be treated differently.
87 |
88 | USER
89 | Summarize the text delimited by triple quotes with a haiku.
90 |
91 | """insert text here"""
92 |
93 | SYSTEM
94 | You will be provided with a pair of articles (delimited with XML tags) about the same topic. First summarize the arguments of each article. Then indicate which of them makes a better argument and explain why.
95 | USER
96 |
97 | <article> insert first article here </article>
98 |
99 | <article> insert second article here </article>
100 |
101 | SYSTEM
102 | You will be provided with a thesis abstract and a suggested title for it. The thesis title should give the reader a good idea of the topic of the thesis but should also be eye-catching. If the title does not meet these criteria, suggest 5 alternatives.
103 | USER
104 | Abstract: insert abstract here
105 |
106 | Title: insert title here
107 |
108 | For straightforward tasks such as these, using delimiters might not make a difference in the output quality. However, the more complex a task is the more important it is to disambiguate task details. Don’t make the model work to understand exactly what you are asking of them.
109 |
110 | Tactic: Specify the steps required to complete a task
111 | Some tasks are best specified as a sequence of steps. Writing the steps out explicitly can make it easier for the model to follow them.
112 |
113 | SYSTEM
114 | Use the following step-by-step instructions to respond to user inputs.
115 |
116 | Step 1 - The user will provide you with text in triple quotes. Summarize this text in one sentence with a prefix that says "Summary: ".
117 |
118 | Step 2 - Translate the summary from Step 1 into Spanish, with a prefix that says "Translation: ".
119 | USER
120 | """insert text here"""
121 |
122 | Tactic: Provide examples
123 | Providing general instructions that apply to all examples is generally more efficient than demonstrating all permutations of a task by example, but in some cases providing examples may be easier. For example, if you intend for the model to copy a particular style of responding to user queries which is difficult to describe explicitly. This is known as "few-shot" prompting.
124 |
125 | SYSTEM
126 | Answer in a consistent style.
127 | USER
128 | Teach me about patience.
129 | ASSISTANT
130 | The river that carves the deepest valley flows from a modest spring; the grandest symphony originates from a single note; the most intricate tapestry begins with a solitary thread.
131 | USER
132 | Teach me about the ocean.
133 |
134 | Tactic: Specify the desired length of the output
135 | You can ask the model to produce outputs that are of a given target length. The targeted output length can be specified in terms of the count of words, sentences, paragraphs, bullet points, etc. Note however that instructing the model to generate a specific number of words does not work with high precision. The model can more reliably generate outputs with a specific number of paragraphs or bullet points.
136 |
137 | USER
138 | Summarize the text delimited by triple quotes in about 50 words.
139 |
140 | """insert text here"""
141 |
142 | USER
143 | Summarize the text delimited by triple quotes in 2 paragraphs.
144 |
145 | """insert text here"""
146 |
147 | USER
148 | Summarize the text delimited by triple quotes in 3 bullet points.
149 |
150 | """insert text here"""
151 |
152 | Strategy: Provide reference text
153 | Tactic: Instruct the model to answer using a reference text
154 | If we can provide a model with trusted information that is relevant to the current query, then we can instruct the model to use the provided information to compose its answer.
155 |
156 | SYSTEM
157 | Use the provided articles delimited by triple quotes to answer questions. If the answer cannot be found in the articles, write "I could not find an answer."
158 | USER
159 | <insert articles, each delimited by triple quotes>
160 |
161 | Question: <insert question here>
162 |
163 | Given that all models have limited context windows, we need some way to dynamically lookup information that is relevant to the question being asked. Embeddings can be used to implement efficient knowledge retrieval. See the tactic "Use embeddings-based search to implement efficient knowledge retrieval" for more details on how to implement this.
164 |
165 | Tactic: Instruct the model to answer with citations from a reference text
166 | If the input has been supplemented with relevant knowledge, it's straightforward to request that the model add citations to its answers by referencing passages from provided documents. Note that citations in the output can then be verified programmatically by string matching within the provided documents.
167 |
168 | SYSTEM
169 | You will be provided with a document delimited by triple quotes and a question. Your task is to answer the question using only the provided document and to cite the passage(s) of the document used to answer the question. If the document does not contain the information needed to answer this question then simply write: "Insufficient information." If an answer to the question is provided, it must be annotated with a citation. Use the following format for to cite relevant passages ({"citation": …}).
