This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
91
87%
Does it follow best practices?
Impact
99%
1.83xAverage score across 3 eval scenarios
Passed
No known issues
Command file structure and naming
Kebab-case filename
100%
100%
Project-level directory
100%
100%
Description frontmatter
0%
100%
Argument-hint frontmatter
0%
100%
Square bracket for optional arg
0%
100%
Correct invocation path
0%
70%
Frontmatter description is action-oriented
0%
100%
Imperative verb-first instructions
100%
100%
Concrete usage example
0%
100%
Error handling section
50%
100%
Expected outcomes included
83%
100%
Agent-optimized instruction writing
Imperative form throughout
100%
100%
Explicit tool for npm
0%
100%
Expected outcomes stated
70%
100%
Concrete realistic examples
0%
100%
Specific error handling
0%
100%
Success criteria defined
80%
100%
Anti-patterns called out
0%
100%
Specific not vague instructions
80%
100%
Project-level placement
100%
100%
Required description frontmatter
0%
100%
Numbered steps
100%
100%
Iterative fixing pattern
Max iteration limit stated
100%
100%
Stuck detection logic
100%
100%
TodoWrite for iteration tracking
0%
100%
Immediate todo completion
0%
100%
Bash tool for make
0%
100%
Per-category fix instructions
100%
100%
Stop conditions documented
100%
100%
Stuck reporting format
100%
100%
iteration-design.md produced
100%
100%
Imperative form
100%
100%
Project-level placement
100%
100%
3027f20
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.