autoresearch
Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the user says "autoresearch" (optionally with a focus, e.g. "autoresearch the optimizer"), asks to run experiments on a repo overnight, to hill-climb or optimize a metric autonomously, or points at a repo with a karpathy-style program.md.
Install
Show step-by-stepHide step-by-step
Open your terminal
- Mac: Press โ Space, type "Terminal", press Enter
- Windows: Press Win R, type "cmd", press Enter
Paste the command above and press Enter
Use the Copy command button, then paste in your terminal (Mac: โV, Windows: Ctrl V).
Restart Claude Code
Close and reopen Claude Code, or start a new session, so it picks up the new skill.
Where it lives
Comments
"Revamped my skill catalog today. Each skill is built by datamining tens of thousands of trajectories from my agentic sessions, finding typical failure modes..."
"It's great when you can "/autoresearch" or do an unbound "/timeboxed" run against some metric. You can too, check out"
Related skills
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements