audit

Audit corrections/rules.md to classify and promote learned rules into CLAUDE.md.

8|5|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/shenxingy/Clade --skill audit-shenxingy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit
Source: https://github.com/shenxingy/Clade/tree/main/configs/skills/audit
Command: npx skills add https://github.com/shenxingy/Clade --skill audit-shenxingy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents your learned correction rules from staying trapped in corrections/rules.md by auditing them for maturity, redundancy, and contradictions so they can be promoted into CLAUDE.md or hooks.

Core Features & Use Cases

  • Improvement-trend visibility: Computes recent effectiveness trends from scorecards.jsonl to show whether the learning system is improving.
  • Rule quality classification: Categorizes rules as PROMOTE, REDUNDANT, CONTRADICT, INEFFECTIVE, KEEP, or CROSS-PROJECT based on stability, effectiveness, clustering, and conflicts with existing configuration.
  • Automated promotions & cleanup: Automatically appends mature rules into the correct section of CLAUDE.md (or creates Auto-Promoted Rules) and removes promoted/redundant rules from corrections/rules.md.

Quick Start

Run the audit skill to review corrections/rules.md and automatically promote stable rules into your CLAUDE.md.

Frequently Asked Questions about audit

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

FAQPage Schema
How do I promote learned correction rules into CLAUDE.md automatically?

Rule quality classification evaluates learned rules against stability, effectiveness, and domain clustering, then labels them as PROMOTE, REDUNDANT, CONTRADICT, INEFFECTIVE, KEEP, or CROSS-PROJECT based on their performance data.

How do I detect contradictory rules in my configuration management system?

Cross-project recurrence detection works by analyzing optional cross-project recurrence logs alongside your rules, identifying stable rules that recur across different projects, and classifying them as CROSS-PROJECT for broader promotion.

Can I audit learned rules in both project scope and global scope?

Yes, rule auditing supports both project scope and global scope modes. This allows you to manage meta-learning, rule clustering by domain tags, and safe automated promotions with timestamp updates at whichever scope your project requires.

How do I clean up redundant correction rules from rules.md?

Cleaning up redundant correction rules is automated by the audit skill. It identifies REDUNDANT rules during the review process and automatically removes promoted or redundant entries from corrections/rules.md to keep the learning system efficient.