autoresearch-agent

v2.9.0

Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).

Claude Code6 skills

by Alireza RezvaniMIT24.2kupdated 10 hours ago

Source

$ git clone https://github.com/alirezarezvani/claude-skills

Clone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is engineering/autoresearch-agent/ inside the repository.

Layout

engineering/autoresearch-agent/

├── .claude-plugin/plugin.json
├── skills/autoresearch-agent/SKILL.md
├── skills/loop/SKILL.md
├── skills/resume/SKILL.md
├── skills/run/SKILL.md
├── skills/setup/SKILL.md
└── skills/status/SKILL.md

Skills6

autoresearch-agentskills/autoresearch-agent/SKILL.md

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.

loopskills/loop/SKILL.md

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or asks to run an autoresearch experiment continuously on a schedule.

resumeskills/resume/SKILL.md

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment.

runskills/run/SKILL.md

Run a single experiment iteration. Edit the target file, evaluate, keep or discard. Use when the user runs /ar:run or asks for one manual autoresearch iteration.

setupskills/setup/SKILL.md

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.

statusskills/status/SKILL.md

Show experiment dashboard with results, active loops, and progress. Use when the user runs /ar:status or asks how an autoresearch experiment is going.

Manifests1

engineering/autoresearch-agent/.claude-plugin/plugin.json

{
  "name": "autoresearch-agent",
  "description": "Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).",
  "version": "2.9.0",
  "author": {
    "name": "Alireza Rezvani",
    "url": "https://alirezarezvani.com"
  },
  "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/engineering/autoresearch-agent",
  "repository": "https://github.com/alirezarezvani/claude-skills",
  "license": "MIT",
  "skills": [
    "./skills"
  ]
}