stakeholder-prep
Skill4 starsChanged 35 days agoMITView on GitHub
Prepare for a stakeholder meeting with an agenda, talking points, anticipated objections with responses, and a follow-up email draft. Use 30 to 60 minutes before a client or executive call. Usage - /stakeholder-prep describe the meeting and who is in it
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- change-requestSkill
- code-review-lightSkill
- deliverable-qaSkill
- exec-summarySkill
- meeting-prepSkill
- sow-reviewSkill
- status-commsSkill
- status-reportSkill
- transcript-actionsSkill
- weekly-briefSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 26
If the description is too thin to prepare from, ask up to three questions, then proceed.
- Distinctive: line 62
Use a professional, confident tone.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Stakeholder Prep
Prepare the delivery lead for a stakeholder meeting: agenda, talking points, anticipated objections with responses, and a ready-to-edit follow-up email. Run it 30 to 60 minutes before the call.
Input
$ARGUMENTS describes the meeting: who is attending, the purpose, and any context, for example:
/stakeholder-prep CFO review of project status; we are 2 weeks behind and need to discuss a scope reductionReference a project file for evidence when one exists:
/stakeholder-prep -- see my-projects/client/status-data.csv; meeting with CFO on the Q2 timelineIf the description is too thin to prepare from, ask up to three questions, then proceed.
Output
Meeting Objective: one sentence describing what a successful meeting looks like.
Suggested Agenda (with time allocations):
- Item 1 (X min)
- Item 2 (X min)
Key Talking Points: For each agenda item, 2 to 3 crisp, evidence-backed bullets. Executive audience: lead with the bottom line, follow with supporting detail.
Anticipated Objections / Tough Questions:
| Question or Objection | Recommended Response |
Prepare for the harder questions, not the straightforward ones.
What You Need From Them:
- Specific decisions, approvals, or inputs. Be explicit. When asking for a decision, bring three options; choosing is easier than creating.
Follow-Up Email Draft:
Subject: [Meeting topic]: Follow-Up and Next Steps
[Opening sentence referencing the meeting] [Summary of key decisions or agreements, 2 to 4 bullets] [Action items table with owner and due date] [Closing with next scheduled touchpoint]
The email is a draft. It carries the delivery lead's name, so it is not sent until they have read it and adjusted it to what was actually said in the room.
Use a professional, confident tone.
Example Output
Meeting Objective: Secure CFO approval for a 2-week timeline extension and agree on the scope reduction approach before the board update on May 15.
Anticipated Objections:
| Question | Recommended Response |
| "Why are we behind? You committed to this date." | "We hit two dependencies on client data access that weren't in the original plan. We flagged them in the Week 6 status report. Here's what we did to recover time..." |
| "What does a 2-week delay cost us?" | "Direct cost: approximately $X in additional resource time. Indirect: UAT readiness shifts to [date]. We've modeled three options; we're happy to walk through 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.

