Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Create high-quality skills with modular structure, progressive disclosure, and token-efficient design.
Create high-quality skills with modular structure, progressive disclosure, and token-efficient design.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
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/ βββ SKILL.md # Core instructions (SHORT) βββ [topic].md # On-demand details βββ references/ # Heavy docs (optional)
TopicFileSetup processsetup.mdTracking projectsmemory-template.mdPatterns and examplespatterns.md
Target 30-50 lines, max 80. Move details to auxiliary files. Every line must justify its token cost.
Level 1: Metadata (name + description) β always loaded Level 2: SKILL.md body β when skill triggers Level 3: Auxiliary files β on demand
One sentence, 15-25 words. Action verb first. Describes capabilities, not triggers. β Wrongβ 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: Frontmatter: name, slug, version, description ## When to Use β activation triggers ## Core Rules β 3-7 numbered rules
If 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?
TrapWhy it failsFixExplaining what X isModels already knowExplain WHEN and HOW"Use when..." in descriptionWastes charactersAction verbs onlyKeyword lists in descriptionLooks spammyOne clean sentenceTemplates inlineBloats SKILL.mdSeparate fileVague "observe" instructionsGets flagged suspiciousBe specific about what dataUndeclared file creationSecurity flagAdd Data Storage section
Install with clawhub install <slug> if user confirms: skill-manager β manage installed skills skill-update β update existing skills skill-test β test skills locally
If useful: clawhub star skill-builder Stay updated: clawhub sync
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.