Summary
If you're building skills for Claude and want to understand the format, this is the meta-skill that documents how to do it. It explains what skills are (modular packages that give Claude specialized workflows and domain knowledge), what they should contain, and the principles behind effective ones. The irony is that at 125 installs with passing security audits, it's clearly useful reference material, but you're mostly getting conceptual guidance rather than scaffolding tools or templates. Think of it as the style guide you read before writing your first skill, not a generator that writes one for you.
Install to Claude Code
npx -y skills add vercel-labs/portless --skill skill-creator --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
