# adversarial-coach

> adversarial-coach — killerapp-adversarial-coach. Use this tool when you need to review and strengthen implementations against adversarial attacks, solving problems of security and robustness in systems. It takes in implementation details and outputs a reviewed and fortified version, based on Block's g3 framework. Ideal for use in high-stakes applications where security is paramount, such as financial or sensitive data processing.

Canonical page: https://skillsregistry.net/skills/killerapp-adversarial-coach  
JSON: https://api.skillsregistry.net/v1/skills/killerapp-adversarial-coach

## Description

Adversarial implementation review based on Block's g3.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/killerapp-adversarial-coach)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "killerapp-adversarial-coach"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/killerapp-adversarial-coach` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/killerapp-adversarial-coach/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt