beta-program-manager
Skill0 starsChanged 17 days agoMITView on GitHub
Plan and run a product beta from start to finish — goals, who to invite, what to ask them, how to track feedback, and the criteria for ending the beta and going live. Use when someone is planning a beta, early access program, pilot, or design partner program, needs invite or check-in messages for beta customers, wants to summarize beta feedback, or is deciding whether a beta is ready to graduate.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- cross-team-dependency-mapSkill
- customer-advisory-board-prepSkill
- 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
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 49
If the person hasn't set numbers for exit criteria, leave placeholders and flag them.
≈ “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
Beta program manager
A beta that never ends, or ends because someone got tired of it, teaches nothing. Every beta needs a question it's answering and a definition of done set before it starts.
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: Write the beta plan
# [Feature] beta plan
**Owner:** [person] · **Start:** [date] · **Planned end:** [date]
## What we need to learn
1. [Specific question, e.g. "Can admins set this up without help?"]
2. ...
## Exit criteria (decided before launch)
- Go live when: [specific, checkable conditions]
- Extend when: [conditions]
- Stop when: [conditions]
## Who's in
- Target: [N] customers matching [profile]
- Must have: [plan, use case, data, willingness to give feedback]
- Avoid: [accounts at risk, accounts with open escalations]
## What we're asking of them
- [Time commitment, e.g. one 30-minute call, a short survey at week 2]
## What they get
- [Early access, direct line to the team, influence on the roadmap]
## Risks
- [Risk] — [mitigation]Rules:
- Two to four learning questions. More than that, and the beta can't answer any of them well.
- Exit criteria must be checkable: "80% of beta accounts completed setup without a support ticket," not "customers are happy."
- If the person hasn't set numbers for exit criteria, leave placeholders and flag them. Don't invent thresholds.
Step 2: Track participants
| Account | Contact | Invited | Accepted | Activated | Last contact | Feedback given | Status |
Flag accounts that accepted but never activated, and accounts with no contact in two or more weeks.
Step 3: Collect and summarize feedback
Tag feedback against the learning questions first, then by theme (see the feedback-tagging skill). For each learning question, say what the evidence shows so far and how confident you can be with this many accounts.
Step 4: The exit readout
# [Feature] beta readout — [Date]
**Recommendation:** Go live / Extend / Stop
## Exit criteria
| Criterion | Target | Actual | Met? |
## What we learned
1. [Question] — [answer, with evidence]
## Must fix before going live
- [Item] — Owner: [name]
## Thank-you and next steps for beta customers
- [What they'll hear and when]Recommend; the owner decides. If criteria weren't met, say so plainly, even if the date has arrived.
Related skills
- feedback-tagging — tag what beta users say
- feature-flag-tracking — track who has the beta turned on
- launch-readiness-checklist — run go / no-go when the beta ends
- experiment-log — when the beta tests a hypothesis
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.

