Create high-quality skills with modular structure, progressive disclosure, and token-efficient design.
On first use, read setup.md for integration guidelines.
User wants to create or improve a skill. Agent guides structure, reviews content, and ensures quality.
If user wants project tracking, create folder in their home directory.
See memory-template.md for the template structure.
The agent does NOT create files automatically. Always ask user first.
Skills follow this structure:
skill-name/
├── SKILL.md # Core instructions (SHORT)
├── [topic].md # On-demand details
└── references/ # Heavy docs (optional)
| Topic | File |
|---|
| Setup process | setup.md |
| Tracking projects | memory-template.md |
| Patterns and examples | patterns.md |
Target 30-50 lines, max 80. Move details to auxiliary files. Every line must justify its token cost.
Level 1: Metadata (name + description) — always loaded
Level 2: SKILL.md body — when skill triggers
Level 3: Auxiliary files — on demand
One sentence, 15-25 words. Action verb first. Describes capabilities, not triggers.
| ❌ Wrong | ✅ Right |
|---|---|
| "Use when user needs PDFs" | "Process, merge, and extract PDF content" |
| "Helper for Docker" | "Build, deploy, and debug Docker containers" |
| "Git guide" | "Manage branches, resolve conflicts, and automate workflows" |
See patterns.md for more examples.
Every skill needs:
## When to Use — activation triggers## Core Rules — 3-7 numbered rulesIf content exceeds 20 lines or is only needed sometimes, split to separate file. Reference from Quick Reference table.
Information lives in ONE place. SKILL.md references files, doesn't duplicate content.
Read the skill as if you're an agent encountering it fresh. Is every instruction clear and necessary?
| Trap | Why it fails | Fix |
|---|---|---|
| Explaining what X is | Models already know | Explain WHEN and HOW |
| "Use when..." in description | Wastes characters | Action verbs only |
| Keyword lists in description | Looks spammy | One clean sentence |
| Templates inline | Bloats SKILL.md | Separate file |
| Vague "observe" instructions | Gets flagged suspicious | Be specific about what data |
| Undeclared file creation | Security flag | Add Data Storage section |
Install with clawhub install <slug> if user confirms:
skill-manager — manage installed skillsskill-update — update existing skillsskill-test — test skills locallyclawhub star skill-builderclawhub sync