Change Impact Auditor

SkillAI & models

Trace a behavioral change through consumers, defaults, docs, tests, errors, and UI. Use when changing configuration, policy, defaults, protocols, or shared data models.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Change Impact Auditor skill

What this skill tells your AI

The instructions your AI receives, as published by caarlos0/dotfiles in skills/change-impact-auditor/SKILL.md and read by ahel’s review.

Audit the semantic concept, not just the edited symbol.

  1. Identify the old and new behavior in one sentence.
  2. Search all producers, consumers, serializers, defaults, migrations, caches, and fallback paths.
  3. Check command help, user-facing errors, documentation, examples, UI status, and tests for claims that became false.
  4. Trace equivalent implementations across languages or process boundaries.
  5. Verify absent, explicit false, explicit true, error, reload, and startup states when relevant.
  6. Report contradictions separately from intentionally deferred scope.

Do not update text mechanically. Confirm each reference describes the changed behavior before editing it.

Signals

GitHub stars
220
Forks
11
Last commit
Sep 2026
Advanced
Item type
skill
Key
change-impact-auditor
Source
github.com/caarlos0/dotfiles