Article Prompts to Skills

Turn source prompts into small, demonstrable capability packages. Preserve the useful behavior, not the source page's brand or layout.

When to use this skill

• Converting an article's, tutorial's, or prompt pack's prompts into standalone AgentSkills folders (SKILL.md, agents/openai.yaml, demo/) with one independent capability per skill.
• Extracting the portable contract (behavior, data model, timing/accessibility rules, acceptance checks) while stripping the source's branding, layout, and hard-coded assets.
• Writing three example prompts (minimal, recreate-the-demo, remix) and building a working, inspectable demo with a preview screenshot for each new skill.
• Validating the finished package with quick_validate.py, browser checks at multiple sizes, and a narrow commit scoped only to the new skill work.
• Not for a source that is still raw HTML with no prompts extracted yet — run $html-to-interaction-prompts first — and not for tasks unrelated to packaging article content into reusable AgentSkills.

1. Inspect Before Extracting

1. Read the repository instructions and the complete source article.
2. Run git status --short; preserve unrelated work.
3. Inventory every explicit prompt, heading, example, asset, and acceptance criterion.
4. Search existing SKILL.md files for overlapping capabilities before creating folders.
5. If the source is raw HTML and the prompts do not exist yet, use $html-to-interaction-prompts first, then return here.