본문으로 건너뛰기
cccskills
무료GitHub에 공개

pm-as-solo-orchestrator

Use when planning a delivery request as the only orchestration agent - one board-writing subtask, backlog first, one approval question, then move approved tasks to todo

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md3.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

PM as Solo Orchestrator

Overview

When product-manager is the only enabled orchestration agent, the plan you write for a request is not a multi-agent handoff — it's one subtask that writes the board, followed by columns doing the rest of the work automatically.

Core principle: One subtask creates the tasks; the board, not the plan, drives every stage after that.

Rules

  • All subtasks are assigned to product-manager — never to system-architect, security-agent, backend-developer, frontend-developer, mobile-developer, data-scientist, game-developer, or qa-agent. Developer work goes through create_board_task, not an orchestration subtask.
  • Multiple parallel PM subtasks are fine only when every one is read-only (e.g. web research + list_board_tasks concurrently). At most one subtask per parallel group may write to the board; a second board writer in the same group rejects the whole plan. Use depends_on to sequence when a later subtask needs an earlier one's result.
  • Delivery stages (analiz, implementation, QA verification, pm_uat, approval) are board columns the task travels through afterwards — never plan a subtask per stage; that opens one board record per stage for a single piece of work and is rejected before the plan runs.
  • Analiz tasks skip approval — they go straight to todo (investigation is always safe to start).
  • Planner sets ready=false only when a product decision blocks creating any board task (max 3 questions, see stakeholder-intake's ask-vs-assume rule). Otherwise ready=true.

Standard flow — one subtask, in order

  1. Create the tasks in backlog (see implementation-task-spec, acceptance-criteria-gwt).
  2. Call ask_user, choice mode:
    • context: what you asked / what you're assuming (name each assumption so the stakeholder can correct it cheaply) / the task list with assignee and order.
    • options: "Start all (recommended)", "Start only some", "Change something", plus whatever else applies.
  3. On approval, move every approved task to todo with move_board_task. Order lives in blocked_by — never hold a task back in backlog to fake an order; a blocked task parks itself and starts automatically once its blocker lands.
  4. On partial approval, move only the selected tasks; leave the rest in backlog.
  5. On rejection or requested changes, update_board_task the affected fields, or delete_board_task + create_board_task for assignee/derived_from (creation-only fields) — and for task_type when update_board_task's schema does not list it.
  6. Report which tasks moved to todo (agents will pick them up) and which stay in backlog, and why.

This is ONE subtask calling these tools in order — not three subtasks. Splitting it hands the same board record to several agents that cannot see each other's writes.

If a blocking product decision remains, call ask_user within a subtask — never append questions as markdown in the final summary.

Common Mistakes

  • A subtask per delivery stage instead of one subtask that creates the tasks.
  • Holding implementation tasks in backlog "until analiz is done" instead of using blocked_by — the board already enforces that order.
  • Two parallel subtasks writing to the board in the same group.
  • Approval-question context that doesn't separate what you asked from what you assumed.

Red Flags

  • A plan with a subtask named "QA stage" or "pm_uat review" — those are columns, not subtasks.
  • More than one board-writing subtask in a parallel group.
  • A task left in backlog with a "Depends on: …" sentence instead of blocked_by.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use when writing acceptance criteria for a task - express each as an observable Given/When/Then that QA can execute, including negative cases

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

makifbaysal/tasktrooper1172026년 10월 21일 업데이트

Use when the diff adds or changes an endpoint, resolver, RPC, job or query that takes an object id, a role check, a request binding or a tenant filter - BOLA/IDOR, function-level authorization, mass assignment and tenant scoping

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

makifbaysal/tasktrooper1172026년 10월 21일 업데이트

Use on every UI change - semantic HTML, labels for controls, keyboard-navigable dialogs/menus, visible focus, and never color as the only signal

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

makifbaysal/tasktrooper1172026년 10월 21일 업데이트

Use when a task changes any screen, form, dialog, menu or control - Lighthouse/axe scan of the changed screens, a keyboard walk, and the thresholds that fail a task

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

makifbaysal/tasktrooper1172026년 10월 21일 업데이트

How to work a task returned with review, QA or UAT findings. Use when a task is in need_revision or PR review comments are in your context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

makifbaysal/tasktrooper1172026년 10월 21일 업데이트

Use when the repository keeps its alerting in code, or a person asks for alerts outside TaskTrooper - PrometheusRule YAML, a Cloud Monitoring alert policy in Terraform, a Datadog monitor, each routed to TaskTrooper's alert ingest URL so it opens an incident here

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

makifbaysal/tasktrooper1172026년 10월 21일 업데이트

makifbaysal의 스킬 모두 보기

이 스킬의 문제 신고