170 | USER
171 | """<insert document here>"""
172 |
173 | Question: <insert question here>
174 |
175 | Strategy: Split complex tasks into simpler subtasks
176 | Tactic: Use intent classification to identify the most relevant instructions for a user query
177 | For tasks in which lots of independent sets of instructions are needed to handle different cases, it can be beneficial to first classify the type of query and to use that classification to determine which instructions are needed. This can be achieved by defining fixed categories and hard-coding instructions that are relevant for handling tasks in a given category. This process can also be applied recursively to decompose a task into a sequence of stages. The advantage of this approach is that each query will contain only those instructions that are required to perform the next stage of a task which can result in lower error rates compared to using a single query to perform the whole task. This can also result in lower costs since larger prompts cost more to run (see pricing information).
178 |
179 | Suppose for example that for a customer service application, queries could be usefully classified as follows:
180 |
181 | SYSTEM
182 | You will be provided with customer service queries. Classify each query into a primary category and a secondary category. Provide your output in json format with the keys: primary and secondary.
183 |
184 | Primary categories: Billing, Technical Support, Account Management, or General Inquiry.
185 |
186 | Billing secondary categories:
187 |
188 | - Unsubscribe or upgrade
189 | - Add a payment method
190 | - Explanation for charge
191 | - Dispute a charge
192 |
193 | Technical Support secondary categories:
194 |
195 | - Troubleshooting
196 | - Device compatibility
197 | - Software updates
198 |
199 | Account Management secondary categories:
200 |
201 | - Password reset
202 | - Update personal information
203 | - Close account
204 | - Account security
205 |
206 | General Inquiry secondary categories:
207 |
208 | - Product information
209 | - Pricing
210 | - Feedback
211 | - Speak to a human
212 | USER
213 | I need to get my internet working again.
214 |
215 | Based on the classification of the customer query, a set of more specific instructions can be provided to a model for it to handle next steps. For example, suppose the customer requires help with "troubleshooting".
216 |
217 | SYSTEM
218 | You will be provided with customer service inquiries that require troubleshooting in a technical support context. Help the user by:
219 |
220 | - Ask them to check that all cables to/from the router are connected. Note that it is common for cables to come loose over time.
221 | - If all cables are connected and the issue persists, ask them which router model they are using
222 | - Now you will advise them how to restart their device:
223 | -- If the model number is MTD-327J, advise them to push the red button and hold it for 5 seconds, then wait 5 minutes before testing the connection.
224 | -- If the model number is MTD-327S, advise them to unplug and plug it back in, then wait 5 minutes before testing the connection.
225 | - If the customer's issue persists after restarting the device and waiting 5 minutes, connect them to IT support by outputting {"IT support requested"}.
226 | - If the user starts asking questions that are unrelated to this topic then confirm if they would like to end the current chat about troubleshooting and classify their request according to the following scheme:
227 |
228 | <insert primary/secondary classification scheme from above here>
229 | USER
230 | I need to get my internet working again.
231 |
232 | Notice that the model has been instructed to emit special strings to indicate when the state of the conversation changes. This enables us to turn our system into a state machine where the state determines which instructions are injected. By keeping track of state, what instructions are relevant at that state, and also optionally what state transitions are allowed from that state, we can put guardrails around the user experience that would be hard to achieve with a less structured approach.
233 |
234 | Tactic: For dialogue applications that require very long conversations, summarize or filter previous dialogue
235 | Since models have a fixed context length, dialogue between a user and an assistant in which the entire conversation is included in the context window cannot continue indefinitely.
236 |
237 | There are various workarounds to this problem, one of which is to summarize previous turns in the conversation. Once the size of the input reaches a predetermined threshold length, this could trigger a query that summarizes part of the conversation and the summary of the prior conversation could be included as part of the system message. Alternatively, prior conversation could be summarized asynchronously in the background throughout the entire conversation.
238 |
239 | An alternative solution is to dynamically select previous parts of the conversation that are most relevant to the current query. See the tactic "Use embeddings-based search to implement efficient knowledge retrieval".
240 |
241 | Tactic: Summarize long documents piecewise and construct a full summary recursively
242 | Since models have a fixed context length, they cannot be used to summarize a text longer than the context length minus the length of the generated summary in a single query.
