review-claudemd

Analyze conversation histories to generate structured CLAUDE.md improvement reports.

9.6k|760|Updated Nov 28, 2025
One-click install
npx skills add https://github.com/ykdojo/claude-code-tips --skill review-claudemd-ykdojo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-claudemd
Source: https://github.com/ykdojo/claude-code-tips/tree/main/skills/review-claudemd
Command: npx skills add https://github.com/ykdojo/claude-code-tips --skill review-claudemd-ykdojo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you systematically review CLAUDE.md files based on recent conversations to identify improvements, ensuring prompts stay effective and consistent across projects.

Core Features & Use Cases

  • Review recent conversations from the project workspace and the global CLAUDE.md to surface inconsistencies, outdated prompts, and missing guidance.
  • Generate actionable improvement suggestions for both local (project) CLAUDE.md and global CLAUDE.md to align practices across your environments.
  • Produce a concise report outlining suggested edits, rationale, and potential impact, so you can apply changes manually.

Quick Start

Run the skill on the current project to analyze the local CLAUDE.md against recent conversations and propose edits.

Frequently Asked Questions about review-claudemd

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

FAQPage Schema
How do I review and improve CLAUDE.md files from past conversations?

To review and improve CLAUDE.md files, you can analyze recent conversation histories to surface inconsistencies and generate a structured report of suggested edits for manual application.

Can I analyze both global and local CLAUDE.md files across multiple projects?

Yes, you can analyze both global and local CLAUDE.md files across multiple projects to surface patterns, identify outdated prompts, and align practices across your environments.

What is the best way to find missing guidance in prompt-engineering documentation?

The best way to find missing guidance is to review conversation histories against your CLAUDE.md files, which surfaces inconsistencies and generates actionable improvement suggestions.

Does this skill automatically apply edits to my CLAUDE.md files?

No, it does not automatically apply edits. It outputs a structured report of findings, rationale, and recommended changes intended for manual application to your CLAUDE.md files.

What kind of output should I expect when reviewing CLAUDE.md improvements?

You should expect a concise structured report outlining suggested edits, rationale, and potential impact for your CLAUDE.md files, intended for manual application.