# Tournament autoresearch

> Tournament autoresearch is an open-source agent skill. Use when the user wants an autonomous ML research loop that pressure-tests competing ideas before spending compute — several research subage. 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/tournament-autoresearch
- **Repository:** https://github.com/gaasher/agent-loop-skills
- **GitHub stars:** 183
- **License:** MIT
- **Skill name:** tournament-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 pressure-tests competing ideas before spending compute — several research subagents each propose one architecture change, a self-calibrating Judge critiques them against a rubric, the proposers refine, and the Judge picks the single change to run. The Judge learns to pick better over time by scoring its own predictions against realized metric deltas, recording predicted-vs-realized in a calibration ledger and refining its working rubric. The result is an experiment ledger where each iteration's change won a de-biased tournament. Not for running a single pre-decided experiment, and not for analysis-only exploration — for one hypothesis proposed and run per iteration without competition, use the sibling ml-autoresearch loop.

## When your agent uses it

> Use when the user wants an autonomous ML research loop that pressure-tests competing ideas before spending compute — several research subagents each propose one architecture change, a self-calibrating Judge critiques them against a rubric, the proposers refine, and the Judge picks the single change to run. The Judge learns to pick better over time by scoring its own predictions against realized metric deltas, recording predicted-vs-realized in a calibration ledger and refining its working rubric. The result is an experiment ledger where each iteration's change won a de-biased tournament. Not for running a single pre-decided experiment, and not for analysis-only exploration — for one hypothesis proposed and run per iteration without competition, use the sibling ml-autoresearch loop.

## 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/tournament-autoresearch)
- [License: MIT](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/tournament-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/tournament-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/tournament-autoresearch &&
cp -R "$tmp/loops/tournament-autoresearch" ~/.claude/skills/tournament-autoresearch &&
rm -rf "$tmp"
```

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

### Codex

Copy the skill folder to `~/.agents/skills/tournament-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/tournament-autoresearch &&
cp -R "$tmp/loops/tournament-autoresearch" ~/.agents/skills/tournament-autoresearch &&
rm -rf "$tmp"
```

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

### Cursor

Copy the skill folder to `~/.cursor/skills/tournament-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/tournament-autoresearch &&
cp -R "$tmp/loops/tournament-autoresearch" ~/.cursor/skills/tournament-autoresearch &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/tournament-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/tournament-autoresearch
```

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

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/tournament-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/tournament-autoresearch &&
cp -R "$tmp/loops/tournament-autoresearch" ~/.copilot/skills/tournament-autoresearch &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/tournament-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/tournament-autoresearch` into your agent's skills folder as `tournament-autoresearch`. Agents that support SKILL.md read one folder per skill.

## FAQ

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

Copy the skill folder from GitHub to ~/.claude/skills/tournament-autoresearch to use it in all your projects, or to .claude/skills/tournament-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 Tournament 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 Tournament 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/tournament-autoresearch
