Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills.
90
85%
Does it follow best practices?
Impact
100%
1.33xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
External skill review workflow
Review workflow documented
100%
100%
Description voice issue found
20%
100%
Trigger conditions issue found
100%
100%
Imperative form violations found
75%
100%
Hardcoded path issue found
100%
100%
Hardcoded secret found
100%
100%
Missing workflow pattern identified
0%
100%
Checklist categories used
10%
100%
Summary table present
40%
100%
Actionable recommendations
100%
100%
Additive-only PR preparation
Original files preserved
100%
100%
No original files removed
100%
100%
Marketplace file created
0%
100%
PR title format
0%
100%
PR Summary section
100%
100%
What's NOT Changed section
100%
100%
Rationale section
100%
100%
Test Plan section
100%
100%
Constructive tone
100%
100%
Changes explained
100%
100%
Skill frontmatter and instruction quality evaluation
Reserved word in name
100%
100%
Description voice issue
100%
100%
Missing trigger conditions
0%
100%
Non-imperative instructions
100%
100%
Absolute path identified
100%
100%
Hardcoded secret identified
100%
100%
Bare except identified
100%
100%
Category structure used
80%
100%
Summary table present
50%
100%
392d34c
Table of Contents
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.