243 |
244 | To summarize a very long document such as a book we can use a sequence of queries to summarize each section of the document. Section summaries can be concatenated and summarized producing summaries of summaries. This process can proceed recursively until an entire document is summarized. If it’s necessary to use information about earlier sections in order to make sense of later sections, then a further trick that can be useful is to include a running summary of the text that precedes any given point in the book while summarizing content at that point. The effectiveness of this procedure for summarizing books has been studied in previous research by OpenAI using variants of GPT-3.
245 |
246 | Strategy: Give models time to "think"
247 | Tactic: Instruct the model to work out its own solution before rushing to a conclusion
248 | Sometimes we get better results when we explicitly instruct the model to reason from first principles before coming to a conclusion. Suppose for example we want a model to evaluate a student’s solution to a math problem. The most obvious way to approach this is to simply ask the model if the student's solution is correct or not.
249 |
250 | SYSTEM
251 | Determine if the student's solution is correct or not.
252 | USER
253 | Problem Statement: I'm building a solar power installation and I need help working out the financials.
254 |
255 | - Land costs $100 / square foot
256 | - I can buy solar panels for $250 / square foot
257 | - I negotiated a contract for maintenance that will cost me a flat $100k per year, and an additional $10 / square foot
258 | What is the total cost for the first year of operations as a function of the number of square feet.
259 |
260 | Student's Solution: Let x be the size of the installation in square feet.
261 |
262 | 1. Land cost: 100x
263 | 2. Solar panel cost: 250x
264 | 3. Maintenance cost: 100,000 + 100x
265 | Total cost: 100x + 250x + 100,000 + 100x = 450x + 100,000
266 | ASSISTANT
267 | The student's solution is correct.
268 |
269 | But the student's solution is actually not correct! We can get the model to successfully notice this by prompting the model to generate its own solution first.
270 |
271 | SYSTEM
272 | First work out your own solution to the problem. Then compare your solution to the student's solution and evaluate if the student's solution is correct or not. Don't decide if the student's solution is correct until you have done the problem yourself.
273 | USER
274 | Problem Statement: I'm building a solar power installation and I need help working out the financials.
275 |
276 | - Land costs $100 / square foot
277 | - I can buy solar panels for $250 / square foot
278 | - I negotiated a contract for maintenance that will cost me a flat $100k per year, and an additional $10 / square foot
279 | What is the total cost for the first year of operations as a function of the number of square feet.
280 |
281 | Student's Solution: Let x be the size of the installation in square feet.
282 |
283 | 1. Land cost: 100x
284 | 2. Solar panel cost: 250x
285 | 3. Maintenance cost: 100,000 + 100x
286 | Total cost: 100x + 250x + 100,000 + 100x = 450x + 100,000
287 | ASSISTANT
288 | Let x be the size of the installation in square feet.
289 | 4. Land cost: 100x
290 | 5. Solar panel cost: 250x
291 | 6. Maintenance cost: 100,000 + 10x
292 | Total cost: 100x + 250x + 100,000 + 10x = 360x + 100,000
293 |
294 | The student's solution is incorrect. They made an error in the maintenance cost calculation, using 100x instead of 10x. The correct total cost for the first year of operations is 360x + 100,000.
295 |
296 | Tactic: Use inner monologue or a sequence of queries to hide the model's reasoning process
297 | The previous tactic demonstrates that it is sometimes important for the model to reason in detail about a problem before answering a specific question. For some applications, the reasoning process that a model uses to arrive at a final answer would be inappropriate to share with the user. For example, in tutoring applications we may want to encourage students to work out their own answers, but a model’s reasoning process about the student’s solution could reveal the answer to the student.
298 |
299 | Inner monologue is a tactic that can be used to mitigate this. The idea of inner monologue is to instruct the model to put parts of the output that are meant to be hidden from the user into a structured format that makes parsing them easy. Then before presenting the output to the user, the output is parsed and only part of the output is made visible.
300 |
301 | SYSTEM
302 | Follow these steps to answer the user queries.
303 |
304 | Step 1 - First work out your own solution to the problem. Don't rely on the student's solution since it may be incorrect. Enclose all your work for this step within triple quotes (""").
305 |
306 | Step 2 - Compare your solution to the student's solution and evaluate if the student's solution is correct or not. Enclose all your work for this step within triple quotes (""").
