skill-authorlisted

# skill-author: grow the library deliberately, or not at all The studied failure mode is real: a library of 557 imported skills with 3 in use. Skills are context spent on every session's listing. Each one must earn that. The general rule this ladder instances - every addition declares where it is paid, and the always-on surface carries the highest bar - is decision 0015. ## 1. Should this be a skill? (ladder: stop at the first rung) 1. **One-off knowledge?** Put it in the task, not the library. 2. **A durable fact or rule?** It belongs in the owning doc (`docs/standards/`, DESIGN.md, AGENTS.md if truly universal), not a skill. 3. **Mechanically checkable?** Add a check to `checks/check.mjs` + a fixture test. Never send a model to do a linter's job. 4. **Recurring *method* requiring judgment** (a way of working you'd teach a new senior hire) → that is a skill. The trigger: you've needed it three times, or you know you will. ## 2. Write it Create `.agents/skills/<name>/SKILL.md` (open Agent Skills standard): - **Frontmatter**: `name` = directory name (lowercase, hyphens, ≤64 chars); `description` ≤1024 chars stating *what it does* **and** *when to load it*. Write the trigger phrases the moment of need actually contains; this line is all the model sees when deciding to load it. - **Body ≤500 lines**, imperative, information-dense. Structure: purpose (one line) → the method (numbered, decision points explicit; ladders beat essays) → what to record → how it