Use for cheap parallel web discovery (gpt-5.6-luna). Triggers: Luna search, parallel research, 루나검색, 루나 서치, 병렬 웹검색, 싸게 많이 찾아봐.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use for requested cheap, broad, parallel discovery (루나검색, 병렬 웹검색, 싸게 많이 찾아봐). Luna output is candidate evidence only; the main model runs cxc-search source-open proof before synthesis.
The user of this skill is already running on Luna, so do not call
catalog_list or any model-picker probe before spawning. Hardcode the model
directly on every spawn call:
agent_type: "explorer"
model: "gpt-5.6-luna"
reasoning_effort: "low"
If the spawn call returns a model-not-found / invalid-model error, do not retry
with a probe. Fall through to serial dispatch immediately: re-issue the same
spawn without the model field so the subagent inherits the main session model.
State plainly which path each agent took. No silent fallback to 5.5 and no
catalog round-trip — the error itself is the signal, and the serial retry is the
recovery.
Default reasoning_effort is "low" — Luna lanes are cheap discovery, not deep reasoning. Keep final judgment in the main session regardless.
| Condition | Reference |
|---|---|
| Before spawning discovery lanes | Spawn surface and skill attachment |
| Choosing lanes, waiting, proof handoff or final report | Swarm and report |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use for AST search and codemods. Triggers: ast-grep, sg, function/call/class/import, empty catch, missing await, YAML rules.
The English summary is being prepared. Showing the original description.
Use for coding, PR delivery, scaffolding and QA. Triggers: develop, fix, refactor, test, review, docs, browse, stacked PR, 개발, 수정, 검토, 스택 PR.
The English summary is being prepared. Showing the original description.
Use for module boundaries and dependencies. Triggers: circular import, coupling, barrel, re-export, validation placement, 모듈 경계, 순환 참조.
The English summary is being prepared. Showing the original description.
Use for APIs, servers and app databases. Triggers: REST, GraphQL, migration, query optimization, middleware, caching, queues, 백엔드, API 작업, 마이그레이션, 쿼리 최적화.
The English summary is being prepared. Showing the original description.
Use for code/PR/diff review and refactor audits. Triggers: review this, before merge, antipattern, 리뷰, 코드 리뷰, 머지 전에 확인.
The English summary is being prepared. Showing the original description.
Use for analytics and data pipelines. Triggers: ETL, ELT, data quality, SQL optimization, schema drift, backfill, 데이터 파이프라인, 데이터 품질, 백필.
The English summary is being prepared. Showing the original description.