skill-writer

A skill is a progressive-disclosure document set the agent loads on demand. Only the name + description are pre-loaded into context; the SKILL.md body is read when the skill triggers, and references/*.md files are read one at a time only when needed. Authoring a skill means writing for that loading model — not dumping a manual into context.

• SKILL.md is a router, not an encyclopedia. It gives a short overview and points to reference files; depth lives in references/.
• Only add what the model doesn't already know. Every token competes with the conversation. Skip what an LLM is already confident about.
• description drives discovery. Write it in third person, stating what the skill does and when to use it, with concrete trigger terms.
• Match this repo's house format, not Anthropic's generic # heading layout. Model new skills on the existing git-commit-convention skill.
• Use doc-writer for the prose. This skill owns skill structure, metadata, and progressive disclosure; doc-writer owns audience, voice, evidence, and Markdown presentation. This skill's house format wins if their guidance overlaps.
• Skills live in skills/{skill-name}/ — the skills/ subdirectory, never the repo root (the repo itself is also named skills).

This skill is pure markdown — no scripts or tooling, matching repo convention.

Core