# aris-autonomous-ml-research

A Markdown skill that links ML idea discovery, experiments, paper writing, review, and rebuttal. It fits workflows where one model checks another.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 360 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/aris-autonomous-ml-research/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/aris-autonomous-ml-research

## What it does

This skill packages ML research work as Markdown instructions that an LLM agent can follow. It covers literature gaps, ranked research ideas, experiment runs, LaTeX paper drafting, paper review, and rebuttal preparation.

ARIS assigns different roles to the models. Claude Code or Codex can run the work, while a separate reviewer examines code, claims, or paper drafts. The available flows include `/research-pipeline`, `/idea-discovery`, `/experiment-bridge`, `/paper-writing`, `/auto-review`, and `/rebuttal`.

The system is made of Markdown files rather than a Python package or Docker service. The standard setup needs `ANTHROPIC_API_KEY` and `OPENAI_API_KEY`; another reviewer can use `LLM_REVIEWER_BASE_URL`, `LLM_REVIEWER_API_KEY`, and `LLM_REVIEWER_MODEL`. Without the Anthropic key, the primary agent cannot run.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

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

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

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

## When to use it
- spot gaps in ML literature
- rank possible research directions
- review experiment code before GPU submission
- turn experiment results into a paper
- draft a rebuttal from reviewer comments

## Example prompts
- Run `/research-pipeline "factorized gap in discrete diffusion LMs"` to start the research flow.
- Use `/idea-discovery "discrete diffusion language models"` to generate and rank research directions.
- Ask the agent to critique `paper.pdf` with `/auto-review "paper.pdf"`.

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 186 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