Verified:GitHub

review-claudemd

Analyze recent JSONL conversation history to identify CLAUDE.md instruction improvements.

Updated Apr 15, 2026

Search Tags:#knowledge management #conversation analysis #claude.md #project configuration #prompt improvement #instruction audit

Ready to run

npx skills add https://github.com/ToanPV90/dotfiles --skill review-claudemd-toanpv90

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review-claudemd
Source: https://github.com/ToanPV90/dotfiles/tree/main/claude/.claude/skills/review-claudemd
Command: npx skills add https://github.com/ToanPV90/dotfiles --skill review-claudemd-toanpv90

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you find where your CLAUDE.md instructions are being ignored, then improves both global and project-specific CLAUDE.md files based on real conversation patterns.

Core Features & Use Cases

Conversation-driven instruction audit: Scans recent JSONL conversation history to detect violated or ineffective instructions.
Global vs. local recommendations: Produces targeted suggestions for ~/.claude/CLAUDE.md (GLOBAL) and ./CLAUDE.md (LOCAL) based on observed behavior.
Safety-first update workflow: Advises backing up both global and local CLAUDE.md before any edits and supports drafting changes for approval.

Quick Start

Use the review-claudemd skill to review recent conversation history and produce specific bullet-point improvements for your global ~/.claude/CLAUDE.md and the project CLAUDE.md.

Frequently Asked Questions about review-claudemd

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

FAQPage Schema

How do I audit CLAUDE.md instructions using conversation history?▼

You can audit CLAUDE.md instructions by parsing recent JSONL conversation sessions from ~/.claude/projects to extract user and assistant text, then batching analysis prompts to identify violated rules and generate specific improvement suggestions for both global and local configuration files.

What is the best way to improve CLAUDE.md prompt quality for a specific project?▼

The best way to improve CLAUDE.md prompt quality is to review recent conversation patterns to detect where instructions are being ignored, then apply targeted suggestions to both global ~/.claude/CLAUDE.md and local project ./CLAUDE.md files based on observed behavior.

Can I update global and project CLAUDE.md files separately?▼

Yes, you can update global and project CLAUDE.md files separately. The audit process produces distinct GLOBAL suggestions for ~/.claude/CLAUDE.md and LOCAL suggestions for ./CLAUDE.md, allowing you to apply configuration changes independently based on conversation analysis results.

How do I safely back up CLAUDE.md before applying instruction updates?▼

To safely back up CLAUDE.md before applying instruction updates, the workflow advises creating copies of both global ~/.claude/CLAUDE.md and local ./CLAUDE.md files prior to any edits, and supports drafting proposed changes for approval before they are committed.

Why are my CLAUDE.md instructions being ignored during conversations?▼

CLAUDE.md instructions may be ignored due to ineffective or outdated rules. Analyzing recent JSONL session history helps detect violated instructions and outdated items, providing specific bullet-point improvements to strengthen your global and local configuration files.

Does CLAUDE.md conversation analysis work without external dependencies?▼

Yes, CLAUDE.md conversation analysis works without external dependencies. It operates by parsing native JSONL session files stored locally in ~/.claude/projects, extracting conversation text, and aggregating findings into violated-instructions and suggestion reports.