Install
$ agentstack add skill-product-on-purpose-pm-skills-deliver-launch-checklist ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Launch Checklist
A launch checklist is a comprehensive verification document that ensures all functions are ready before releasing a feature or product. It coordinates across engineering, QA, design, marketing, support, legal, and operations to prevent launch-day surprises. Good launch checklists surface blockers early and create shared accountability for launch readiness.
When to Use
- 1-2 weeks before any significant launch
- During launch planning kickoff meetings
- When coordinating cross-functional releases
- Before major version releases or feature rollouts
- After incidents to improve launch processes
When NOT to Use
- You are validating whether to ship at all via an experiment -> use
measure-experiment-design - You need the customer-facing announcement of what shipped -> use
deliver-release-notes - The launch already happened and you want results or reflection -> use
measure-experiment-resultsoriterate-retrospective - The change is small and single-team with no cross-functional surface: a launch checklist adds ceremony without value; track it in the sprint instead
Instructions
When asked to create a launch checklist, follow these steps:
- Define Launch Context
Document what is launching, when, and who the key stakeholders are. Establish the launch tier (major release, minor feature, experiment) as this affects checklist scope.
- Gather Functional Requirements
For each function (engineering, QA, marketing, etc.), identify what must be complete, verified, or in place before launch. Distinguish between blockers (must-have) and nice-to-haves.
- Assign Owners and Dates
Every checklist item needs an owner and a target completion date. Ownership creates accountability; dates enable tracking.
- Identify Dependencies and Blockers
Flag items that block other work or are blocked by external factors. Surface these early so teams can unblock.
- Define Go/No-Go Criteria
Establish clear criteria for making the launch decision. What conditions must be met? Who makes the final call?
- Document Rollback Plan
Every launch should have a rollback strategy. Document how to revert if critical issues emerge post-launch.
- Schedule Check-in Cadence
Establish when the team will review checklist progress (daily standups, T-2 days review, launch day sync).
Output Format
Use the template in references/TEMPLATE.md to structure the output. A complete checklist fills every template section: Launch Overview; Engineering Readiness; QA & Testing; Design & UX; Marketing & Communications; Customer Support; Legal & Compliance; Operations & Infrastructure; Analytics & Monitoring; Go/No-Go Criteria; Rollback Plan; Check-in Schedule; and Open Issues.
Quality Checklist
Before finalizing, verify:
- [ ] All functional areas are represented
- [ ] Every item has an owner and target date
- [ ] Blockers are clearly distinguished from nice-to-haves
- [ ] Go/No-Go criteria are specific and measurable
- [ ] Rollback plan is documented and tested
- [ ] Check-in cadence is scheduled
Examples
See references/EXAMPLE.md for a completed example.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: product-on-purpose
- Source: product-on-purpose/pm-skills
- License: Apache-2.0
- Homepage: https://product-on-purpose.github.io/pm-skills/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.