# Adversarial

> Red-team / devil's advocate on analyses, proposals, architecture, ideas, specs, or plans — attack assumptions, kill vacuous claims, surface bypass and failure modes. Triggers: "adversarial" | "red team" | "devil's advocate" | "attack this design" | "kill this idea" | "stress test this" | "what breaks this" | "adversarial review".

## Facts
- Page: https://tashan.sh/capability/skill-roxabi-adversarial
- tashan id: skill:Roxabi/adversarial
- Source: https://github.com/Roxabi/roxabi-plugins
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 96.0
- Freshness: 92.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: AGPL-3.0
- Official: no

## Install

```sh
cp -r adversarial ~/.claude/skills/
```

## 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 2026-08-20 by tashan (https://tashan.sh) from public evidence. Scorer s5.