Is the Launchworthy skill free?

Yes. The skill itself is free from Wunderlandmedia/launchworthy. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Launchworthy SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Launchworthy?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Launchworthy with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Launchworthy

Production-readiness audit for vibe-coded apps: scored scorecard plus fix list

by Wunderlandmedia · Wunderlandmedia/launchworthy

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 18, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 1bd7843

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 18, 2026; it's queued for a re-test.

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 18, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran it against a planted Vite+React+Supabase demo carrying eight real production holes. Following the checklist surfaced roughly 15 severity-tagged findings across all five domains with exact file paths and fix playbooks, including the Supabase-specific ones a quick review misses: RLS off as the CRITICAL root cause, the committed .env needing key rotation rather than mere deletion, and correctly NOT flagging the public anon key as a leak. A no-skill eyeball pass of the same code caught about five issues as a flat list with no severities and no urgency ordering. A clear, reproducible edge over the baseline, and it honestly marks live-only checks as MANUAL CHECK NEEDED instead of self-certifying.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Launchworthy does

A stack-agnostic production readiness audit for apps shipped fast with AI tools (Lovable, Bolt, v0, Cursor, Claude Code). Auto-detects framework and backend, runs severity-tagged checks across five domains (Frontend, Backend, Auth & Security, Infrastructure, Operations), and outputs a scored scorecard plus a prioritized punch list with file paths and copy-paste fixes. Triggers on 'is this production ready', 'harden this', 'audit my app', or 'is my Supabase secure'.

How to install Launchworthy

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Launchworthy

/launchworthy Production-readiness audit for vibe-coded apps: scored scorecard plus fix list

It also activates on plain-language prompts like these:

Is my Supabase app production ready before I launch it to real users?
Can you harden this app I vibe-coded with Cursor before I ship it?
Audit my app for security holes, I built it fast with AI tools.

Frequently asked questions

Is the Launchworthy skill free?: Yes. The skill itself is free from Wunderlandmedia/launchworthy. SkillProof publishes the install command and an independent test verdict at no cost.
Does Launchworthy work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 18, 2026. Verdict: Tested · Works. Ran it against a planted Vite+React+Supabase demo carrying eight real production holes. Following the checklist surfaced roughly 15 severity-tagged findings across all five domains with exact file paths and fix playbooks, including the Supabase-specific ones a quick review misses: RLS off as the CRITICAL root cause, the committed .env needing key rotation rather than mere deletion, and correctly NOT flagging the public anon key as a leak. A no-skill eyeball pass of the same code caught about five issues as a flat list with no severities and no urgency ordering. A clear, reproducible edge over the baseline, and it honestly marks live-only checks as MANUAL CHECK NEEDED instead of self-certifying.
What is the Launchworthy SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Launchworthy?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Launchworthy with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.