stakeholder-update
Skill0 starsChanged 38 days agoMITView on GitHub
Writes project stakeholder updates readable in under 60 seconds - honest RAG status, decisions made, explicit asks with owners and dates, next milestones - tiered to the audience. Use when someone asks "write my weekly project update", "how do I tell stakeholders we're at risk", "draft a status email for leadership", or "my updates get ignored, fix the format". Do NOT use for aggregating many teams' statuses into one engineering-wide report - use eng-status-rollup instead. For monthly investor letters with metrics and asks to VCs, use investor-update-writer; for customer-facing incident status, use status-page-update.
18 other projects use a version of this.
Adopted by
Most recently taken up by
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- Sach1ng/PM-operating-OStheir own version, first seen Nov 1, 2026
- codeApe-7/ai-agent-workflowGrouptheir own version, first seen Nov 1, 2026
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- fabiandistler/agentstheir own version, first seen Nov 1, 2026
- Tngc93/product-management-skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use experiment-designer, launch-readiness and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Dokkabei97Skillexperiment-designer
Designs A/B tests and product experiments with hypothesis structuring, sample size calculation, duration estimation, and result interpretation. Unified framework for both product and marketing experiments.
Also in 3 projects that use this
pratikshadakeSkilllaunch-readiness
Audits whether a feature or product is truly ready for launch with a structured checklist and readiness status (Ready/At Risk/Not Ready). Use before any product launch to catch critical gaps.
Also in 3 projects that use this
RhyGSkillwrite-prd
Also in 3 projects that use this
OpenAISkillmarket-sizing
Estimate market, segment, or opportunity size with transparent assumptions and uncertainty. Use for TAM/SAM/SOM, sizing scenarios, or comparing the scale of possible opportunities.
Also in 3 projects that use this
MetaSkillroadmap
Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.
Also in 3 projects that use this
dillonluiSkilldesign-review
Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- anthropics/knowledge-work-plugins★ 35ksame name
- me2resh/apexyard★ 542same name
- hamzafarooq/claude-code-starter★ 145same name
- Mehdibargach/claude-code-pm-skills★ 97same name
- codeApe-7/ai-agent-workflowGroup★ 18same name
- broomva/skills★ 4same name
- RizwanZafaris/product-manager-OS★ 4same name
- Sach1ng/PM-operating-OS★ 3same name
- ai-champions-hub/skills★ 2same name
- fabiandistler/agents★ 2same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- 1on1-agendaSkill
- async-communicationSkill
- feedback-writerSkill
- meeting-notes-to-actionsSkill
- okr-builderSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Every update has exactly these, in this order:
- Distinctive: line 90
Do not bury a blocker below the fold - no one reads paragraph four, and an unread ask is an unmade ask.
- Distinctive: line 91
Do not list activity instead of outcomes - meetings held is effort, not progress.
- Distinctive: line 92
Do not surprise stakeholders with a red that was amber for weeks - the earlier flag was the cheap moment to ask for help.
- Distinctive: line 93
Do not send the same wall of text to every tier - executives who scroll past detail once will skip the email entirely next time.
- Distinctive: line 94
Do not write asks without a named owner and date - "leadership should be aware" produces awareness, not action.
- Distinctive: line 100
Every ask has one name and one date.
“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Stakeholder Update
Stakeholders are busy and skim. A good update answers their questions before they ask them, in under 60 seconds of reading. The costly failure is the buried blocker: the ask that sat in paragraph four for three weeks, unread, until the project went red and the stakeholder's first question was "why am I hearing this now?"
Inputs to collect
- Audience tier (see below) - this decides length and vocabulary before anything else.
- Honest status: on track, at risk, or off track - and the one thing driving that call.
- Decisions made since the last update, with who made them.
- Asks: what is needed, from whom, by when. If there are none, confirm that is really true.
- Next 2-3 milestones with target dates.
- Cadence and send time - same day, same time, every time.
Audience tiering
One project, different updates. Write the core once, then tier it; sending the team-tier update to executives is how updates stop being read.
- Executive tier (sponsors, VPs): status line + one sentence of context + asks only. 60 seconds max, under 100 words. They act on exactly two things: the RAG signal and the asks. Cut decisions and milestones to links unless a decision needs their sign-off.
