pm-transversal-stakeholder
Skill1 starsChanged 42 days agoMITView on GitHub
Cross-phase skill for **stakeholder alignment, decision-rights design, and executive-ready reporting** — the hard-skill version of "stakeholder management". Invoke whenever multiple functions or leaders must converge on a decision, when "who decides what" is unclear, when an exec review/QBR is due, when a recommendation memo is needed, or when an escalation is being prepared. Trigger on "align stakeholders", "alinhe com time X", "exec review", "QBR", "write a memo for leadership", "DACI", "RACI", "escalation", "decision rights", "status report", "quem decide?", "briefar o diretor", "review panel", "pre-review the one-pager", "roda o painel". Works across all Double Diamond phases. Produces DACI pages, stakeholder maps, exec memos, review packs, and escalation notes.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- anti-slopSkill
- data-science-analystSkill
- humanize-deliverablesSkill
- humanizerSkill
- inference-disciplineSkill
- pm-archetype-aiSkill
- pm-archetype-enterpriseSkill
- pm-archetype-growthSkill
- pm-archetype-platformSkill
- pm-phase-defineSkill
- pm-phase-deliverSkill
- pm-phase-developSkill
- pm-phase-discoverSkill
- pm-prioritization-regua-comumSkill
- pm-product-senseSkill
- pm-storytellingSkill
- pm-transversal-analysisSkill
- pm-transversal-commsSkill
- pm-transversal-docsSkill
- repo-doctorSkill
- anti-slopSkill
- data-science-analystSkill
- humanize-deliverablesSkill
- humanizerSkill
- inference-disciplineSkill
- pm-archetype-aiSkill
- pm-archetype-enterpriseSkill
- pm-archetype-growthSkill
- pm-archetype-platformSkill
- pm-phase-defineSkill
- pm-phase-deliverSkill
- pm-phase-developSkill
- pm-phase-discoverSkill
- pm-prioritization-regua-comumSkill
- pm-product-senseSkill
- pm-storytellingSkill
- pm-transversal-analysisSkill
- pm-transversal-commsSkill
- pm-transversal-docsSkill
- pm-transversal-stakeholderSkill
- repo-doctorSkill
- umbertoSkill
- anti-slopSkill
- data-science-analystSkill
- humanize-deliverablesSkill
- humanizerSkill
- inference-disciplineSkill
- pm-archetype-aiSkill
- pm-archetype-enterpriseSkill
- pm-archetype-growthSkill
- pm-archetype-platformSkill
- pm-phase-defineSkill
- pm-phase-deliverSkill
- pm-phase-developSkill
- pm-phase-discoverSkill
- pm-prioritization-regua-comumSkill
- pm-product-senseSkill
- pm-storytellingSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 106
Every phase: pm-phase-discover, pm-phase-define, pm-phase-develop, pm-phase-deliver all need decision-rights clarity at key moments.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PM Transversal — Stakeholder alignment, decision-rights, exec reporting
Transversal skill — useful in every Double Diamond phase whenever humans must converge on a decision. Complements the phase skills with explicit decision-architecture artefacts.
Progressive loading
Load this SKILL.md first. For large or specialized tasks, use references/progressive-loading.md to choose the narrowest supporting reference before reading more.
When to use this skill
Invoke when:
- a decision involves more than 2 functions or 1 level of seniority above the PM
- "who decides?" is unclear or has drifted
- an executive review or QBR is being prepared
- a recommendation memo is needed (one-way vs two-way door framing)
- an escalation is imminent — and needs to be clean, not messy
- status reporting is absorbing too much time for too little decision-value
- a DACI, RACI, or RAPID needs to be designed or updated
Skip for decisions that are genuinely within PM authority and can be made in a PRD or decision log (→ pm-phase-define/references/decision-memo-daci.md for the artefact template itself).
Prime directive
Stakeholder management becomes a hard skill only when it produces concrete structures that reduce ambiguity and latency. "I had a meeting with X" is not alignment. A named driver, an approver, a decision date, and a written recommendation is alignment.
Core sub-skills
1. Stakeholder mapping and decision-rights design
Explicitly define who drives, approves, contributes, and is informed for important product decisions. Time-box decision windows. Document decision forums.
Outputs: DACI page, RACI matrix, stakeholder map (influence × interest), decision calendar, escalation protocol.
