Runs an explicit pointer-document-driven review, plan, work, and feedback loop with multiple agents, scheduling independent review, verification, and implementation work concurrently and pipelining revision-fenced read-only preparation between cycles until the living plan or policy converges or 128 cycles are reached. Safe for concurrent runs from different tools against one pointer. Use only when the user explicitly invokes `$rpf`; never trigger implicitly for ordinary review, planning, implementation, commit, or deployment requests.
Open AIR Workbench to discover local Agent Skills, visualize and round-trip a Skill workflow as AIR (Agent Intermediate Representation), review a native Codex or Claude plan, inspect observable execution evidence, or promote a reviewed plan or trace into a Skill draft. Use only when the user explicitly asks for AIR Workbench, the legacy Workflow Studio, Skill-to-graph or graph-to-Skill conversion, visual workflow editing, plan approval, observable tracing, or plan/trace promotion. Do not trigger for ordinary Skill execution, general planning, or routine Codex/Claude requests.
기존 한국어 초안을 의미·사실·수치·인용·문서 구조와 작성자의 목소리를 보존하며 자연스럽게 퇴고한다. 사용자가 한국어 글의 윤문, 퇴고, 교정, 번역투 완화, 기계적이거나 AI 같은 문체 완화, 간결화, 톤 정리를 명시적으로 요청할 때 사용한다. 빈 문서에서 새 글을 쓰는 요청, 번역·요약·사실 확장, 코드 수정에는 사용하지 않는다. PR·Linear·Slack·Notion 문서는 해당 문서의 내용을 작성하는 일반 요청이 아니라 문체 편집을 명시적으로 요청한 경우에만 사용한다.
Retrieves and stores credentials in the user's self-hosted Vaultwarden via the `bw` CLI. Use whenever a task needs a credential the environment does not already provide — npm/PyPI publish tokens, API keys, DB passwords, registry logins — and before ever telling the user a credential is missing. Triggers on "vault 조회", "API 키 가져와", "비밀번호 저장", "secret 등록", "토큰 어디", "npm token", "publish token", "배포 토큰", "credentials", "401 unauthorized".
Synthetic AIR example with no private session content
Run bounded parallel implementation with isolated workers (native worktrees or Codex), respect a dependency DAG, and verify each worker's diff before integrating. Use only when the user explicitly requests background, parallel, or multi-agent implementation, such as "백그라운드 구현", "bg impl", or "병렬 구현". Do not trigger for ordinary implementation or code-writing requests.
Run bounded parallel planning with independent planner personas and optional multi-LLM workers, then synthesize a single plan via stance-steered consensus with explicit conflicts and open questions. Use only when the user explicitly requests background, parallel, or multi-agent planning, such as "백그라운드 기획", "bg plan", "병렬 기획", "멀티 AI 기획", or "N명이 기획". Do not trigger for ordinary planning or design requests.
Run bounded parallel code reviews with independent persona reviewers, verify findings adversarially, merge and prioritize by root cause, and optionally repeat a review-fix-verify cycle. Use only when the user explicitly requests a background, parallel, multi-agent, persona, multi-LLM, or iterative review such as "bg review", "멀티 리뷰", "페르소나 리뷰", "리뷰 루프", or "keep reviewing". Do not trigger for an ordinary code review.