claude-md-improver

Audit CLAUDE.md files and propose targeted improvements after approval.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/Wizarck/eligia-skills --skill claude-md-improver-wizarck
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-md-improver
Source: https://github.com/Wizarck/eligia-skills/tree/main/claude-plugins-official/plugins/claude-md-management/skills/claude-md-improver
Command: npx skills add https://github.com/Wizarck/eligia-skills --skill claude-md-improver-wizarck

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps teams keep CLAUDE.md files accurate, concise, and useful so Claude Code has reliable project context.

Core Features & Use Cases

  • Scans repositories for project root, package, and local CLAUDE.md variants.
  • Scores each file against commands, architecture, gotchas, currency, and actionability.
  • Produces a quality report before any edits and then proposes targeted improvements after approval.
  • Useful for monorepos, stale project memory, and onboarding new contributors.

Quick Start

Ask the skill to audit the repository's CLAUDE.md files and propose concise improvements.

Frequently Asked Questions about claude-md-improver

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

FAQPage Schema
How do I audit and improve stale CLAUDE.md project memory files?

Auditing CLAUDE.md files involves discovering all project root and package variants, scoring them against a rubric covering commands, architecture, and gotchas, then proposing targeted improvements after approval.

What is the best way to maintain CLAUDE.md context across a monorepo?

Maintaining CLAUDE.md context across a monorepo requires scanning for root, package, and local file variants, generating a quality report, and applying targeted context updates to ensure reliable codebase hygiene.

Does the CLAUDE.md documentation audit require any external dependencies?

The CLAUDE.md documentation audit requires no external dependencies, operating entirely within the repository environment to discover files, score coverage against a rubric, and propose edits after explicit approval.

How do I score CLAUDE.md files for actionability and codebase hygiene?

Scoring CLAUDE.md files for actionability and codebase hygiene involves evaluating each file against commands, architecture, gotchas, currency, and actionability criteria to produce a targeted quality report before any edits.

Can I review a CLAUDE.md quality report before any file edits are made?

You can review a quality report before any file edits are made; the process generates a rubric-based assessment of your project context coverage and only proposes targeted improvements after receiving explicit approval.

When should I review and update project context documentation for new contributors?

You should review and update project context documentation for new contributors when files become stale, using a documentation audit to score currency and actionability, ensuring reliable onboarding context across the codebase.