audit-doc-consistency

Audit CLAUDE.md, AI_INDEX.md, AGENTS.md, and SKILL.md files against repository implementation.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/ElPoot/contabilidad --skill audit-doc-consistency
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit-doc-consistency
Source: https://github.com/ElPoot/contabilidad/tree/main/.agents/skills/audit-doc-consistency
Command: npx skills add https://github.com/ElPoot/contabilidad --skill audit-doc-consistency

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you detect mismatches between a repo’s operational documentation (CLAUDE.md, AI_INDEX.md, AGENTS.md, and local skill docs) and what the project actually implements, preventing incorrect agent behavior.

Core Features & Use Cases

  • Cross-file coherence checks: Compares CLAUDE.md, AI_INDEX.md, AGENTS.md, and local .agents/skills/*/SKILL.md against the repository’s current codebase and structure.
  • Scope-limited auditing: Focuses specifically on documentary consistency rather than deep code or per-skill technical correctness.
  • Truth-first reporting: Produces only inconsistencies verified against real files, minimizing false assumptions.

Use Case: When onboarding or refactoring an automation-heavy repo, run this audit to ensure the “operational map” used by AI agents still matches reality and to avoid prompts that could cause incorrect or unsafe workflows.

Quick Start

Ask the auditor: "Audit document consistency between CLAUDE.md, AI_INDEX.md, AGENTS.md, and local skills, and report only real inconsistencies with severity and impact."

Frequently Asked Questions about audit-doc-consistency

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check if my CLAUDE.md and AGENTS.md files match the actual codebase?

Documentation consistency auditing compares your CLAUDE.md, AGENTS.md, and AI_INDEX.md files against the repository's current implementation to detect mismatches. It verifies cited documentation claims against actual files and reports contradictions with severity, impact, and exact quotes.

What happens if my AI agent prompts reference outdated project modules or rules?

Outdated agent prompts cause incorrect or unsafe workflows by guiding AI agents with mismatched code structure and rules. A documentation consistency audit prevents this by verifying that your operational map still matches reality before onboarding or refactoring.

How do I audit local skill SKILL.md files against my repository structure?

Auditing local .agents/skills/*/SKILL.md files involves cross-file coherence checks that compare the skill documentation against the repository's current codebase. The audit focuses specifically on documentary consistency rather than deep code technical correctness.

Can I verify documentation consistency without getting false positives?

Truth-first reporting ensures only inconsistencies verified against real files are produced, minimizing false assumptions. The verified-only workflow compares cited documentation claims against actual files to report only real contradictions with severity and impact.

When should I run a documentation-code consistency audit for AI agent onboarding?

Run a consistency audit when onboarding or refactoring an automation-heavy repo to ensure the operational map used by AI agents still matches reality. It prevents incorrect agent behavior by verifying documentary guidance matches code structure, modules, rules, and run instructions.