Create effective Claude Code SKILL.md files following Anthropic's official patterns. Use when writing new skills, improving existing skills, or learning skill best practices.
/plugin marketplace add wayne930242/Reflexive-Claude-Code/plugin install ACE-core@Reflexive-Claude-CodeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/examples.mdreferences/patterns.mdreferences/spec.mdscripts/init_skill.pyscripts/validate_skill.pyCreate skills that extend Claude's capabilities with specialized knowledge and workflows.
references/ if approaching limit.py scripts for tasks requiring exact format or validation; for templates, prefer Python scripts over raw markdown to ensure stable formatting.claude/
└── skills/
└── skill-name/
├── SKILL.md # Required: instructions (<200 lines)
├── scripts/ # Optional: executable code
├── references/ # Optional: docs loaded on-demand
└── assets/ # Optional: templates, images
Run the init script to create proper structure:
python3 scripts/init_skill.py <skill-name>
Options:
--path, -p: Output directory (default: .claude/skills)Frontmatter (required):
---
name: my-skill
description: [What it does]. Use when [specific triggers].
---
Body: Instructions only. Keep lean—move details to references/.
python3 scripts/validate_skill.py <path/to/skill>
Restart Claude Code, trigger naturally (don't mention skill name).
| Level | When | Format |
|---|---|---|
| High | Multiple valid approaches | Text guidance |
| Medium | Preferred pattern exists | Pseudocode |
| Low | Fragile/critical operations | Specific scripts |
Split content when SKILL.md grows:
## Quick start
[Essential usage]
## Advanced
- **Forms**: See [forms.md](references/forms.md)
- **API**: See [api.md](references/api.md)
Claude loads references only when needed.
.claude/rules/Rules = conventions shared across skills.
If you find yourself repeating the same guideline in multiple skills:
.claude/rules/ using write-rules skill