Skip to content
Agentmart
Submit a tool

launch-checklist

Assess cross-functional launch readiness from supplied product, engineering, design, marketing, sales, support, legal, operations, analytics, risk, and…

Skill by ThorStarlord

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thorstarlord-launch-checklist

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Assess cross-functional launch readiness from supplied product, engineering, design, marketing, sales, support, legal, operations, analytics, risk, and approval evidence. Use for a risk_and_readiness responsibility and produce readiness_report with launch-blocking checks, conditions, rollback/monitoring requirements, and a bounded go/no-go recommendation. Do not mark work complete, approved, tested, scheduled, deployed, or ready without corresponding evidence; a checklist or recommendation never grants launch authority.

Use cases: design, data, marketing, sales

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/launch-checklist

What's inside

Skill name
launch-checklist
Description
Assess cross-functional launch readiness from supplied product, engineering, design, marketing, sales, support, legal, operations, analytics, risk, and approval evidence. Use for a risk_and_readiness responsibility and produce readiness_report with launch-blocking checks, conditions, rollback/monitoring requirements, and a bounded go/no-go recommendation. Do not mark work complete, approved, tested, scheduled, deployed, or ready without corresponding evidence; a checklist or recommendation never grants launch authority.
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • contract.md · references/

SKILL.md (first lines)

# Launch checklist

Satisfy a `risk_and_readiness` responsibility by producing `readiness_report`.

## Inputs

Require the launch scope and enough context to identify relevant readiness functions. Accept a PRD, risk analysis, release candidate/build evidence, QA/security/legal/design/operations evidence, GTM material, and explicit owner approvals when available. A launch date or tier may remain unknown rather than invented.

## Procedure

1. Read [references/contract.md](references/contract.md).
2. Bind the launch scope, tier if known, target window if known, and evidence/currentness boundary.
3. Inventory supplied evidence before evaluating checklist state.
4. Tailor checks to the launch rather than mechanically requiring every upstream template item.
5. Mark each check `evidence_backed_complete`, `blocked`, `planned`, `unknown`, or `not_applicable` according to durable evidence; never convert absence of evidence into completion.
6. Distinguish launch-blocking conditions from required and advisory work.
7. Preserve missing sign-offs, unresolved risks, unavailable rollback evidence, and unknown operational readiness as explicit conditions or blockers.
8. Form a bounded `go`, `go_with_conditions`, `no_go`, or `not_assessed` recommendation. This is advice, not execution authority.
9. Define proposed rollback triggers and monitoring expectations without claiming they are configured or tested unless evidence says so.
10. Stop when remaining uncertainty would not change the bounded readiness recommendation, or when required evidence/authority is unavailable.
11. Return `readiness_report` and control.

## Boundary

`checklist item present != work complete`, `validator PASS != launch ready`, `go recommendation != launch authorization`, `rollback plan written != rollback tested`, and `target date stated != date committed`.

From ThorStarlord/sensemaking-skills, MIT.

More from ThorStarlord/sensemaking-skills

Signals

Stars
0
Forks
0
Open issues
7
Last commit (this folder)
Sep 10, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ThorStarlord

Cite this page

launch-checklist skill. Agent Mart. https://agentmart.dev/skills/thorstarlord-launch-checklist (last updated 2026-10-24)