CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".

Invalid
This skill can't be scored yet
Validation errors are blocking scoring. Review and fix them to unlock Quality, Impact and Security scores. See what needs fixing →
SKILL.md
Quality
Evals
Security

Evaluation results

100%

65%

CLAUDE.md Documentation Audit

Quality report format and scoring

Criteria
Without context
With context

Report heading

60%

100%

Summary section

0%

100%

Numerical score

100%

100%

Letter grade

0%

100%

Commands/Workflows criterion

40%

100%

Architecture Clarity criterion

0%

100%

Non-Obvious Patterns criterion

0%

100%

Conciseness criterion

0%

100%

Currency criterion

0%

100%

Actionability criterion

0%

100%

Issues section present

100%

100%

Stale command flagged

100%

100%

Missing file reference flagged

100%

100%

100%

4%

Improve Project Documentation for AI Sessions

Targeted CLAUDE.md updates with diff format

Criteria
Without context
With context

Report before edits

100%

100%

Diff file header

50%

100%

Diff additions shown

100%

100%

Why explanation

100%

100%

Generic advice removed

100%

100%

Verbose sections removed or condensed

100%

100%

Generic advice flagged as issue

100%

100%

Project-specific commands added

100%

100%

Environment variable documented

100%

100%

Concise additions

100%

100%

Existing structure preserved

100%

100%

DB import ordering gotcha

100%

100%

78%

9%

Monorepo Documentation Health Check

Multi-file discovery and monorepo audit

Criteria
Without context
With context

Discovery bash command

0%

0%

All three files assessed

100%

100%

File type identification

70%

100%

Per-file numerical scores

0%

100%

Duplicate content flagged

100%

100%

Outdated architecture flagged

100%

53%

Broken file references flagged

100%

100%

Currency criterion assessed

87%

100%

Issues per file

71%

100%

Repository
anthropics/claude-plugins-official
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.