メニュー
Use when organizing a large local skill library into category router skills, refreshing a compact skill inventory, or deciding which leaf skill bodies need to be read before agent classification.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
| name | skill-router |
| description | Use when organizing a large local skill library into category router skills, refreshing a compact skill inventory, or deciding which leaf skill bodies need to be read before agent classification. |
Use this skill to organize many local skills without loading every leaf skill body into the model context. The script builds a compact inventory, marks ambiguous or duplicate-description skills for body review, and lets the agent author the final routing plan.
skill-router.config.json, or set
SKILL_ROUTER_LEAF_ROOTS, SKILL_ROUTER_EXPOSED_ROOT, and
SKILL_ROUTER_ROUTING_ROOT.SKILL.md bodies only when routing-review.md marks them under
Needs Body Review, the compact metadata is ambiguous, or a category boundary
would change.node scripts/skill-router.mjs scan.routing-review.md, skill-inventory.json, and the current
routing-index.json from the configured routing root.use_when and avoid_when boundaries
stay clear.routing-plan.json with all categories and routes.node scripts/skill-router.mjs apply, then scan, then validate.Theory(category boundary -> leaf routing) / Changed / Verified / Risk
Use first for ambiguous failures, messy project context, surprising results, repeated failures, postmortems, or contested product and architecture framing.
Use first for API boundaries, module ownership, domain modeling, contracts, architecture seams, and recurring design structures.
Use first for bounded code edits, refactors, implementation, simplification, control-flow cleanup, or maintainer clarity before choosing a more specific theory skill.
Use to organize a large skill library into category routers, route new skills, and propose new categories when existing routers are insufficient.
Use first when the user asks for tests, correctness, high reliability, static reasoning, proof, or safety evidence.
Use first for work shaped by users, tools, procedures, runtime evidence, operational artifacts, interfaces, or organizational workflows.