Agent skill · research science · alirezarezvani
autoresearch-agent
Make a file measurably better by trial: faster code, smaller bundle, higher pass rate or prompt score. Use whenever the user wants something optimized against a metric, before hand-tuning; loops edits, keeps wins, resets losses. Needs an eval command.
Why this skill is useful
Adds executable scripts for autonomous optimization loops that the AI cannot generate on its own.
What it needs
Requires python installed locally. About 7k tokens when loaded. Last updated 2026-08-05. 23,939 stars on the source repository.
What this skill does
Autoresearch Agent You sleep. The agent experiments. You wake up to results. Autonomous experiment loop inspired by Karpathy's 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 --------- ------------- /autoresearch-agent: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 Experiment Run the setup script. The user decides where experiments live: Project-level (inside repo, git-tracked, shareable with team): User-level (personal, in ~/.autoresearch/): The --scope flag determines where .autoresearch/ lives: project (default) → .autoresearch/ in the repo root. Experiment definitions are git-tracked. Results are gitignored. user → ~/.autoresearch/ in the home directory. Everything is personal. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/autoresearch-agent--334adf