Individual skill
autoresearch
Autonomous iteration loop: modify, verify, keep/discard against any metric
pi-extension/skills/autoresearch/SKILL.md
Source commit 7bddd056dfd0b0ded8360588d8101b1ecb5c0baa
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 6,829
- Repository last updated
- Oct 31, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- autonomous-agent Repository topic
- autoresearch Repository topic
- claude Repository topic
- claude-code Repository topic
- iteration Repository topic
- karpathy Repository topic
- productivity Repository topic
- skill Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 10,058 bytesSKILL.mdcore · 10,058 bytesSKILL.mdcore · 10,058 bytesSKILL.mdcore · 10,058 bytesSKILL.mdcore · 10,058 bytesreferences/behavior-preserving-optimization.mddoc · 2,692 bytesreferences/fork-and-flush.mddoc · 8,602 bytesreferences/orchestrator-routing.mddoc · 7,350 bytesreferences/predict-personas.mddoc · 3,145 bytesreferences/reason-judge-protocol.mddoc · 3,508 bytesreferences/security-checklist.mddoc · 3,524 bytesscripts/orchestrate.shruns · 29,476 bytesscripts/score-regression.shruns · 7,775 bytes
Read excerpt
# Autoresearch — Autonomous Goal-directed Iteration
## Safety Invariants (all subcommands)
- Never push, publish, or deploy without explicit user approval.
- Bounded by default. Override with `Iterations: unlimited`.
- All results logged to `autoresearch/{subcommand}-{YYMMDD}-{HHMM}/` directory.
- Chain handoff via `handoff.json`. Evals reads `*-results.tsv`.
## Dispatch (bare `/autoresearch`)
Parse the invocation in this order:
| Condition | Mode |
|---|---|