Claude MD Enhancer
Generates and audits CLAUDE.md files against a fixed section checklist and quality score
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 5052d0a
GitHub API was rate-limited, so I cloned the repo and found SKILL.md at generated-skills/claude-md-enhancer/; frontmatter has name+description, every body-referenced file exists (analyzer.py, generator.py, workflow.py all HTTP 200 on raw, examples/ holds the 6 reference files it claims), no hardcoded paths, and the security grep turned up only the validator's own secret-detection regex. I built a fixture repo (Fastify+Postgres invoicing API: package.json, src/routes/, migrations/, tests/, CI workflow), wrote a BASELINE CLAUDE.md my normal way (42 lines: What this is / Commands / Layout / Conventions / Notes), then a SKILL artifact following the body's Critical Validation Rule and Core template (133 lines, adding Overview, a Project Structure ASCII tree, File Structure, Architecture with the request-flow path, Setup & Installation, versioned Tech Stack, Testing Requirements and Error Handling). Running the skill's own analyzer.py over both scored the baseline 35/100 with "Missing critical sections: Core Principles, Tech Stack, Workflow" and the skill artifact 69/100 — the checklist genuinely made me write an Architecture section and a directory tree I would not have written unprompted, though ~15 lines of the skill version are filler (quarterly-review note, footer metadata). Docs lose points for the unverifiable "100% Native Format Compliance ... matching /update-claude-md" claim and an internal inconsistency: analyzer.py's RECOMMENDED_SECTIONS still demanded "Quick Navigation" and "Workflow Instructions" from a file that followed the body's own section list.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 3/5
What Claude MD Enhancer does
Generates new CLAUDE.md files for a repository and audits existing ones against a fixed section checklist (Overview, Project Structure, File Structure, Architecture, Setup, Tech Stack, Workflow, Commands). Ships Python modules that parse a CLAUDE.md, list missing sections, and compute a 0-100 quality score with ranked recommendations. Triggers when you ask Claude to create, restructure, or review a CLAUDE.md, or to split project guidelines into per-directory files.
How to install Claude MD Enhancer
git clone --depth 1 https://github.com/alirezarezvani/claude-code-skill-factory.git /tmp/claude-md-enhancer-src
mkdir -p ~/.claude/skills
cp -R /tmp/claude-md-enhancer-src/generated-skills/claude-md-enhancer ~/.claude/skills/claude-md-enhancer
# No dependencies beyond Python 3 (stdlib only) for the optional analyzer/validator modules.
# The five .py files (analyzer, validator, generator, template_selector, workflow) have no
# CLI entrypoint (no __main__ block) — they are importable modules, e.g.
# python3 -c "import sys;sys.path.insert(0,'$HOME/.claude/skills/claude-md-enhancer');
# from analyzer import CLAUDEMDAnalyzer;print(CLAUDEMDAnalyzer(open('CLAUDE.md').read()).analyze_file())"
# The repo is a multi-skill monorepo; only the claude-md-enhancer directory is needed.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Claude MD Enhancer
-
/claude-md-enhancerGenerates and audits CLAUDE.md files against a fixed section checklist and quality score
It also activates on plain-language prompts like these:
-
Generate a CLAUDE.md for this new project -
Improve my existing CLAUDE.md file for this project -
Add tech stack conventions to CLAUDE.md
Frequently asked questions
- Is the Claude MD Enhancer skill free?
- Yes. The skill itself is free from alirezarezvani/claude-code-skill-factory. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Claude MD Enhancer work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. GitHub API was rate-limited, so I cloned the repo and found SKILL.md at generated-skills/claude-md-enhancer/; frontmatter has name+description, every body-referenced file exists (analyzer.py, generator.py, workflow.py all HTTP 200 on raw, examples/ holds the 6 reference files it claims), no hardcoded paths, and the security grep turned up only the validator's own secret-detection regex. I built a fixture repo (Fastify+Postgres invoicing API: package.json, src/routes/, migrations/, tests/, CI workflow), wrote a BASELINE CLAUDE.md my normal way (42 lines: What this is / Commands / Layout / Conventions / Notes), then a SKILL artifact following the body's Critical Validation Rule and Core template (133 lines, adding Overview, a Project Structure ASCII tree, File Structure, Architecture with the request-flow path, Setup & Installation, versioned Tech Stack, Testing Requirements and Error Handling). Running the skill's own analyzer.py over both scored the baseline 35/100 with "Missing critical sections: Core Principles, Tech Stack, Workflow" and the skill artifact 69/100 — the checklist genuinely made me write an Architecture section and a directory tree I would not have written unprompted, though ~15 lines of the skill version are filler (quarterly-review note, footer metadata). Docs lose points for the unverifiable "100% Native Format Compliance ... matching /update-claude-md" claim and an internal inconsistency: analyzer.py's RECOMMENDED_SECTIONS still demanded "Quick Navigation" and "Workflow Instructions" from a file that followed the body's own section list.
- What is the Claude MD Enhancer SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.
- How do I install Claude MD Enhancer?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Claude MD Enhancer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.