- Peer tier (adjacent leads, PMs, dependent teams): the full four-section format below, core under 150 words. They need decisions (which may affect them) and milestones (which they schedule against).
- Team tier (the working group): the four sections plus the Details block - metrics, links, technical context. This is the source document the other two tiers are cut from, never the other way around.
Rule: write for the peer tier by default, compress upward for executives, expand downward for the team. If one email goes to all tiers, structure it so the executive can stop after "Help needed" and lose nothing they act on.
The four sections
Every update has exactly these, in this order:
- Status - one-line health signal + a sentence of context.
- Decisions made - what was decided since the last update, and by whom.
- Help needed - explicit asks, each with an owner and a deadline. This is what gets you unblocked; make it the most scannable section.
- Next milestones - what is coming and when.
Skeleton
Subject: [FILL: project] Update - [FILL: date] - [FILL: On track / At risk / Off track]
Status: [FILL: Green / Amber / Red]
[FILL: one sentence of context - the single most important thing this period]
Decisions made:
- [FILL: decision] - [FILL: decider] - [FILL: date]
Help needed:
- [FILL: specific ask] - owner: [FILL: named person] - needed by: [FILL: date]
Next milestones:
- [FILL: milestone] - [FILL: target date]
Details (optional - team tier only):
[FILL: links, metrics, deeper context]The RAG status - the honesty rules
- Green - on track, no help needed.
- Amber - at risk; there is a specific, nameable thing that could derail it. Name it in the status sentence.
- Red - off track; a decision or resource is needed now, and the "Help needed" section says exactly which.
Sandbagging - reporting green when it is amber - destroys trust the moment reality hits, and one surprise red erases a year of credible greens. Flagging amber early is the mark of a strong owner, not a weak one. If the status has been amber for two consecutive updates with the same cause, escalate it as an explicit ask; amber is a flag, not a parking spot.
Writing rules
- Lead with the signal. Status first, context second - bottom line up front, always.
- Make asks unmissable. Each ask names one person and one date. "We could use more support" is not an ask; "Need Priya's sign-off on the vendor contract by Friday the 14th" is.
- Quantify when possible. "70% complete, 2 of 3 integrations done" beats "good progress" - the second is unverifiable, the first is a claim someone can check.
- Keep the core under 150 words (under 100 for the executive tier). Push depth into Details or a linked doc.
- Report outcomes, not activity. "Aligned on scope with legal" - not "had 5 meetings with legal."
- Be consistent. Same format, same section order, same send time, so readers learn where to look - weekly for active projects, biweekly for slow-burn.
Worked contrast
Bad status line: "Things are moving along, some challenges but the team is working hard." (No signal, no cause, unverifiable, and the reader learns nothing they can act on.)
Good status line: "Amber - API migration is 1 week behind because the vendor sandbox arrived late; recoverable if we get security review scheduled by the 20th (see ask below)." (Signal, cause, recovery condition, and a pointer to the ask.)
Deliverable
Produce the tiered update: the filled skeleton at the correct tier, core under the word budget, at least the status line and every ask carrying a name and a date, sent on the standing schedule.
Do NOT
- Do not bury a blocker below the fold - no one reads paragraph four, and an unread ask is an unmade ask.
- Do not list activity instead of outcomes - meetings held is effort, not progress.
- Do not surprise stakeholders with a red that was amber for weeks - the earlier flag was the cheap moment to ask for help.
- Do not send the same wall of text to every tier - executives who scroll past detail once will skip the email entirely next time.
- Do not write asks without a named owner and date - "leadership should be aware" produces awareness, not action.
Quality bar
- Readable in under 60 seconds at the target tier; core within the word budget.
- The RAG status matches what the sender would say privately - no sandbagging.
- Every ask has one name and one date; every milestone has a target date.
- A reader of the last three updates would not be surprised by this one's status.
Related skills
For rolling many teams' updates into one org-level report, use eng-status-rollup - it aggregates; this skill writes the single-project source it aggregates from. Investor letters have different anatomy (metrics, runway, asks to VCs) - use investor-update-writer. Customer-facing incident comms belong to status-page-update, and a one-off deep-dive summary for leadership is executive-summary territory.
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.

