autoresearch
Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code improvement, generating adversarial eval harnesses, running hypothesis-implement-eval-keep/discard loops, or checking autoresearch progress. Triggers on "autoresearch", "autonomous improvement", "eval loop", "hypothesis loop", "self-improvement loop".
npx skills add majiayu000/claude-skill-registry --skill autoresearch-tdimino-claude-code-minoan --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
<critical> ## Five Invariants (never violate) 1. **Single mutable surface** — one hypothesis per iteration, one change per experiment 2. **Fixed eval budget** — eval runs in bounded time, no network calls in gates 3. **One scalar metric** — composite score drives keep/discard, not vibes 4. **Binary keep/discard** — improved = keep, else revert `git reset --hard HEAD~1` 5. **Git-as-memory** — every experiment is a commit, discards are reverts, history is the log ## Safety rules - Never modify `.lab/` contents during hypothesis implementation - Never skip eval — every commit must be evaluated before keep/discard - Always revert on crash — `atexit` handler restores git state - Runner uses **subscription auth** (`claude -p` with ANTHROPIC_API_KEY stripped) </critical> # Autoresearch Scaffold and run autonomous code improvement loops in any git repo. The pattern: generate a hypothesis via `claude -p`, implement it, run programmatic eval gates, keep if the composite score improves, discard if it doesn't. Proven across 50+ iterations on two codebases (shadow-engine: 0.69 to 1.0, perplexity-clone: search quality optimization). ## Category **Runbooks** — mechanical process with clear steps,
- Five Invariants (never violate)
- Safety rules
- Category
- Quick Start
- Command Dispatch
- Init Workflow (/autoresearch init)
- Eval-Gen Workflow (/autoresearch eval-gen)
- Run Workflow (/autoresearch run)
- Status Workflow (/autoresearch status)
- Resume Workflow (/autoresearch resume)
- .lab/ Directory Layout
- Three-Tier Output Protocol
- Scripts Reference
- Gotchas
python3 ~/.claude/skills/autoresearch/scripts/detect_stack.py python3 ~/.claude/skills/autoresearch/scripts/scaffold.py --repo-root . --yes python3 .lab/eval.py python3 ~/.claude/skills/autoresearch/scripts/eval_gen.py --repo-root . --output .lab/eval.py python3 .lab/runner.py --max-iterations 50 python3 .lab/runner.py --dry-run --max-iterations 1 tail -f .lab/results.tsv python3 ~/.claude/skills/autoresearch/scripts/report.py --repo-root .
What does the autoresearch skill do?
Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code improvement, generating adversarial eval harnesses, running hypothesis-implement-eval-keep/discard loops, or checking autoresearch progress. Triggers on "autoresearch", "autonomous improvement", "eval loop", "hypothesis loop", "self-improvement loop".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill autoresearch-tdimino-claude-code-minoan --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.