skill-scaffoldlisted
Install: claude install-skill jacob-balslev/skills
# Skill Scaffold
## Coverage
- Authoring flow: copy → rename → adapt → strip teaching annotations → verify → commit
- Frontmatter identity: `schema_version`, `name`, `description`, `version`, `type`, `category`, `scope`, `owner`, plus the eval-health triple and `drift_check` required by every Skill Metadata Protocol v6 skill
- Archetype selection: how to pick between `capability`, `workflow`, `router`, and `overlay` and which `## H2` body sections each archetype requires
- v6 understanding fields: when to add `comprehension_state`, `mental_model`, `purpose`, `boundary`, `analogy`, `misconception`, and when the legacy `concept` back-compat block is still useful
- Semantic-layer discipline: how `description:` (≤ 3 sentences, pushy, boundary-aware routing contract) differs from `## Coverage` (bulleted scope map of distinct topics) and why each must stay in its own layer
- Teaching-layer mechanics: how to use `> **TEMPLATE NOTE:**` blockquotes and `# TEMPLATE NOTE:` YAML comments to teach without cargo-culting meta sections into derived skills
- Lint-first authoring gate: passing focused skill lint against your new skill before commit, every time, no exceptions
- Routing-eval honesty: defaulting to `routing_eval: absent` and only flipping to `present` after `node scripts/skill-graph-routing-eval.js --skill <name>` exits 0
- Grounding declarations: when to populate `grounding.truth_sources`, when URL truth sources are acceptable, and how local truth-source hashes differ from ext