307 |
308 | Step 3 - If the student made a mistake, determine what hint you could give the student without giving away the answer. Enclose all your work for this step within triple quotes (""").
309 |
310 | Step 4 - If the student made a mistake, provide the hint from the previous step to the student (outside of triple quotes). Instead of writing "Step 4 - ..." write "Hint:".
311 | USER
312 | Problem Statement: <insert problem statement>
313 |
314 | Student Solution: <insert student solution>
315 |
316 | Alternatively, this can be achieved with a sequence of queries in which all except the last have their output hidden from the end user.
317 |
318 | First, we can ask the model to solve the problem on its own. Since this initial query doesn't require the student’s solution, it can be omitted. This provides the additional advantage that there is no chance that the model’s solution will be biased by the student’s attempted solution.
319 |
320 | USER
321 | <insert problem statement>
322 |
323 | Next, we can have the model use all available information to assess the correctness of the student’s solution.
324 |
325 | SYSTEM
326 | Compare your solution to the student's solution and evaluate if the student's solution is correct or not.
327 | USER
328 | Problem statement: """<insert problem statement>"""
329 |
330 | Your solution: """<insert model generated solution>"""
331 |
332 | Student’s solution: """<insert student's solution>"""
333 |
334 | Finally, we can let the model use its own analysis to construct a reply in the persona of a helpful tutor.
335 |
336 | SYSTEM
337 | You are a math tutor. If the student made an error, offer a hint to the student in a way that does not reveal the answer. If the student did not make an error, simply offer them an encouraging comment.
338 | USER
339 | Problem statement: """<insert problem statement>"""
340 |
341 | Your solution: """<insert model generated solution>"""
342 |
343 | Student’s solution: """<insert student's solution>"""
344 |
345 | Analysis: """<insert model generated analysis from previous step>"""
346 |
347 | Tactic: Ask the model if it missed anything on previous passes
348 | Suppose that we are using a model to list excerpts from a source which are relevant to a particular question. After listing each excerpt the model needs to determine if it should start writing another or if it should stop. If the source document is large, it is common for a model to stop too early and fail to list all relevant excerpts. In that case, better performance can often be obtained by prompting the model with followup queries to find any excerpts it missed on previous passes.
349 |
350 | SYSTEM
351 | You will be provided with a document delimited by triple quotes. Your task is to select excerpts which pertain to the following question: "What significant paradigm shifts have occurred in the history of artificial intelligence."
352 |
353 | Ensure that excerpts contain all relevant context needed to interpret them - in other words don't extract small snippets that are missing important context. Provide output in JSON format as follows:
354 |
355 | [{"excerpt": "..."},
356 | ...
357 | {"excerpt": "..."}]
358 | USER
359 | """<insert document here>"""
360 | ASSISTANT
361 | [{"excerpt": "the model writes an excerpt here"},
362 | ...
363 | {"excerpt": "the model writes another excerpt here"}]
364 | USER
365 | Are there more relevant excerpts? Take care not to repeat excerpts. Also ensure that excerpts contain all relevant context needed to interpret them - in other words don't extract small snippets that are missing important context.
366 |
367 | Strategy: Use external tools
368 | Tactic: Use embeddings-based search to implement efficient knowledge retrieval
369 | A model can leverage external sources of information if provided as part of its input. This can help the model to generate more informed and up-to-date responses. For example, if a user asks a question about a specific movie, it may be useful to add high quality information about the movie (e.g. actors, director, etc…) to the model’s input. Embeddings can be used to implement efficient knowledge retrieval, so that relevant information can be added to the model input dynamically at run-time.
370 |
371 | A text embedding is a vector that can measure the relatedness between text strings. Similar or relevant strings will be closer together than unrelated strings. This fact, along with the existence of fast vector search algorithms means that embeddings can be used to implement efficient knowledge retrieval. In particular, a text corpus can be split up into chunks, and each chunk can be embedded and stored. Then a given query can be embedded and vector search can be performed to find the embedded chunks of text from the corpus that are most related to the query (i.e. closest together in the embedding space).
372 |
373 | Example implementations can be found in the OpenAI Cookbook. See the tactic “Instruct the model to use retrieved knowledge to answer queries” for an example of how to use knowledge retrieval to minimize the likelihood that a model will make up incorrect facts.
