Summary
If you're maintaining a skills repo with any kind of standards, you know the pain: someone dumps a wall of text, calls it a skill, and breaks validation. This workflow gives you the six-phase discipline to go from rough notes to a compliant SKILL.md that actually passes metadata checks and fits the catalog. It leans hard on dogfooding the repo's own scripts (find-a-skill.sh, add-a-skill.sh, test-a-skill.sh) and enforces a definition of done with no exceptions. The facilitation protocol borrows from workshop-facilitation for guided sessions, and it's opinionated about when to use the wizard versus content-first generation. Honest take: it's process-heavy, but if you've ever had to clean up after ad hoc skill submissions, you'll appreciate the guardrails.
Install to Claude Code
npx -y skills add deanpeters/product-manager-skills --skill skill-authoring-workflow --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 →
