AI Agent Skills

A beginner's project on automating the training, evaluation, versioning, and deployment of models using GitHub Actions.

Using LlamaIndex, Redis, and OpenAI to chat with PDF documents. Supplementary material for blog post on Microsoft Developer Blog

Install, configure, audit, and fix AgentMarkup machine-readable website metadata in JavaScript web repos. Use when adding @agentmarkup/vite, @agentmarkup/astro, @agentma…

Rank LLMs, RAG systems, and prompts using automated head-to-head evaluation

Code and Data for "MIRAI: Evaluating LLM Agents for Event Forecasting"

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface as…

Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base. When a user pastes a link or text (in ANY channel — Discord, Slack, CLI, etc.),…

Initialize or repair SigNoz MCP server configuration for Claude Code, Codex, Cursor, VS Code/GitHub Copilot, Claude Desktop, Gemini CLI, Devin CLI, Grok Build, Windsurf,…

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface as…

Foundation for building, modifying, debugging, or verifying Runway Dev Platform integrations in an application: connect Dev MCP, use llms.txt to find current resources,…

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. U…

Analyze code changes and update KNOWLEDGE_BASE.md with architectural and feature changes.

Use this when adding evaluation to an LLM/agent app - measuring output quality (correctness, faithfulness, relevance, safety) rather than just watching traces. Trigger o…

Use this to build a good evaluation dataset for an LLM app, the part everyone underestimates. Trigger on "make an eval set", "what should I test my LLM on", "I don't hav…

Maintain a project-local, version-pinned wiki of every external dependency. Use whenever a new library is being added, an existing one is being upgraded, an idiom for us…

Prove that a knowledge base actually works before trusting it — after building or adopting docs, a knowledge graph, or a wiki, verify it can orient a fresh agent and res…