# ML autoresearch

> ML autoresearch is an open-source agent skill. Use when the user wants an autonomous ML research loop that does more than blindly try changes. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch
- **Repository:** https://github.com/gaasher/agent-loop-skills
- **GitHub stars:** 183
- **License:** MIT
- **Skill name:** ml-autoresearch
- **Collection:** https://github.com/gaasher/Agent-Loop-Skills
- **Listing updated:** 2026-11-17

## About

Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps.

## When your agent uses it

> Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/ml-autoresearch)
- [License: MIT](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/ml-autoresearch)

## Install

### Claude Code

This skill ships in the `agent-loops` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add gaasher/Agent-Loop-Skills
/plugin install agent-loops@agent-loop-skills
```

Or copy only this skill to `~/.claude/skills/ml-autoresearch`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/ml-autoresearch &&
cp -R "$tmp/loops/ml-autoresearch" ~/.claude/skills/ml-autoresearch &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/ml-autoresearch` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/ml-autoresearch` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/ml-autoresearch &&
cp -R "$tmp/loops/ml-autoresearch" ~/.agents/skills/ml-autoresearch &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/ml-autoresearch` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/ml-autoresearch` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/ml-autoresearch &&
cp -R "$tmp/loops/ml-autoresearch" ~/.cursor/skills/ml-autoresearch &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/ml-autoresearch` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/gaasher/Agent-Loop-Skills.git --path loops/ml-autoresearch
```

Or copy the folder to `~/.gemini/skills/ml-autoresearch` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/ml-autoresearch`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/ml-autoresearch &&
cp -R "$tmp/loops/ml-autoresearch" ~/.copilot/skills/ml-autoresearch &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/ml-autoresearch` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git
```

Then copy `Agent-Loop-Skills/loops/ml-autoresearch` into your agent's skills folder as `ml-autoresearch`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install ML autoresearch in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/ml-autoresearch to use it in all your projects, or to .claude/skills/ml-autoresearch in one project. Or install the agent-loops plugin, which includes it: /plugin marketplace add gaasher/Agent-Loop-Skills, then /plugin install agent-loops@agent-loop-skills.

### Does ML autoresearch run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use ML autoresearch?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/ml-autoresearch
