Menu
Use when need to create reusable technique, pattern, or reference guide for AI agents
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when approach is chosen and need a detailed implementation plan before coding. After researching, before implementer
Use when idea is vague, multiple interpretations exist, scope is undefined, or stakeholders need alignment before technical work begins
Use when requirements are fuzzy, multiple technical approaches exist, or change affects architecture, API, data, or security
Use when an approved implementation blueprint exists and you are about to start implementation
Use when code needs behavior-preserving restructuring to improve clarity, reduce duplication, or enable safer changes without altering outputs
Use when need to create specialized subagent for recurring tasks, domain-specific work, or pipeline automation
| name | creating-skills |
| description | Use when need to create reusable technique, pattern, or reference guide for AI agents |
Skills are reference guides for proven techniques, patterns, or tools. They help AI agents find and apply effective approaches.
Skip if: one-off solution, project-specific convention (→ put in CLAUDE.md), or well-documented elsewhere.
| Type | Purpose | Example |
|---|---|---|
| Technique | Concrete method with steps | discovering, researching |
| Pattern | Way of thinking about problems | creating-subagents |
| Reference | API docs, syntax guides | tool documentation |
skills/
skill-name/
skill.md # Main reference (required)
*.md # Supporting files if needed
---
name: skill-name
description: Use when [specific triggering conditions].
---
# Skill Name
## Overview
What is this? Core principle in 1-2 sentences.
## When to Use
- Symptoms, situations, triggers
- When NOT to use
## Quick Reference
Table or bullets for scanning.
## Core Pattern
Main technique or approach.
## Delegate (if applicable)
Which agents/subagents to use and when.
## Common Mistakes
What goes wrong + fixes.
Description = When to Use, NOT What It Does
# ❌ BAD: Describes process
description: Evaluates options with evidence to choose approach.
# ❌ BAD: Too vague
description: For research tasks.
# ✅ GOOD: Triggering conditions only
description: Use when requirements are fuzzy or multiple approaches exist.
Why: If description summarizes workflow, AI may follow description instead of reading the full skill content.
creating-skillsdiscovering, researching, creating-subagentsBefore writing:
Description determines when skill is loaded. Write it before content.
Run scenarios where skill should activate:
When skill fails, identify the gap and fix.
| Mistake | Fix |
|---|---|
| Description describes process | Only triggering conditions |
| Too much content | Minimal, scannable, tables |
| Narrative storytelling | Structured reference format |
| Project-specific rules | Put in CLAUDE.md instead |
| No "When to Use" section | Always include triggers and skip conditions |
| Generic labels in examples | Semantic, meaningful names |
Reference other skills by name:
# ✅ Good
**Prerequisites:** Use **discovering** skill first.
# ❌ Bad: force-loads file
@skills/discovering/skill.md