374 |
375 | Tactic: Use code execution to perform more accurate calculations or call external APIs
376 | Language models cannot be relied upon to perform arithmetic or long calculations accurately on their own. In cases where this is needed, a model can be instructed to write and run code instead of making its own calculations. In particular, a model can be instructed to put code that is meant to be run into a designated format such as triple backtick. After an output is produced, the code can be extracted and run. Finally, if necessary, the output from the code execution engine (i.e. Python interpreter) can be provided as an input to the model for the next query.
377 |
378 | SYSTEM
379 | You can write and execute Python code by enclosing it in triple backticks, e.g. `code goes here`. Use this to perform calculations.
380 | USER
381 | Find all real-valued roots of the following polynomial: 3*x\*\*5 - 5*x**4 - 3\*x**3 - 7\*x - 10.
382 |
383 | Another good use case for code execution is calling external APIs. If a model is instructed in the proper use of an API, it can write code that makes use of it. A model can be instructed in how to use an API by providing it with documentation and/or code samples showing how to use the API.
384 |
385 | SYSTEM
386 | You can write and execute Python code by enclosing it in triple backticks. Also note that you have access to the following module to help users send messages to their friends:
387 |
388 | ```python
389 | import message
390 | message.write(to="John", message="Hey, want to meetup after work?")
391 | ```
392 |
393 | WARNING: Executing code produced by a model is not inherently safe and precautions should be taken in any application that seeks to do this. In particular, a sandboxed code execution environment is needed to limit the harm that untrusted code could cause.
394 |
395 | Tactic: Give the model access to specific functions
396 | The Chat Completions API allows passing a list of function descriptions in requests. This enables models to generate function arguments according to the provided schemas. Generated function arguments are returned by the API in JSON format and can be used to execute function calls. Output provided by function calls can then be fed back into a model in the following request to close the loop. This is the recommended way of using OpenAI models to call external functions. To learn more see the function calling section in our introductory text generation guide and more function calling examples in the OpenAI Cookbook.
397 |
398 | Strategy: Test changes systematically
399 | Sometimes it can be hard to tell whether a change — e.g., a new instruction or a new design — makes your system better or worse. Looking at a few examples may hint at which is better, but with small sample sizes it can be hard to distinguish between a true improvement or random luck. Maybe the change helps performance on some inputs, but hurts performance on others.
400 |
401 | Evaluation procedures (or "evals") are useful for optimizing system designs. Good evals are:
402 |
403 | Representative of real-world usage (or at least diverse)
404 | Contain many test cases for greater statistical power (see table below for guidelines)
405 | Easy to automate or repeat
406 | DIFFERENCE TO DETECT SAMPLE SIZE NEEDED FOR 95% CONFIDENCE
407 | 30% ~10
408 | 10% ~100
409 | 3% ~1,000
410 | 1% ~10,000
411 | Evaluation of outputs can be done by computers, humans, or a mix. Computers can automate evals with objective criteria (e.g., questions with single correct answers) as well as some subjective or fuzzy criteria, in which model outputs are evaluated by other model queries. OpenAI Evals is an open-source software framework that provides tools for creating automated evals.
412 |
413 | Model-based evals can be useful when there exists a range of possible outputs that would be considered equally high in quality (e.g. for questions with long answers). The boundary between what can be realistically evaluated with a model-based eval and what requires a human to evaluate is fuzzy and is constantly shifting as models become more capable. We encourage experimentation to figure out how well model-based evals can work for your use case.
414 |
415 | Tactic: Evaluate model outputs with reference to gold-standard answers
416 | Suppose it is known that the correct answer to a question should make reference to a specific set of known facts. Then we can use a model query to count how many of the required facts are included in the answer.
417 |
418 | For example, using the following system message:
419 |
420 | SYSTEM
421 | You will be provided with text delimited by triple quotes that is supposed to be the answer to a question. Check if the following pieces of information are directly contained in the answer:
422 |
423 | - Neil Armstrong was the first person to walk on the moon.
424 | - The date Neil Armstrong first walked on the moon was July 21, 1969.
425 |
426 | For each of these points perform the following steps:
427 |
428 | 1 - Restate the point.
429 | 2 - Provide a citation from the answer which is closest to this point.
430 | 3 - Consider if someone reading the citation who doesn't know the topic could directly infer the point. Explain why or why not before making up your mind.
