foundation-stakeholder-update
Skill777 starsChanged 10 months agoApache-2.0View on GitHub
Produces async communication to stakeholders, primarily non-attendees and secondarily some attendees who want a reference. Translates meeting outcomes into what-it-means language for readers, with channel variants (slack, teams, email, notion, exec-memo) and audience variants (engineering, design, leadership, customer-facing, mixed). Surfaces a primary CTA up front, flags technical-to-business translations for user verification, and detects thread continuation from prior updates.
In this repository69 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- define-hypothesisSkill
- define-jtbd-canvasSkill
- define-opportunity-treeSkill
- define-prioritization-frameworkSkill
- define-problem-statementSkill
- deliver-acceptance-criteriaSkill
- deliver-edge-casesSkill
- deliver-launch-checklistSkill
- deliver-prdSkill
- deliver-release-notesSkill
- deliver-user-storiesSkill
- develop-adrSkill
- develop-design-rationaleSkill
- develop-solution-briefSkill
- develop-spike-summarySkill
- discover-competitive-analysisSkill
- discover-interview-synthesisSkill
- discover-journey-mapSkill
- discover-market-sizingSkill
- discover-stakeholder-summarySkill
- foundation-build-risk-reviewSkill
- foundation-lean-canvasSkill
- foundation-meeting-agendaSkill
- foundation-meeting-briefSkill
- foundation-meeting-recapSkill
- foundation-meeting-synthesizeSkill
- foundation-okr-writerSkill
- foundation-personaSkill
- foundation-prioritized-action-planSkill
- foundation-stakeholder-briefingsSkill
- iterate-lessons-logSkill
- iterate-pivot-decisionSkill
- iterate-refinement-notesSkill
- iterate-retrospectiveSkill
- measure-dashboard-requirementsSkill
- measure-experiment-designSkill
- measure-experiment-resultsSkill
- measure-instrumentation-specSkill
- measure-okr-graderSkill
- measure-survey-analysisSkill
- tool-design-sprint-briefSkill
- tool-design-sprint-decide-and-storyboardSkill
- tool-design-sprint-map-and-targetSkill
- tool-design-sprint-prototype-planSkill
- tool-design-sprint-readinessSkill
- tool-design-sprint-sketchSkill
- tool-design-sprint-test-and-scoreSkill
- tool-foundation-sprint-approach-optionsSkill
- tool-foundation-sprint-basicsSkill
- tool-foundation-sprint-briefSkill
- tool-foundation-sprint-differentiationSkill
- tool-foundation-sprint-founding-hypothesisSkill
- tool-foundation-sprint-magic-lensesSkill
- tool-foundation-sprint-readinessSkill
- tool-note-and-voteSkill
- utility-mermaid-diagramsSkill
- utility-pm-changelog-curatorSkill
- utility-pm-criticSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Distinctive: line 26
After a meeting with outcomes affecting teams who were not in the room
- Distinctive: line 27
When a decision or commitment needs to propagate to downstream teams async
- Distinctive: line 28
When a recap exists and needs to be translated into audience-specific language
- Distinctive: line 29
When the user needs something from readers (specific CTA) and cannot afford for it to be buried
- Very specific: line 49
If invoked with --go, skip the inference summary.
- Distinctive: line 53
When asked to create a stakeholder update, follow these steps:
- Distinctive: line 68
If action is needed: lead with it, not bury it If FYI-only: state explicitly in the TL;DR
- Distinctive: line 69
If FYI-only: state explicitly in the TL;DR
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->Stakeholder Update
A stakeholder update is async communication to readers who need to know the outcomes of a meeting. Primary audience is non-attendees; secondary audience is some attendees who want a reference version (came in late, stepped out, need something to forward).
Distinct from foundation-meeting-recap in audience, format, and purpose: the recap is a summary of what happened for people who were in the room; the stakeholder-update is a translation of outcomes into what-it-means for readers (tailored to their role, with technical-to-business translation where the audience warrants it).
Distinct from /discover-stakeholder-summary: that skill is about understanding stakeholders (input to the user's work). This skill is about communicating to stakeholders (output from the user's work).
This skill belongs to the Meeting Skills Family. It conforms to the Meeting Skills Family Contract.
