Analyzes and optimizes prompt files for LLM agents. Use this skill when working with .prompt files, improving agent instructions, enhancing prompt clarity, or debugging agent behavior. Helps with prompt engineering, structure optimization, and LangGraph agent prompt management.
Track, evaluate, and analyze multi-agent AI workflows using Azure AI Foundry cloud evaluations. Use when logging agent trajectories, computing evaluation metrics, measuring plan adherence, or generating workflow analytics.
Synchronizes prompt files (agents, rules, commands) from the skill's prompts directory to both GitHub Copilot and OpenCode global configuration directories. Use when the user wants to update their AI editor prompt libraries.
Generate comprehensive learning documents by combining information from tickets, memories, GitHub PRs, and proposals. Use after completing significant work to capture lessons learned.
General-purpose guidance for Claude Code (terminal) and Claude Dev (platform). Covers stable principles (progressive disclosure, hooks, security) and volatile details with lookup workflows.
Ensures questions are answered literally before taking action. Triggers on user input containing '?' or patterns like 'why did you...?', 'will that work?', 'have you considered...?'. Use when user asks about your decisions, challenges an approach, or requests assessment. Prevents interpreting questions as implicit instructions or criticism.
Convert repeated tasks into versioned skills, track performance gaps, and iteratively polish through Git version control. Use for identifying repeated patterns, improving skill consistency, tracking skill evolution, and addressing failure cases. Achieves 20% consistency improvement through iterative refinement. Triggers on "improve skill", "polish skill", "repeated task", "skill evolution", "version skill", "refine pattern".
Generate `llms.txt` and `llms-full.txt` for a docs/product website from just a URL. Detect and reuse an existing `/llms.txt`, discover the docs source repo via “Edit this page”/GitHub links, fall back to `sitemap.xml` or an internal crawl when needed, and optionally use Context7 when the target is a known library.
Automatically generate Claude skills from documentation websites, GitHub repositories, and PDF files using the Skill_Seekers tool. **ALWAYS use this skill when:**
Expert guidance for deploying and managing containerized AI agents on Microsoft Foundry Agent Service. Use this skill when building production-ready, scalable AI agents using code-based frameworks (Microsoft Agent Framework, LangGraph, or custom implementations) that need enterprise-grade hosting, scaling, observability, and integration with Azure services.
Design, build, deploy, and troubleshoot AI agents using AWS Strands Agents Framework (PRIMARY), Google ADK v1.0, A2A (Agent-to-Agent) protocols, and AWS Bedrock AgentCore. Use when creating new agents, implementing agent communication patterns, configuring AgentCore runtime, setting up RAG pipelines, integrating with Gemini 3.0, debugging deployment issues, or optimizing agent performance.
Expert prompt optimization for LLMs and AI systems, specialized in agent cognitive architecture. Use PROACTIVELY when optimizing agent prompts, persona caching, reflection/planning prompts, or A2A conversation generation. (project)
Generate any kind of visual asset using OpenRouter's Nano Banana Pro (Google Gemini 3 Pro Image Preview). Handles images, graphics, illustrations, icons, banners, backgrounds, UI elements, stickers, characters, and more. Flexible and adaptable to any creative request.
Create new Agent Skills for this project. Use when asked to create a skill, document a workflow, or teach Copilot a new capability. Skills are stored in .github/skills/ and can include instructions, scripts, examples, and resources.
Interface for managing the Temporal Database and AI system (ReDB + GGUF embeddings).
Guide for using and supporting the AGENTS.md standard in VS Code. Use this when asked about AGENTS.md, custom instructions, or repo-level AI agent configuration.
Get second opinions from external AI agents (OpenAI, Gemini, GitHub). Use when user says "second opinion", "ask other AIs", "what would GPT say", "check with others", or wants to validate an approach.
