Summary
When you're building Claude Code plugins, getting skills right means understanding progressive disclosure: metadata triggers the skill, SKILL.md provides instructions, and bundled resources (scripts, references, assets) load only when needed. This skill walks you through the creation process starting with concrete examples, then planning what belongs in scripts versus references versus assets, then structuring it all with strong triggering descriptions. The distinction between references (docs Claude reads) and assets (files Claude uses in output) is subtle but matters for context efficiency. If you're writing your first skill or wondering why Claude isn't picking up your existing ones, the triggering guidance alone is worth it.
Install to Claude Code
npx -y skills add anthropics/claude-plugins-official --skill skill-development --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
