Communitygithub.com

Orchestra-Research/AI-Research-SKILLs

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

What is AI-Research-SKILLs?

AI-Research-SKILLs is a Claude Code agent skill that records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

Works with~Claude Code~Codex CLI~Cursor
npx skills add Orchestra-Research/AI-Research-SKILLs

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does AI-Research-SKILLs do?

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

Related Skills