When to Use
- After a meeting with outcomes affecting teams who were not in the room
- When a decision or commitment needs to propagate to downstream teams async
- When a recap exists and needs to be translated into audience-specific language
- When the user needs something from readers (specific CTA) and cannot afford for it to be buried
When NOT to Use
- Summarizing what happened for attendees. Use
foundation-meeting-recap. - Broadcasting status with no specific audience tailoring. A plain Slack message is sufficient; the skill adds value when translation or CTA framing matters.
- Communicating research findings to stakeholders. Use
/discover-interview-synthesisplus targeted comms. - The source is not one meeting's outcomes but a broader artifact (a spec, discovery synthesis, research report, GTM plan, or experiment results) that needs to fan out to several audience-tailored briefings from one canonical master. Use
foundation-stakeholder-briefings.
Zero-friction execution
Per the family contract, this skill never blocks on interrogation. Default flow:
- Load related recap (preferred) or raw meeting notes
- Detect thread continuation by scanning same directory for prior stakeholder-updates on the same
project/topics - Infer channel (if not specified) from audience variant: engineering / design → slack; leadership → email; mixed → notion
- Present a brief inference summary (detected channel, audience, CTA, thread continuation if any, translation candidates)
- Accept
goor corrections - Produce the channel-tailored update
If invoked with --go, skip the inference summary. The entire output is shareable content (per family contract. no separate summary block needed).
Instructions
When asked to create a stakeholder update, follow these steps:
- Load related recap Parse frontmatter to extract meeting context, decisions, actions, outcomes. If no recap provided, accept raw meeting notes with a lower input-quality flag.
- Detect thread continuation
Scan same directory for prior
stakeholder-updateartifacts with matchingproject/topics. If found, reference the prior update in the frontmatterthread_continuation_offield. - Present go-mode inference summary Show inferred channel (if not specified), detected audience, proposed CTA, thread continuation status, translation candidates (flagged jargon or acronyms that may not land).
- Distill key outcomes From the recap or notes, select 3-5 outcomes that matter to the target audience. Do not include everything from the recap. filter by audience relevance.
- Frame the CTA If action is needed: lead with it, not bury it If FYI-only: state explicitly in the TL;DR
- Translate technical-to-business Flag jargon and acronyms unlikely to land with the audience. Provide plainer alternatives. Keep a translations-applied log for user verification in the output's Generation context.
Build the channel-tailored variant
- Slack / Teams: headline (one action-oriented line, optionally one emoji), TL;DR 3 bullets, context sentence, "what this means for [audience]", CTA (bold with marker if action needed; italic "FYI-only" if not), thread-continuation link, more-links footer
- Email: subject line (topic + outcome), greeting ("Hi [audience]"), opening sentence (headline + why they are receiving this), TL;DR, context 2-3 sentences, what was decided / advanced, what this means for your team, what I need from you (with by-when), thread reference, sign-off
- Notion: rich H1/H2/H3 structure, longer context block, collapsible sections for detail, table for decisions and actions
- Exec-memo: TL;DR first (3-4 lines), supporting detail in 3 sections max, asks section upfront, formal tone, no emoji
- Render TEMPLATE.md with the selected variant as primary Other variants may be included as collapsible alternates for user flexibility. Remove all guidance blockquotes from the final artifact.
- Validate
channelis in enumaudience_variantis in enumprimary_ctais non-empty (use "FYI-only" if no action needed)related_recapis a valid filename reference or flagged as raw-notes input
Quality Checklist
- Channel variant matches the specified or inferred channel
- Audience variant's "what this means for you" is specifically tailored (not generic)
- CTA is surfaced up front, not buried
- Technical-to-business translations are logged in Generation context for user verification (INTERNAL. outside shareable boundary)
- Thread continuation referenced if prior updates exist on the same topic
## Shareable updatesection present with channel-tailored body (v1.1.0. replaces "entire output is shareable" from v1.0.0)- Explicit boundary marker between Shareable update and internal sections (translations, sources)
- Sources and References section lists the source recap and any prior updates in thread (INTERNAL)
- Filename uses v1.1.0 variant pattern:
YYYY-MM-DD_HH-MMtimezone_title_stakeholder-update-{channel}-{audience}.md
See also
- Meeting Skills Family Contract
foundation-meeting-recap. upstream: primary input source/discover-stakeholder-summary. distinct purpose (understanding stakeholders, not communicating to them)
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.

