Pular para o conteúdo
TakoAPI
Voltar às skills

soul-audit

por kapslap

Coding Agents & IDEs
295Downloads informados pelo clawskills.sh
1Estrelas
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

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

Descrição

O que esta skill faz

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.

Quando usá-la

  • 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

Exemplo de fluxo de trabalho

ENTRADA

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

AGENTE
  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

SAÍDA

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

Instalação

clawhub install kapslap/soul-audit

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links