本文へスキップ
TakoAPI
スキル一覧に戻る

soul-audit

kapslap 作

Coding Agents & IDEs
295ダウンロード数はclawskills.shが公開している値です
1スター
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

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

説明

このスキルでできること

Scores an AI agent's soul file, system prompt, or AGENTS.md against the Guardian Angel v0.7 framework, a rubric derived from Forrest Landry's Immanent Metaphysics. Produces a structured report with dimension scores, identified gaps, and symmetry violations. Useful before deploying or upgrading an agent's ethical configuration.

Uses a scored 12-dimension rubric rather than vague heuristics, making gaps concrete and comparable across different agent configurations.

使いどころ

  • Auditing a custom agent's SOUL.md before deployment
  • Checking if a system prompt would behave differently when monitored vs unmonitored
  • Comparing two agent configurations on ethical rigor
  • Identifying which dimensions of an agent's ethics need the most work
  • Preparing a documented ethics baseline for a new AI project

ワークフロー例

入力

User asks: 'Audit my AGENTS.md against the Guardian Angel framework'

エージェント
  1. 1

    Reads the specified AGENTS.md from the workspace

  2. 2

    Loads the rubric from references/rubric.md

  3. 3

    Scores each of the 12 dimensions 0-3 with brief justifications

  4. 4

    Identifies symmetry violations where behavior would differ under observation

  5. 5

    Outputs the full structured report with strengths, gaps, and ranked recommendations

出力

A scored Soul Audit Report showing overall score out of 45, per-dimension breakdown, critical gaps with document quotes, and prioritized improvement steps

インストール

clawhub install kapslap/soul-audit

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク