Review and improve skill quality. Use when: user asks to review skill, check skill quality, improve skill, or after creating a skill with skill-creator-pro.
Evaluates and refactors skills against a 9-dimension quality rubric.
/plugin marketplace add theflysurfer/claude-skills-marketplace/plugin install theflysurfer-claude-skills-marketplace@theflysurfer/claude-skills-marketplaceThis skill is limited to using the following tools:
ATTRIBUTION.mdreferences/dry-patterns.mdreferences/quality-rubric.mdreferences/refactoring-templates.mdreferences/review-examples.mdreferences/validation-checks.mdscripts/quality-checker.pySystematically evaluate and improve skill quality through scoring, refactoring, and iteration.
# Read main file
Read skills/skill-name/SKILL.md
# Discover all resources
Glob skills/skill-name/**/*
# Check line count
wc -l skills/skill-name/SKILL.md
Parse YAML frontmatter: name, description, license, allowed-tools.
Evaluate 9 dimensions (1-5 scale). See references/quality-rubric.md for detailed criteria.
| Dimension | Check |
|---|---|
| Clarity | Clear steps, no ambiguity |
| Completeness | All scenarios covered |
| Discoverability | Good name + description |
| Context Efficiency | < 500 lines, refs used |
| Actionability | Concrete, copy-paste ready |
| Resource Organization | Proper scripts/refs/assets |
| Examples | Concrete, realistic |
| Skill Chaining | I/O/Dependencies documented |
| Error Handling | Troubleshooting provided |
Average = Sum of 9 scores / 9
| Score | Status |
|---|---|
| 1.0-2.4 | Needs major rework |
| 2.5-3.4 | Functional, needs improvement |
| 3.5-4.4 | Good, minor refinements |
| 4.5-5.0 | Excellent, production ready |
Minimum for production: 3.5/5, no dimension < 3/5
For each dimension < 4/5, document with line references. See references/refactoring-templates.md for issue format.
Create prioritized plan:
See references/dry-patterns.md for common patterns.
Ask user before changes:
A) Show detailed plan
B) Execute Priority 1 automatically
C) Walk through one-by-one
D) Focus on specific dimension
After refactoring:
If score < 3.5/5, continue iterations. Safety limit: Max 5 iterations.
See references/validation-checks.md for complete list.
| Check | Requirement |
|---|---|
| Line count | SKILL.md < 500 lines |
| Name | ≤ 64 chars, lowercase + hyphens |
| Description | Third person, ≤ 1024 chars |
| Paths | Forward slashes only |
| References | One level deep |
| Long files | TOC if > 100 lines |
| No duplicates | Content in one place only |
| File | Content |
|---|---|
| references/quality-rubric.md | 9-dimension scoring details |
| references/dry-patterns.md | DRY violations and fixes |
| references/refactoring-templates.md | Report and plan templates |
| references/validation-checks.md | Automated and manual checks |
Before marking production-ready:
references/ directorySKILL.md.backup-YYYYMMDD-HHMMSSRecommandés (if score ≥ 3.5/5):
Read (usage: read SKILL.md, references/)Glob (usage: discover skill files)Grep (usage: search patterns, word count)Edit (usage: refactor SKILL.md)Write (usage: create references/*.md)Bash (usage: wc -l, backup files)User: "Review skills/my-skill"
↓
[THIS SKILL]
├─► Read SKILL.md + refs
├─► Score 9 dimensions
├─► Identify issues
└─► Generate report
↓
Score < 3.5/5?
YES → Refactor → Re-evaluate → Iterate
NO → Production ready ✅
↓
[Next steps]
├─► package_skill.py
└─► sync-personal-skills
Scenario: Review deployment skill
Command: "Review the skill at skills/deployment-manager/"
Result:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.