SkillAgentSearch skills...

launch-check

Passive pre-launch report card for a live URL of an app or site built with AI (Lovable, Bolt, Replit, Cursor, v0, Claude).

Install / Use

npx skills add davepoon/buildwithclaude --skill launch-check

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

91/100

Category

Security

Supported Platforms

Claude Code
Cursor
Replit Agent

Our assessment of launch-check

launch-check scores 91/100 on our quality scale, 432nd of 1,103 Security skills we index (top 40%).

Its SKILL.md is 5.0 KB long, well organised into 9 sections with 4 code examples: a solid amount of guidance for an agent.

With 3,715 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so launch-check is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-11-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

launch-check compared with similar skills

All 4 of these similar skills score higher than launch-check; compare them before choosing.

SkillScoreStarsUpdatedFormat
launch-check (this skill)by davepoon913.7ktodaySKILL.md
taste-skillby Leonxlnx100109.4ktodayCLAUDE.md
Agent-Reachby Panniantong100108.4k2d agoCLAUDE.md
headroomby headroomlabs-ai10078.7ktodayCLAUDE.md
Scraplingby D4Vinci10094.7ktodayMCP Server

Frequently asked questions

How do I install launch-check?
Run npx skills add davepoon/buildwithclaude --skill launch-check. The install tabs above show the steps for each supported agent.
Which AI agents does launch-check work with?
It is written for Claude Code, Cursor and Replit Agent, as a SKILL.md file. Other agents that read the same format can often use it too.
Is launch-check safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is launch-check still maintained?
The repository was last updated today, so launch-check is actively maintained.

name: launch-check description: Passive pre-launch report card for a live URL of an app or site built with AI (Lovable, Bolt, Replit, Cursor, v0, Claude). Scores security (secret keys visible in the page JavaScript, Supabase service_role keys, open Supabase or Firebase tables with --owner-check, security headers, HTTPS, cookies), phone design at 375 px, Google and AI search, and speed, then writes a "fix this first" list. Use when the user asks "is my app safe to launch", "did I leak my API key", "is my Supabase open", or wants a pre-launch checklist. category: security license: MIT

Launch Check

scripts/launch_check.py (Python standard library; Playwright optional) loads a live URL the way a visitor's browser does, scans what it downloaded, runs the two bundled audits (scripts/polish_audit.py for phone design, scripts/geo_audit.py for search) and prints one report card. Run the tool and explain what it found; do not judge the site by reading it. Source (MIT): https://github.com/Ces107/agent-forge/tree/main/skills/launch-check

When to Use This Skill

  • The user asks whether an app or site is ready or safe to launch, or wants a pre-launch checklist.
  • The user asks whether an API key (Stripe, OpenAI, Anthropic, AWS, Supabase service_role) leaked into the frontend.
  • The user asks whether their Supabase or Firebase database can be read by anyone.
  • Not for authenticated flows, API fuzzing or penetration testing.

What This Skill Does

  1. Finds Python 3.9+ (python3 --version, then python --version, then py -3 --version on Windows) as <PY>; <DIR> is the folder that holds this SKILL.md.
  2. Runs <PY> "<DIR>/scripts/launch_check.py" <url> --report launch-report.html.
  3. Scores four areas 0-100 with PASS (80+) / WARN (50-79) / FAIL (under 50), and an overall score (security 40 %, the other three 20 % each; any exposed secret or open table caps it at 39).
  4. Gives a verdict (NOT READY, ALMOST READY, READY TO LAUNCH) and a prioritized fix list, plus a one-page HTML report.

Options:

  • --owner-check: only when the user confirms they own the site. If the page contains a Supabase URL with its public anon key (or a Firebase databaseURL), it lists which tables exist and reads at most 1 row per table (GET only, at most 20 tables, never writes; row contents are never printed or saved).
  • --repo .: also scan the local project for committed .env files and secrets in tracked files.
  • --prompt: only the fix list, as a prompt for the AI that built the app. --json: everything.
  • --skip phone,search,speed: faster partial run. --fail-under 80: exit 1 below this score.
  • Phone design and page-load metrics need Playwright (<PY> -m pip install playwright, then <PY> -m playwright install chromium). Ask the user before installing; without it those checks are skipped.

How to Use

Basic Usage

Is my app ready to launch? https://my-app.example
python3 scripts/launch_check.py https://my-app.example --report launch-report.html

Database check (site owner only)

python3 scripts/launch_check.py https://my-app.example --owner-check --prompt

Example

User: "Did I leak anything? https://my-app.example"

Output:

SCORE 30/100  NOT READY: 5 things to fix before you launch
FAIL  Security                0  Anyone can see your Stripe secret key in your website's code (+7 more)
WARN  Phone design           77  The page is wider than a phone screen (+4 more)
FIX THIS FIRST
 1. HIGH   Anyone can see your Stripe secret key in your website's code
              in /assets/index-4f9c2a.js   value sk_l...(50 chars)

Then: an exposed secret key is already public, so move the call server-side, keep the key in a server environment variable and rotate it in the provider dashboard. For an open table, enable Row Level Security or database rules and re-run with --owner-check. Paste the --prompt output into the AI that built the app, redeploy, re-run.

What It Fetches

Only the URL the user passes and that site's public files: the page, its same-site scripts, links on the home page, /favicon.ico, robots.txt, sitemap.xml, llms.txt, and up to 5 same-site pages for the search check. With --owner-check, also the Supabase project or Firebase database that page references, read-only. It never probes hidden paths such as /.env or /admin, never writes to any server, and sends nothing anywhere else (no telemetry, no third-party API). Secrets are cut to their first 4 characters in all output.

Tips

  • Exit code 0 = ready, 1 = findings, 2 = bad URL or the site could not be loaded. HTTP 403 usually means bot protection: run it on a preview URL.
  • A Supabase anon key or a Firebase web key in the page is normal (INFO/LOW); safety depends on Row Level Security and key restrictions, which --owner-check tests.
  • A good score means these common launch mistakes were not found, not that the app is secure: no login flows, no API fuzzing, no server-side auth checks. Scripts served from another host are not scanned.

Related Skills

View on GitHub
GitHub Stars3.7k
CategorySecurity
Updated20h ago
Forks683

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions