stakeholder-comms
Skill2 starsChanged 7 days agoApache-2.0View on GitHub
Draft a team-facing message about a decision, tradeoff, or change — Slack, PR or RFC comment, email — so it is diplomatic, specific, and drives a decision rather than narrating. Use when writing a blurb for the team, announcing a change that affects others, explaining a tradeoff to stakeholders, or pushing back on a proposal without relitigating sign-offs already given. Produces a draft the user sends under their own name; Slack messages are drafted, never sent. Do NOT use for PR descriptions (see create-pr) or routine status replies.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- insight68/Skillstheir own version, first seen Nov 8, 2026
- andreaskelm/pm-braintheir own version, first seen Oct 17, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
- gmanch94/claude-code-aidlc-templatetheir own version, first seen Jul 11, 2026
- michaelsvanbeek/personal-agent-skillstheir own version, first seen Apr 9, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- andreaskelm/pm-brain★ 235same name
- insight68/Skills★ 5same name
- gmanch94/claude-code-aidlc-template★ 2same name
- michaelsvanbeek/personal-agent-skills★ 1same name
- akachandan1/proofstack★ 0same name
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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adopt-evalSkill
- contract-validationSkill
- create-prSkill
- designSkill
- graphifySkill
- helm-upgradeSkill
- ingest-readingSkill
- investigate-alertSkill
- k8s-debugSkill
- parallax-reviewSkill
- shiny-engineerSkill
- stop-slop-codeSkill
- systematic-debuggingSkill
- upstream-triageSkill
- verify-claimsSkill
The file
Files
Skill: Stakeholder Comms
Draft team-facing messages (Slack, PR/RFC, email) about a decision, tradeoff, or change so they're diplomatic, clear, and decision-driving -- without relitigating prior sign-offs or making anyone defensive.
When to use
- Drafting a message to a team or another team about a decision, tradeoff, surfaced complexity, or asking them to choose or do cross-team work.
- Especially when the message touches someone else's prior decision, or asks another team for effort.
When NOT to use
- Notes to self, status one-liners, commit messages, internal bd comments.
Principles
- Honor prior decisions. Acknowledge any sign-off explicitly; don't relitigate. Frame newly-surfaced complexity as discovered during implementation -- blameless, not "the design was wrong."
- Enable, don't block. Lead with "ready to run either way"; you're confirming alignment, not resisting.
- Neutral, symmetric options. Present each path's value first, then cost. Don't stack the deck; make the lighter path visible without disparaging the chosen one.
- Concrete, not alarmist. Quantify complexity (real numbers, named artifacts) but keep the tone even.
- Ask for a clear decision and state what you need from them.
- Redact + link out. Strip internal-only details from anything external; link external/public docs over internal ones.
- Format for the medium. Short, bulleted, scannable. In Slack avoid markdown tables (won't render) and code-block tables (hard to copy) -- prefer bullets. Keep clickable links outside code blocks.
- Offer to dial the tone (softer/firmer) rather than guessing.
Output
- The copy-paste-ready message.
- A one-line note on the tone/framing choices made, and an offer to adjust the lean.
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.

