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".

87

1.39x
Quality

84%

Does it follow best practices?

Impact

92%

1.39x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured multi-phase audit skill with concrete templates and clear sequencing, held back by a missing post-apply verification loop for its destructive batch edits and one orphaned reference file. Conciseness and actionability are solid with only minor redundancy.

Suggestions

Add a post-apply verification step in Phase 5 (e.g., re-read each edited CLAUDE.md to confirm changes applied correctly and no syntax/structure was broken) to satisfy the destructive/batch validation requirement and raise workflow clarity above 3.

Link references/update-guidelines.md from Phase 4 (or move its inline 'Update Guidelines' content into that file and reference it) so the orphaned bundle file is reachable from the body.

Trim the 'What Makes a Great CLAUDE.md' and 'User Tips to Share' sections, whose principles already appear in the Phase 2 assessment checklist, to reduce redundancy.

DimensionReasoningScore

Conciseness

Mostly efficient with no concept-padding aimed at Claude, but the 'What Makes a Great CLAUDE.md' and 'User Tips to Share' sections restate principles already covered in the assessment checklist, which could be trimmed.

4 / 5

Actionability

Provides copy-paste ready artifacts — the `find` discovery command, the full report template, and a diff-format example — but the assessment phase itself is qualitative judgment rather than executable steps, leaving minor gaps.

4 / 5

Workflow Clarity

Five clearly sequenced phases with an approval checkpoint before updates ('ask user for confirmation before updating'), but Phase 5 applies batch edits to CLAUDE.md files with no post-apply verification step, capping destructive/batch workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

Body cleanly signals one-level-deep references to real files (quality-criteria.md, templates.md) for detail, but update-guidelines.md is an orphaned bundle file never linked from the body, a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, comprehensive concrete actions, explicit what-and-when trigger guidance, and a well-scoped niche. It mirrors the top anchor examples closely with no padding or vague claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Audit and improve', 'Scans for all CLAUDE.md files', 'evaluates quality against templates', 'outputs quality report', 'makes targeted updates' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what ('Audit and improve CLAUDE.md files...') and when ('Use when user asks to check, audit, update, improve, or fix...'), with concrete trigger phrases in third person.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and exact user phrasings: 'check, audit, update, improve, or fix CLAUDE.md files' plus 'CLAUDE.md maintenance' and 'project memory optimization'.

5 / 5

Distinctiveness Conflict Risk

Scoped narrowly to CLAUDE.md files with distinct triggers, giving it a clear niche with minimal overlap risk against other skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anthropics/claude-plugins-official
Reviewed

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.