autoresearch-agent
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
npx skills add majiayu000/claude-skill-registry --skill autoresearch-agent --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.
# Autoresearch Agent > You sleep. The agent experiments. You wake up to results. Autonomous experiment loop inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch). The agent edits one file, runs a fixed evaluation, keeps improvements, discards failures, and loops indefinitely. Not one guess — fifty measured attempts, compounding. --- ## Slash Commands | Command | What it does | |---------|-------------| | `/ar:setup` | Set up a new experiment interactively | | `/ar:run` | Run a single experiment iteration | | `/ar:loop` | Start autonomous loop with configurable interval (10m, 1h, daily, weekly, monthly) | | `/ar:status` | Show dashboard and results | | `/ar:resume` | Resume a paused experiment | --- ## When This Skill Activates Recognize these patterns from the user: - "Make this faster / smaller / better" - "Optimize [file] for [metric]" - "Improve my [headlines / copy / prompts]" - "Run experiments overnight" - "I want to get [metric] from X to Y" - Any request involving: optimize, benchmark, improve, experiment loop, autoresearch If the user describes a target file + a way to measure success → this skill applies. --- ## Setup ### First Time — Create the
- Slash Commands
- When This Skill Activates
- Setup
- First Time — Create the Experiment
- What Setup Creates
- Domains
- If program.md Already Exists
- Agent Protocol
- Before Starting
- Each Iteration
- What the Script Handles (you don't)
- Starting an Experiment
- Strategy Escalation
- Self-Improvement
python scripts/setup_experiment.py \ Single iteration (the agent calls this repeatedly) python scripts/run_experiment.py --experiment engineering/api-speed --single Dry run (test setup before starting) python scripts/run_experiment.py --experiment engineering/api-speed --dry-run Single experiment python scripts/log_results.py --experiment engineering/api-speed All experiments in a domain python scripts/log_results.py --domain engineering Cross-experiment dashboard
What does the autoresearch-agent skill do?
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill autoresearch-agent --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.