Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

soul-audit

bởi kapslap

Coding Agents & IDEs
295Lượt tải do clawskills.sh công bố
1Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

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

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

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

AGENT
  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

ĐẦU RA

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

Cài đặt

clawhub install kapslap/soul-audit

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết