The Skills Hub at /skills had cards that, when expanded, showed only the
one-line description, tags, author, version, and an install command. For
the 163 bundled and optional skills shipped with the repo, this was thinner
than the data we already have on disk.
Three changes, all under website/:
1. extract-skills.py now pulls four extra fields per local skill:
- 'overview' — first non-heading body paragraph from SKILL.md (stripped
of admonitions/code fences, capped at ~500 chars at a sentence boundary)
- 'envVars' / 'commands' — from the prerequisites: block in frontmatter
- 'license' — from the top-level frontmatter
- 'docsPath' — slug to the per-skill /docs/user-guide/skills/.../* page,
computed with the same logic as generate-skill-docs.py
162 of 163 local skills get a non-empty overview automatically. The
remaining one (media/heartmula) has only headings/code in its body and
falls through to the description.
2. Skill TS interface + SkillCard expanded-panel render the new fields:
- Overview paragraph at the top of the panel
- Prerequisites box (env vars + required commands) when frontmatter
declares them
- License row alongside author/version
- 'View full documentation →' link to the per-skill docs page
Search now covers the overview text too, so users can find skills by
matching content from inside SKILL.md, not just the one-line description.
3. styles.module.css gains six new classes (overviewBlock, detailLabel,
overviewText, prereqBlock/Row/Kind/List/Item, docsLink) styled to match
the existing dark panel aesthetic.
External / community skills (Anthropic, LobeHub, Claude Marketplace cached
indexes) keep the old behavior — overview is empty, no prereqs, no docsPath.
Validation: 'npm run build' clean (exit 0); broken-link count unchanged at
155 baseline; all 163 generated docsPath values resolve to existing pages
under website/docs/user-guide/skills/.
Adds a Skills Hub page to the documentation site with browsable/searchable catalog of all skills (built-in, optional, and community from cached hub indexes).
- Python extraction script (website/scripts/extract-skills.py) parses SKILL.md frontmatter and hub index caches into skills.json
- React page (website/src/pages/skills/) with search, category filtering, source filtering, and expandable skill cards
- CI workflow updated to run extraction before Docusaurus build
- Deploy trigger expanded to include skills/ and optional-skills/ changes
Authored by @IAvecilla
