launch-checklist
Skill0 starsChanged 52 days agoMITView on GitHub
Generates a launch checklist tailored to launch type, internal pilot, beta, or general availability, with named owners and explicit go/no-go gates for each stage. Use when the user is planning a product launch, rollout, or release and needs a checklist, launch plan, rollback plan, or go/no-go criteria.
26 other projects use a version of this.
Adopted by
Most recently taken up by
- getpaidskills/skillstheir own version, first seen Nov 8, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- fullstackinnoAI/skillstheir own version, first seen Nov 1, 2026
- munnam77/claude-for-solopreneurstheir own version, first seen Oct 20, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
Used with
Projects with it also use patch-notes, asset-audit and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CoralGameSkillpatch-notes
Generate player-facing patch notes from git history, sprint data, and internal changelogs. Translates developer language into clear, engaging player communication.
Also in 4 projects that use this
CoralGameSkillasset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
Also in 4 projects that use this
- +10 more from CoralGame
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- aakashg/pm-claude-code-setup★ 152same name
- hamzafarooq/claude-code-starter★ 145same name
- striderZA/OpenCodeGameStudios★ 118same name
- Mehdibargach/claude-code-pm-skills★ 97same name
- tranhieutt/software_development_department★ 71same name
- cenconq25/claude-code-app-studio★ 40same name
- aroyburman-codes/pm-skills★ 25same name
- CoralGame/Claude-Code-Game-Studios★ 19same name
16 more not listed
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 repository4 other files it gives its agents.
- competitive-teardownSkill
- eval-rubric-writerSkill
- prd-drafterSkill
- user-interview-synthesizerSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
7
Distinctive
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 15
Ask if it is not already stated.
- Distinctive: line 35
Ask for whatever is missing:
- Distinctive: line 47
If the user does not have an owner for a required gate, do not leave the row blank.
- Distinctive: line 61
Tracked, not blocking: should be done, but a gap is a judgment call for the launch owner rather than an automatic stop.
- Distinctive: line 69
Always fill in the rollback plan section, even for an internal pilot.
- Distinctive: line 77
If the user asks for a checklist but has not told you whether the rollback mechanism has been tested, do not assume it has.
- Distinctive: line 80
If two people are named as owner for the same gate, ask who is accountable if it slips.
“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Launch checklist
A checklist with no owner on a row is a checklist that will still be incomplete at launch. Every gate in the output needs a name or a role attached, and every gate needs to be labeled as a hard blocker or a tracked item, not left ambiguous.
Step 1: Confirm launch type
Ask if it is not already stated. The three types below need meaningfully different checklists; do not reuse a beta checklist for a GA launch or the reverse.
- Internal pilot: employees or a small named group, not the public. Lightest checklist. Still needs internal comms and a feedback channel, does not need legal, compliance, or external comms.
- Beta: external users, but opted in, limited, or clearly labeled as beta. Needs a support runbook (what the support team does when a user hits a problem), a feedback channel, and a kill switch. Does not necessarily need full legal or compliance review, but ask if the product touches regulated data before assuming it does not.
- General availability (GA): everyone. Needs the full set: legal or compliance review if the product touches user data, payments, or a regulated domain, monitoring and alerting in place before launch, a tested rollback path, an external comms plan, and on-call coverage for at least the first 48 to 72 hours.
Step 2: Gather owners and inputs
Ask for whatever is missing:
- Owner for each relevant function: engineering, support, and, for beta or GA, legal or compliance if applicable, and marketing or comms if there is external communication.
- Whether a rollback mechanism exists (feature flag, config toggle, full revert) and whether it has been tested.
- The specific success criteria or metrics that will be checked after launch, not "see how it goes."
- Anything already known to be incomplete or risky, so it lands in the checklist rather than being discovered at launch.
If the user does not have an owner for a required gate, do not leave the row blank. Write "unassigned, needs an owner before launch" so the gap is visible rather than silently dropped.
Step 3: Build the checklist
Use templates/launch-checklist-template.md. Split items into two tables:
- Go/no-go gates: hard blockers. The launch does not proceed until every row is done, or the launch owner explicitly accepts the risk in writing (record that acceptance in the Notes column, do not just check the box).
- Tracked, not blocking: should be done, but a gap is a judgment call for the launch owner rather than an automatic stop.
Tailor which items are gates versus tracked based on launch type from Step 1. For example, a tested rollback path is a gate for GA and should usually be tracked-not-blocking for an internal pilot, where the blast radius of a bad rollout is small.
Always fill in the rollback plan section, even for an internal pilot. "No rollback needed, we will just turn the pilot off" is a valid answer, but it should be written down rather than left blank.
Decision rules
- A GA launch with no legal or compliance review and no stated reason one is unnecessary goes in the go/no-go gates table, not tracked-not-blocking.
- If the user asks for a checklist but has not told you whether the rollback mechanism has been tested, do not assume it has. Write "not yet tested" and put it in gates for GA, tracked for beta or pilot.
- If two people are named as owner for the same gate, ask who is accountable if it slips. A gate with two owners functions like a gate with none.
Anti-patterns
- Items with no owner, or an owner written as "the team" instead of a name or role.
- Copying a GA-level checklist onto an internal pilot, which slows down a low-risk launch for no reason, or copying a pilot-level checklist onto a GA launch, which under-scopes real risk.
- A rollback plan section that says only "we can always roll back" without naming the mechanism, the owner, or how long it takes.
- A post-launch check-in with no specific metrics named, which in practice means no one checks anything.
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.

