customer-advisory-board-prep
Skill0 starsChanged 19 days agoMITView on GitHub
Prepare for a customer advisory board (CAB) or customer council session — goals, member list, agenda, pre-reads, discussion questions, and a follow-up tracker that shows members what happened with their input. Use when someone is planning a CAB meeting, customer council, design partner session, or executive customer roundtable, needs a CAB agenda, invite, pre-read, or questions, or wants to write up and follow through on CAB feedback.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beta-program-managerSkill
- cross-team-dependency-mapSkill
- data-request-routerSkill
- decision-logSkill
- deprecation-planSkill
- duplicate-request-mergingSkill
- experiment-logSkill
- feature-flag-trackingSkill
- feedback-taggingSkill
- information-debt-auditSkill
- internal-enablement-briefSkill
- kpi-health-checkSkill
- launch-readiness-checklistSkill
- meeting-to-action-converterSkill
- new-pm-onboarding-packSkill
- pricing-packaging-change-logSkill
- process-documentationSkill
- product-metrics-definitionsSkill
- product-ops-contextSkill
- quarterly-planning-prepSkill
- raci-builderSkill
- release-notes-draftingSkill
- request-intake-triageSkill
- retro-facilitationSkill
- ritual-calendarSkill
- roadmap-hygieneSkill
- sprint-review-summarySkill
- support-escalation-patternsSkill
- tool-stack-auditSkill
- vendor-evaluation-scorecardSkill
- voice-of-customer-digestSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 18
Before anything else, write down two or three things the company wants to learn or test.
- Distinctive: line 52
Avoid leading questions ("Wouldn't it be great if…") and yes/no questions.
- Distinctive: line 73
Never record a feature commitment that wasn't explicitly made in the session.
≈ “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
Customer advisory board prep
A CAB is valuable only if members feel heard and the company learns something it couldn't learn from a survey. Both depend on asking a few sharp questions and closing the loop afterward.
Before you start
If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.
Step 1: Set the goals
Before anything else, write down two or three things the company wants to learn or test. Each should be something only these customers can answer:
- "Which of these three directions would change how you budget for us next year?"
- "Where does our product sit in your team's workflow today, and what's around it?"
Not: "Get feedback on the roadmap."
Step 2: Members
| Member | Company | Role | Segment | Why they're on the board | Account owner | Attending? |
Flag any member with an open escalation or at-risk renewal. The account owner should know before the session so it doesn't become a support call in front of the group.
Step 3: Agenda (example: 2-hour virtual session)
0:00 Welcome and goals for today (10 min)
0:10 What we heard last time and what we did with it (15 min)
0:25 Discussion 1: [learning goal 1] (30 min)
0:55 Break (5 min)
1:00 Discussion 2: [learning goal 2] (30 min)
1:30 Member-led topic: what's on your mind (20 min)
1:50 What happens next (10 min)"What we heard last time" is the most important slot. Skip it, and members stop believing their input matters.
Step 4: Discussion questions
For each learning goal, write three to five open questions that ask about their own experience and decisions, not opinions on features:
- "Walk us through the last time you had to [job]."
- "If you could only fix one part of that, which would it be, and why?"
Avoid leading questions ("Wouldn't it be great if…") and yes/no questions.
Step 5: Pre-read
One page: the goals for the session, what was done with last session's input, and the two or three topics with enough context to think about in advance. No sales material.
Step 6: After the session
# CAB session — [Date] — Write-up
## What we learned
1. [Learning goal] — [what members said, with short quotes by role, not name, unless agreed]
## Commitments we made
| Commitment | Owner | Due | Told members? |
## Follow-up to members (draft)
[Thank-you message, top takeaways, and what happens next]Never record a feature commitment that wasn't explicitly made in the session.
Related skills
- voice-of-customer-digest — bring the latest themes to the session
- meeting-to-action-converter — turn session notes into owned follow-ups
- feedback-tagging — tag what members say alongside other feedback
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.

