# Auto Research

> Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor, competitive analyst, gap analyst, tech scout), synthesizes findings into ranked proposals, then runs an iterative keep/discard experiment loop to improve any Claude Code skill. Scores skills on 7 quality dimensions and only keeps changes that genuinely improve the composite score.

## Facts
- Page: https://tashan.sh/capability/plugin-gyoz-ai-auto-research-auto-research
- tashan id: plugin:gyoz-ai/auto-research/auto-research
- Source: https://github.com/gyoz-ai/auto-research
- Type: plugin
- Category: security
- tashan score: 25.0 / 100
- Adoption: 15.0
- Upkeep: 43.0
- Freshness: 54.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: solid
- GitHub stars: 3
- License: MIT
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install auto-research@claude-community
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.