review-claudemd

Analyze CLAUDE conversation history to recommend CLAUDE.md file updates.

Updated Mar 12, 2023
One-click install
npx skills add https://github.com/Bliz243/.dotfiles --skill review-claudemd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-claudemd
Source: https://github.com/Bliz243/.dotfiles/tree/main/.claude/skills/review-claudemd
Command: npx skills add https://github.com/Bliz243/.dotfiles --skill review-claudemd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill analyzes CLAUDE conversation history to identify improvements for global (~/.claude/CLAUDE.md) and local (project) CLAUDE.md files, enabling targeted updates.

Core Features & Use Cases

  • Analyze recent CLAUDE conversations to extract patterns that enhance documentation guidance.
  • Propose project-specific and global CLAUDE.md refinements to improve agent behavior and consistency.

Quick Start

To begin, run a review pass against your CLAUDE history to generate suggested updates for 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 improve CLAUDE.md files using conversation history?

To improve CLAUDE.md files using conversation history, you analyze recent CLAUDE conversations to extract behavioral patterns, generating concrete refinement recommendations for both global and project-level documentation.

What is the difference between global and project CLAUDE.md?

Global CLAUDE.md (located at ~/.claude/CLAUDE.md) provides universal agent behavior rules, while project CLAUDE.md (./CLAUDE.md) applies context-specific guidance. Conversation history analysis outputs targeted recommendations for updating both configuration scopes.

How do I analyze conversation history to optimize my workflow?

Analyzing conversation history to optimize workflows involves parsing per-project conversation logs to identify recurring issues, extracting improvement patterns, and outputting actionable suggestions to refine CLAUDE.md documentation for better agent consistency.

Can I update local and remote CLAUDE.md configurations simultaneously?

Yes, CLAUDE.md updates can be applied across local and remote environments. The analysis reads conversation histories and outputs concrete documentation improvement recommendations applicable to both local project files and global remote configurations.

Do I need any dependencies to run a CLAUDE.md review pass?

No dependencies are required to run a CLAUDE.md review pass. The process reads directly from existing ~/.claude/CLAUDE.md and ./CLAUDE.md files, parsing conversation histories natively to suggest documentation improvements without external tools.

When should I update my CLAUDE.md documentation?

You should update CLAUDE.md documentation when conversation history analysis reveals recurring behavioral inconsistencies. Running a review pass extracts recent interaction patterns, identifying specific friction points that require configuration refinements for better agent guidance.