mcpbeat Sign in

Foundation Stakeholder Briefings Agent Skill

Turns any source artifact (spec, discovery, research, GTM plan, experiment results, retro, or raw notes) into one canonical master document plus a set of audience-tailored briefings, each re-pitched to a stakeholder lens (executive, board, engineering, UX, PMM, sales, CS, legal, data, or a custom audience). Every briefing is a traceable projection of the master, so the versions never disagree. Use when one piece of work must reach several audiences who each need a different framing, decision, and level of detail.

7k tokens
context cost
the whole folder, loaded on every use
7
files
instructions only
0
copies elsewhere
how many repositories repackaged it
516
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/product-on-purpose/pm-skills --skill foundation-stakeholder-briefings

The instruction itself

8 sections, as written by the author

<!-- 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:

  • 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
  • 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:

  • 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.
  • 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.
  • 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.
  • 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.

  • 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.
  • 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.
  • 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 Format

  • 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

  • references/TEMPLATE.md - the master + briefing-block scaffold.
  • references/audience-lenses.md - the nine lenses, boundaries, and overlap matrix.
  • references/source-type-map.md - the source-type to audience proposal.
  • foundation-stakeholder-update - one meeting update for one audience (distinct).
  • discover-stakeholder-summary - mapping stakeholders (distinct).

Other skills for the same job

different authors, same section of the catalogue
Create Technical Spike
by github
vendor ×1

Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation.

2k tokens
Spec To Backlog
by openai
vendor ×1

Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.

12k tokens
Grill With Docs
by sanity-io
vendor ×1

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

2k tokens
Clinical Decision Support Documents
by BioTender-max
×1

Guidelines for clinical decision support (CDS) documents: biomarker-stratified cohort analyses and GRADE-graded treatment reports. Covers structure, executive summaries, evidence grading (1A–2C), stats (HR, CI, survival), and biomarker integration. Use for pharma research docs, clinical guidelines, regulatory submissions.

3k tokens
Clinical Decision Support
by christophacham
×1

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

83k tokens scripts
Secure Workflow Guide
by christophacham
×1

Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas.

4k tokens
Adr Log
by ComeOnOliver
×1

Document architecture decisions with ADR (Architecture Decision Records). Use when making significant technical decisions, choosing between alternatives, or when onboarding needs context on past decisions.

7k tokens
Plan Approval
by ComeOnOliver
×1

Plan-approval workflow patterns for user control over AI actions in Claude Code Waypoint Plugin. Use when planning complex changes, need user approval before execution, want to prevent mistakes, or need to document proposed changes. Covers plan creation, approval checkpoints, plan deviation tracking, revision management, and learning from approved/rejected plans.

8k tokens

How to use it

Copy the folder

Take product-on-purpose/foundation-stakeholder-briefings from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.