# Autoresearch

Bounded research experiment loop that tries hypotheses, measures benchmark evidence...

- Repository: https://github.com/Companion-Inc/feynman (10055 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-10-31
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Companion-Inc/feynman --skill autoresearch -g -a claude-code -y`
Codex: `npx skills add Companion-Inc/feynman --skill autoresearch -g -a codex -y`
Cursor: `npx skills add Companion-Inc/feynman --skill autoresearch -g -a cursor -y`
Gemini CLI: `npx skills add Companion-Inc/feynman --skill autoresearch -g -a gemini-cli -y`

## Description

Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records what fails. Use when the user asks to optimize a research metric, run an experiment loop, improve model/retrieval/evaluation performance iteratively, or benchmark a research hypothesis.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Autoresearch

Run the `/autoresearch` workflow. The slash command expands the full workflow instructions in the active session; do not try to read a relative prompt-template path from the installed skill directory.

Run the benchmark through the shell and record each result, its evidence, and the keep/revert decision in the session files.

Session files: `autoresearch.md`, `autoresearch.sh`, `autoresearch.jsonl`