MCP HubMCP Hub
SKILL·82E44F

foundation-stakeholder-briefings

product-on-purpose
업데이트됨 18 days ago
1 조회
452
58
452
GitHub에서 보기
디자인wordaidata

정보

이 스킬은 단일 진실 공급원 문서를 생성하고, 이를 기반으로 경영진이나 엔지니어링 부서와 같이 서로 다른 대상에 맞춤화된 여러 이해관계자별 브리핑을 생성합니다. 파생된 모든 브리핑이 추적 가능한 투영물로 일관성을 유지하도록 보장합니다. 동일한 핵심 정보를 각기 다른 프레이밍과 세부 사항이 필요한 다양한 그룹에 전달해야 할 때 사용하세요.

빠른 설치

Claude Code

추천
기본
npx skills add product-on-purpose/pm-skills -a claude-code
플러그인 명령대체
/plugin add https://github.com/product-on-purpose/pm-skills
Git 클론대체
git clone https://github.com/product-on-purpose/pm-skills.git ~/.claude/skills/foundation-stakeholder-briefings

Claude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요

문서

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

Stakeholder Briefings

A stakeholder-briefings artifact takes one source (a PRD, a discovery synthesis, a research report, a GTM or launch plan, experiment results, a retro or incident write-up, or raw notes) and produces a single saveable file containing:

  1. a master document: the canonical, audience-neutral synthesis of the work (what and why, decisions, status, risks and open questions, asks, timeline), with each claim numbered (M1, M2, ...); and
  2. a set of audience briefings: the same content re-pitched for each chosen stakeholder, one self-contained, copy-paste-ready block per audience.

The skill runs master-first, then projects. The master is the single source of truth; every briefing is a projection of it. A briefing may omit, reorder, and translate master content, but it may never assert a claim that is not in the master. That projection rule is what keeps the executive version and the engineering version from quietly disagreeing, and it is the difference between this skill and asking a model to "rewrite this six ways."

Distinct from foundation-stakeholder-update (one async update of meeting outcomes for a single audience, meeting-bound), discover-stakeholder-summary (a map of who stakeholders are and their influence/interest), and foundation-persona (a customer/buyer viewpoint to design or market against).

When to Use

  • One piece of work must reach several audiences who each need a different framing, decision, and level of detail (a spec going to engineering, design, data, and the funder at once).
  • You are about to manually rewrite the same update three to five ways, one per audience.
  • A decision or result needs to propagate across functions without the versions drifting apart.
  • A single audience needs a tailored briefing from a non-meeting source (N=1 is supported; the fan-out is the signature use, not a floor).

When NOT to Use

  • One async update of meeting outcomes for stakeholders. Use foundation-stakeholder-update (it is meeting-bound; that is its scope).
  • Understanding or mapping stakeholders (influence, interest, comms plan). Use discover-stakeholder-summary.
  • A persona to design or market against. Use foundation-persona.
  • There is no source content yet. This skill projects an existing artifact; it does not do the underlying analysis.

Instructions

When asked to create stakeholder briefings, follow these steps:

  1. Ingest and classify the source. Read the provided artifact. Classify its type (spec/PRD, discovery/research, GTM/launch, strategy/roadmap, experiment/metrics, incident/retro, compliance/privacy/security, or raw/ambiguous). If the source is thin, continue but set input_quality: low and name the gap.

  2. Build the master. Write the audience-neutral canonical document with these sections: What and Why, Decisions, Status, Risks and Open Questions, Asks, Timeline. Number every load-bearing claim with a stable ID (M1, M2, ...). The master carries no audience-specific spin; it is the shared substrate.

  3. Propose the audiences. From the source type, propose the relevant subset using references/source-type-map.md (for example, a spec proposes Engineering, UX/Design, Data/BI, Executive; a GTM plan proposes PMM, Sales, CS/Support, Executive). Present the proposal and accept go (generate the proposed set), an edit (drop X, add Y), or all (all nine). If invoked with --go, skip the prompt and generate the proposal. No audience is ever locked out.

  4. Project each briefing. For each chosen lens (see references/audience-lenses.md), render a self-contained block delimited by --- BEGIN: <lens> --- / --- END ---, containing:

    • Draws on: the master claim IDs this briefing projects (required).
    • Primary ask: exactly one decision or action for this audience (required).
    • a one-line headline, a "what this means for you" framing, and the body, at the lens's length, vocabulary, and tone. Every load-bearing line must trace to a master claim. Do not introduce a claim that is not in the master.
  5. Flag translations. Keep a translations-applied log (internal, below the shareable boundary) for every technical-to-business or inferred re-pitch, so the user can verify it lands. This section is never part of a shareable briefing.

