skills.rest
Clay-HHK
Clay-HHKCOMMUNITY
Explore all skills by this author →
GitHub

skill-quality-reviewer

Evaluates Claude Skills across description, organization, style, and structure to generate scored quality reports.

1|Updated Mar 5, 2026
Search Tags:#documentation#claude skills#quality analysis#yaml frontmatter#skill review#scoring rubric#improvement plan
One-click install
npx skills add https://github.com/Clay-HHK/claude-skills --skill skill-quality-reviewer-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-quality-reviewer
Source: https://github.com/Clay-HHK/claude-skills/tree/main/skill-quality-reviewer
Command: npx skills add https://github.com/Clay-HHK/claude-skills --skill skill-quality-reviewer-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Skill authors lack an objective way to measure whether their Claude Skills follow best practices before sharing them, leading to vague descriptions, bloated SKILL.md files, and broken references that hurt discoverability. ## Core Features & Use Cases - Four-Dimension Scoring: Evaluates description quality (25%), content organization (30%), writing style (20%), and structural integrity (25%) with detailed rubrics. - Weighted Grades: Computes an overall score from 0-100 mapped to letter grades from A+ to F. - Actionable Reports: Generates a quality report and a prioritized improvement plan with file locations, current vs. suggested content, and estimated score impact. - Use Case: Before publishing a new skill, run the reviewer to confirm it scores B- or higher and get a checklist of fixes for weak trigger phrases or missing references. ## Quick Start Analyze the skill quality of ~/.claude/skills/git-workflow and generate a quality report with improvement recommendations.

Frequently Asked Questions about skill-quality-reviewer

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

FAQPage Schema
How do I evaluate the quality of a Claude Skill?▼

Point the reviewer at a skill directory containing SKILL.md, and it parses the YAML frontmatter, scores four quality dimensions, and writes a quality report plus an improvement plan to the working directory.

What makes a good skill description for Claude Skills?▼

A good description uses third-person phrasing like "This skill should be used when...", includes 3-5 specific trigger phrases, stays between 100-300 characters, and names concrete use cases rather than vague claims.

How long should a SKILL.md file be?▼

SKILL.md should stay under 5,000 words, with 1,500-2,000 words considered ideal. Detailed content belongs in references/ files so the main file loads only essential instructions.

What score does a skill need before sharing it publicly?▼

The rubric recommends B (83) or higher for pre-publication checks, with certified status requiring at least 80 overall plus minimum thresholds in each dimension such as 80 in structural integrity.

Why does skill evaluation fail on YAML frontmatter?▼

Evaluation fails when the frontmatter is missing the required name or description fields or contains invalid YAML syntax such as unquoted colons. The extract-yaml.sh script isolates the frontmatter block for inspection.

Related Skills

Explore More Software Engineering Skills→
aws-samplesaws-samples
12

skill-eval

Evaluate AI Agent Skills for safety, quality, reliability, and cost.

Official
Advanced
LauraFlorentinLauraFlorentin
1

skill-checker

Validate skill folders against Anthropic's official guidelines and generate scorecards.

Community
Advanced
microsoftmicrosoft
4.9k

creating-skills

Guides creation of custom skills with SKILL.md frontmatter and optional bundled scripts.

Official
Intermediate
tolgaiotolgaio

Rate AI Response

Rate AI responses against a standardized rubric with letter grade and score.

Community
Advanced