# soul-audit

> soul-audit — kapslap-soul-audit. Use this tool when you need to evaluate the integrity and compliance of AI agents against a standardized framework. The soul-audit tool assesses soul files, system prompts, and AGENTS.md files against the Guardian Angel v0.6 framework, identifying potential issues and ensuring alignment with established guidelines. It takes in AI agent configurations as input and produces a compliance report as output, helping you ensure trustworthy and reliable AI interactions.

Canonical page: https://skillsregistry.net/skills/kapslap-soul-audit  
JSON: https://api.skillsregistry.net/v1/skills/kapslap-soul-audit

## Description

Evaluate any AI agent's soul file, system prompt, or AGENTS.md against the Guardian Angel v0.6 framework (Forrest.

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-09-25

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/kapslap-soul-audit)

## 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": "kapslap-soul-audit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kapslap-soul-audit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kapslap-soul-audit/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