  6. Self-check the invariant before finalizing:

    • Trace references resolve (deterministic, checkable): every briefing Draws on: ID resolves to a real master claim.
    • One CTA (deterministic, checkable): exactly one Primary ask: per block.
    • No untraced claim (review): re-read each block against its Draws on: set and confirm the body introduces nothing absent from those master claims. This is a review step, not automated.
    • Neutral master (review): the master has no audience-specific spin. List anything that fails.
  7. Render the artifact. Master (with claim IDs) -> the delimited briefing blocks -> the boundary marker -> the translations-applied log -> Sources and References. Remove all guidance blockquotes from the final output.

Audience lenses

Nine first-class lenses, each defined by the decision it owns, plus a Custom slot whose lens is inferred from the audience name and source and shown for confirmation. Full definitions, per-lens "not this lens when" boundaries, and the overlap matrix (Exec vs Board, PMM vs Sales, Engineering vs Data, Legal vs Exec) are in references/audience-lenses.md.

Output

  • A single artifact (filename YYYY-MM-DD_HH-MMtz_<title>_stakeholder-briefings.md), built from references/TEMPLATE.md.
  • Each briefing block is self-contained and send-ready (BEGIN/END cut-lines) so it can be copied out without edits.
  • A future --split mode (write each block to its own file) is deferred; v1 is single-artifact.

Quality checklist

  • Master present with numbered claim IDs (M1, M2, ...) and no audience-specific spin.
  • Each briefing block has a Draws on: line whose IDs all resolve to master claims.
  • Each briefing block has exactly one Primary ask:.
  • No briefing asserts a claim absent from the master (projection rule).
  • Audience set matches the source-type proposal or the user's edit; N=1 honored without refusal.
  • Translations-applied log present (internal) when any translation was made; boundary marker separates shareable blocks from internal sections.
  • Each briefing is at the lens's length and tone (a board block reads nothing like an engineering block).
  • Guidance blockquotes removed from the final artifact.

See also

GitHub 저장소

product-on-purpose/pm-skills
경로: skills/foundation-stakeholder-briefings
0
agent-skillsagentskillsai-skillsclaude-codeclaude-desktopcodex
FAQ

Frequently asked questions

What is the foundation-stakeholder-briefings skill?

foundation-stakeholder-briefings is a Claude Skill by product-on-purpose. Skills package instructions and resources that Claude loads on demand, so Claude can perform foundation-stakeholder-briefings-related tasks without extra prompting.

How do I install foundation-stakeholder-briefings?

Use the install commands on this page: add foundation-stakeholder-briefings to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.

What category does foundation-stakeholder-briefings belong to?

foundation-stakeholder-briefings is in the Design category, tagged word, ai and data.

Is foundation-stakeholder-briefings free to use?

Yes. foundation-stakeholder-briefings is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.

연관 스킬

executing-plans
디자인

executing-plans 스킬은 검토 체크포인트가 포함된 통제된 배치로 실행할 완전한 구현 계획이 있을 때 사용합니다. 이 스킬은 계획을 불러와 비판적으로 검토한 후, 소규모 배치(기본값 3개 작업)로 작업을 실행하면서 각 배치 사이에 진행 상황을 아키텍트 검토를 위해 보고합니다. 이를 통해 내재된 품질 관리 체크포인트를 갖춘 체계적인 구현이 보장됩니다.

스킬 보기
requesting-code-review
디자인

이 스킬은 코드 변경 사항을 요구 사항에 따라 분석하기 위해 코드 리뷰어 하위 에이전트를 호출합니다. 작업 완료 후, 주요 기능 구현 후, 또는 메인 브랜치에 병합하기 전에 사용해야 합니다. 이 리뷰는 현재 구현체와 원래 계획을 비교하여 문제를 조기에 발견하는 데 도움이 됩니다.

스킬 보기
connect-mcp-server
디자인

이 스킬은 개발자들이 HTTP, stdio 또는 SSE 전송 방식을 통해 MCP 서버를 Claude Code에 연결하는 포괄적인 가이드를 제공합니다. GitHub, Notion 및 사용자 정의 API와 같은 외부 서비스를 통합하기 위한 설치, 구성, 인증 및 보안을 다룹니다. MCP 통합 설정, 외부 도구 구성 또는 Claude의 모델 컨텍스트 프로토콜 작업 시 활용하세요.

스킬 보기
web-cli-teleport
디자인

이 스킬은 작업 분석을 기반으로 개발자가 Claude Code 웹 인터페이스와 CLI 인터페이스 중 선택할 수 있도록 돕고, 두 환경 간 원활한 세션 텔레포트를 가능하게 합니다. 웹, CLI 또는 모바일 환경 전환 시 세션 상태와 컨텍스트를 관리하여 워크플로를 최적화합니다. 다양한 단계에서 서로 다른 도구가 필요한 복잡한 프로젝트에 사용하세요.

스킬 보기