Galileo-Agent-Labs/eval-engineer

Skills that guide AI coding agents to help you build product-specific AI evals.

🔨 Kyoko is the all-in-one, fully local tool for debugging and improving your AI agents.

Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond

🧠 Your AI teammate that fixes your AI. No more 2am debugging sessions or silent failures. Automatically detects issues, generates fixes, tests them, and ships PRs. Built to make AI actually reliable in production.

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

🪞 Make your agents recursively self-improve

Give your coding agent the power to write and run agent evals.

AI Instructions Diagnostics | Supported agents: Claude | Codex | Copilot | Cursor | Gemini