431 | 4 - Write "yes" if the answer to 3 was yes, otherwise write "no".
432 |
433 | Finally, provide a count of how many "yes" answers there are. Provide this count as {"count": <insert count here>}.
434 |
435 | Here's an example input where both points are satisfied:
436 |
437 | SYSTEM
438 | <insert system message above>
439 | USER
440 | """Neil Armstrong is famous for being the first human to set foot on the Moon. This historic event took place on July 21, 1969, during the Apollo 11 mission."""
441 |
442 | Here's an example input where only one point is satisfied:
443 |
444 | SYSTEM
445 | <insert system message above>
446 | USER
447 | """Neil Armstrong made history when he stepped off the lunar module, becoming the first person to walk on the moon."""
448 |
449 | Here's an example input where none are satisfied:
450 |
451 | SYSTEM
452 | <insert system message above>
453 | USER
454 | """In the summer of '69, a voyage grand,
455 | Apollo 11, bold as legend's hand.
456 | Armstrong took a step, history unfurled,
457 | "One small step," he said, for a new world."""
458 |
459 | There are many possible variants on this type of model-based eval. Consider the following variation which tracks the kind of overlap between the candidate answer and the gold-standard answer, and also tracks whether the candidate answer contradicts any part of the gold-standard answer.
460 |
461 | SYSTEM
462 | Use the following steps to respond to user inputs. Fully restate each step before proceeding. i.e. "Step 1: Reason...".
463 |
464 | Step 1: Reason step-by-step about whether the information in the submitted answer compared to the expert answer is either: disjoint, equal, a subset, a superset, or overlapping (i.e. some intersection but not subset/superset).
465 |
466 | Step 2: Reason step-by-step about whether the submitted answer contradicts any aspect of the expert answer.
467 |
468 | Step 3: Output a JSON object structured like: {"type_of_overlap": "disjoint" or "equal" or "subset" or "superset" or "overlapping", "contradiction": true or false}
469 |
470 | Here's an example input with a substandard answer which nonetheless does not contradict the expert answer:
471 |
472 | SYSTEM
473 | <insert system message above>
474 | USER
475 | Question: """What event is Neil Armstrong most famous for and on what date did it occur? Assume UTC time."""
476 |
477 | Submitted Answer: """Didn't he walk on the moon or something?"""
478 |
479 | Expert Answer: """Neil Armstrong is most famous for being the first person to walk on the moon. This historic event occurred on July 21, 1969."""
480 |
481 | Here's an example input with answer that directly contradicts the expert answer:
482 |
483 | SYSTEM
484 | <insert system message above>
485 | USER
486 | Question: """What event is Neil Armstrong most famous for and on what date did it occur? Assume UTC time."""
487 |
488 | Submitted Answer: """On the 21st of July 1969, Neil Armstrong became the second person to walk on the moon, following after Buzz Aldrin."""
489 |
490 | Expert Answer: """Neil Armstrong is most famous for being the first person to walk on the moon. This historic event occurred on July 21, 1969."""
491 |
492 | Here's an example input with a correct answer that also provides a bit more detail than is necessary:
493 |
494 | SYSTEM
495 | <insert system message above>
496 | USER
497 | Question: """What event is Neil Armstrong most famous for and on what date did it occur? Assume UTC time."""
498 |
499 | Submitted Answer: """At approximately 02:56 UTC on July 21st 1969, Neil Armstrong became the first human to set foot on the lunar surface, marking a monumental achievement in human history."""
500 |
501 | Expert Answer: """Neil Armstrong is most famous for being the first person to walk on the moon. This historic event occurred on July 21, 1969."""
502 |
503 | END PROMPT WRITING KNOWLEDGE
504 |
505 | # STEPS:
506 |
507 | - Interpret what the input was trying to accomplish.
508 | - Read and understand the PROMPT WRITING KNOWLEDGE above.
509 | - Write and output a better version of the prompt using your knowledge of the techniques above.
510 |
511 | # OUTPUT INSTRUCTIONS:
512 |
513 | 1. Output the prompt in clean, human-readable Markdown format.
514 | 2. Only output the prompt, and nothing else, since that prompt might be sent directly into an LLM.
515 |
516 | # INPUT
517 |
518 | The following is the prompt you will improve:
519 |
```