Anti-patterns: inviting everyone without clarifying roles, endless consultation, changing decision-maker mid-stream, status-sharing mistaken for alignment.
→ Deep-dive: references/decision-rights-daci.md
2. Executive-ready reporting and operating reviews
Translate product work into concise reporting that clarifies outcomes, trade-offs, risks, asks, and next decisions for senior stakeholders.
Outputs: executive memo, review deck (exception-based), KPI scorecard, portfolio recommendation note, decision/ask summary.
Anti-patterns: traffic-light reports without decisions, presenting too much detail, reporting outputs instead of outcomes, burying the ask or risk.
→ Deep-dive: references/exec-reporting.md
→ For the QBR / exec-review deck itself (slide-by-slide storyline, claim titles proven by evidence, 6–10 slide budget): pm-storytelling/references/deck-storyline.md
3. Stakeholder mapping (tactical)
Who are the stakeholders for this specific decision/initiative, what do they need to know/decide, what are their constraints and incentives, and how should they be engaged (sync/async, depth/summary)?
Outputs: stakeholder map, engagement plan, FAQ anticipating concerns, escalation ladder.
Anti-patterns: treating stakeholders as a single undifferentiated group, engaging everyone at the same depth, no plan for dissent.
→ Deep-dive: references/stakeholder-mapping.md
4. Review panel (multi-lens pre-review)
Run a stage-4 one-pager or a stage-6 PRD through the stakeholder lenses its exposures call for, drawn from five (commercial, customer success, marketing and positioning, exec and finance, user advocate), before the real stakeholders see it; every lens not run is named with a one-line reason, and a lens the author wants skipped because it might object is the one to run. Each lens returns an objection with its evidence gap and an owner, or "no objection" with a one-line reason. No objection is a valid output; a manufactured objection is a failure of calibrated disagreement (../DOCTRINE.md, behaviour 7). Companion to the pm-product-sense shadow evaluation: non-blocking, never a gate.
Outputs: panel report per lens, objections carried into the dissent protocol, unverified claims added to the assumption map.
Anti-patterns: manufactured objection, persona cosplay, panel as gate, skipping the lenses the author expects to object, running all five as a ritual, re-running until the report is clean.
→ Deep-dive: references/review-panel.md
Workflow
- Load context — the decision at stake, the phase it's in, and existing
.ai/memory/projects/<slug>/decisions.mdentries. When present,.ai/memory/org/goals.mdis what the exec lens reads first. - Classify the ask — decision rights, exec reporting, stakeholder map, or a review panel?
- Name the driver and approver explicitly — no "TBD", no "we'll figure it out".
- Frame one-way vs two-way door — the rigor required scales with reversibility.
- Write the recommendation before the meeting — meetings are for friction, not for drafting.
- Persist — decision artefact →
.ai/memory/projects/<slug>/decisions.md; stakeholder map →stakeholders.md; exec memo →.ai/memory/projects/<slug>/exec-memos/<topic>.md; panel report →reviews/<artefact>-panel-<date>.md.
Output contract
## [DACI / Exec memo / Stakeholder map]
### Decision at stake
### One-way or two-way door
### Roles
- Driver: ...
- Approver: ...
- Contributors: ...
- Informed: ...
### Recommendation (1 paragraph)
### Options considered
### Trade-offs and risks
### Ask (what we need from whom, by when)
### Decision date
### Memory updatesIntegration
- Every phase:
pm-phase-discover,pm-phase-define,pm-phase-develop,pm-phase-deliverall need decision-rights clarity at key moments. - Paired:
pm-transversal-docs(DACI published in Confluence),pm-phase-define/references/decision-memo-daci.md(template). - Agents: invoked implicitly by every agent when cross-function decisions arise; explicitly by
@pm-orchestratorand archetype agents for launch decisions, pricing changes, deprecation decisions, etc.
Communication modes follow ../../docs/patterns/COMMUNICATION_MODES.md. Per-skill: Lean (default) is a 1-page DACI + recommendation; Standard is the full memo with options and trade-offs; Caveman is a 4-line driver / approver / ask / date.
Success criteria
- decisions are made by named people within declared windows
- meetings leave with decisions, not "we'll sync again"
- exec reports prompt decisions, not information dumps
- escalations are clean: one memo, two options, one recommendation
- stakeholder surprises drop quarter over quarter
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

