# autoresearch

autoresearch runs another skill through repeated test cycles, grades each output against pass/fail checks, and rewrites its prompt until the score stops climbing.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 152 installs · ★ 655 repo stars
- Author: pedronauck
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/pedronauck/skills/tree/HEAD/skills/curated/autoresearch/SKILL.md
- Updated: 2026-10-20
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/pedronauck-autoresearch

## What it does

The skill takes the path to a target `SKILL.md`, a handful of test prompts, and 3–6 yes/no checks, then loops: generate outputs, grade them against the checks, tweak the wording, keep edits that raise the pass rate and drop the rest. Before any run starts, the agent has to confirm with the user which skill to tune, what test scenarios to cover, what the pass/fail checks are, how many runs per experiment (5 by default), and how often cycles repeat (every 2 minutes by default).

Before touching anything, the agent reads the full `SKILL.md` and any linked files under `references/` to understand the skill's job, then turns the user's criteria into checks written as a question plus explicit pass and fail conditions. The first pass runs the skill unchanged as experiment zero, its score becomes the baseline, and the original file is copied to `SKILL.md.baseline`.

Every experiment gets logged to `results.tsv` and `results.json`, feeding a self-contained HTML dashboard with a score-progression chart, a per-experiment table, and a breakdown of which checks pass or fail most often; it auto-opens in the browser and refreshes as new runs land. If the baseline already lands near 90%, the skill flags that to the user before continuing.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add pedronauck/skills --skill autoresearch -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/autoresearch/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/autoresearch/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add pedronauck/skills --skill autoresearch -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/autoresearch/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add pedronauck/skills --skill autoresearch -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/autoresearch/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install pedronauck/skills skills/curated/autoresearch
```

2. **Manually: put the files in place**
- File: `.github/skills/autoresearch/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add pedronauck/skills --skill autoresearch -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/pedronauck/skills --path skills/curated/autoresearch
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/autoresearch/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add pedronauck/skills --skill autoresearch -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/pedronauck/skills/tree/HEAD/skills/curated/autoresearch/SKILL.md

## When to use it
- find which inputs break an existing skill
- turn vague quality bars into testable pass/fail checks
- auto-tune a skill's prompt instead of editing it by hand
- track pass-rate progress across experiments on a chart
- log which prompt edits helped and which got discarded

## Example prompts
- Run autoresearch on the skill at `~/.claude/skills/pdf-report/SKILL.md`
- Benchmark this skill with evals until the pass rate plateaus
- Improve this skill — set up 5 test scenarios and binary checks

## Similar
- [skill-autoresearch](https://affpapa.org/en/nevibecode/skills/skill-autoresearch.md) — skill · 323 installs
- [skill-optimizer](https://affpapa.org/en/nevibecode/skills/skill-optimizer.md) — skill · 1400 installs
- [prompt-optimizer](https://affpapa.org/en/nevibecode/skills/haabe-prompt-optimizer.md) — skill · ★ 54 repo stars
- [write-judge-prompt](https://affpapa.org/en/nevibecode/skills/write-judge-prompt.md) — skill · 1300 installs
- [prompt-engineer-toolkit](https://affpapa.org/en/nevibecode/skills/borghei-prompt-engineer-toolkit.md) — skill · 106 installs
- [prompt-governance](https://affpapa.org/en/nevibecode/skills/prompt-governance.md) — skill · 40 installs

## Other versions with the same name
- [autoresearch · github](https://affpapa.org/en/nevibecode/skills/autoresearch.md) — 3400 installs
- [autoresearch · uditgoenka](https://affpapa.org/en/nevibecode/skills/uditgoenka-autoresearch.md) — 2700 installs
- [autoresearch · yeachan-heo](https://affpapa.org/en/nevibecode/skills/yeachan-heo-autoresearch.md) — 654 installs
- [autoresearch · orchestra-research](https://affpapa.org/en/nevibecode/skills/orchestra-research-autoresearch.md) — 1200 installs
- [autoresearch · agricidaniel](https://affpapa.org/en/nevibecode/skills/agricidaniel-autoresearch.md) — 572 installs

From the same set: [pedronauck/skills](https://affpapa.org/en/nevibecode/by/pedronauck/skills.md) — 52 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
