# autoresearchclaw-autonomous-research

A skill that wires up AutoResearchClaw, a 23-stage pipeline turning one topic string into a paper with verified citations and experiment code.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1600 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/autoresearchclaw-autonomous-research/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/autoresearchclaw-autonomous-research

## What it does

The skill covers AutoResearchClaw, an external research engine you run from the terminal or from Python. Give it a topic and it searches arXiv and Semantic Scholar, forms hypotheses, writes experiment code, executes it in a sandbox and drafts a conference-style paper. Output lands in `artifacts/rc-…/deliverables/`, including `paper.tex`, `references.bib` and a citation integrity report.

Setup happens outside the agent: clone the repo, create a venv, `pip install -e .`. Python 3.11+ is required, plus configuration in `config.arc.yaml`. An LLM provider has to be picked there too. OpenAI and OpenRouter read keys from environment variables; the ACP option leans on an agent CLI for login instead.

Three stages stop for approval — literature screening, experiment design, final quality gate — so a long run does not go off the rails unnoticed. Adding `--auto-approve` drops those pauses. If a provider key or the agent CLI is missing, the run will not start.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill autoresearchclaw-autonomous-research -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill autoresearchclaw-autonomous-research -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill autoresearchclaw-autonomous-research -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills autoresearchclaw-autonomous-research
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill autoresearchclaw-autonomous-research -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/autoresearchclaw-autonomous-research
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill autoresearchclaw-autonomous-research -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/reason-machines/trending-skills/tree/HEAD/skills/autoresearchclaw-autonomous-research/SKILL.md

## When to use it
- turn a topic phrase into a full paper draft
- run generated experiments in a sandbox and collect metrics
- check citations against real sources before submission
- produce LaTeX that matches conference formatting
- resume a finished or interrupted run from a chosen stage

## Example prompts
- Run the autonomous pipeline on “efficient attention for long context” with `--auto-approve`
- Generate a paper from my idea and show the citation verification report
- Run only the stages from `LITERATURE_COLLECT` to `KNOWLEDGE_EXTRACT`

## Similar
- [anysearch](https://affpapa.org/en/nevibecode/skills/anysearch.md) — skill · 38500 installs
- [academic-paper](https://affpapa.org/en/nevibecode/skills/academic-paper.md) — skill · 10800 installs
- [nature-figure](https://affpapa.org/en/nevibecode/skills/nature-figure.md) — skill · 18800 installs
- [academic-paper-reviewer](https://affpapa.org/en/nevibecode/skills/academic-paper-reviewer.md) — skill · 9800 installs
- [nature-polishing](https://affpapa.org/en/nevibecode/skills/nature-polishing.md) — skill · 17500 installs
- [nature-citation](https://affpapa.org/en/nevibecode/skills/nature-citation.md) — skill · 15600 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 139 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