agentleFS
Sign inStart free
dmminga1983dmminga1983/minga-replica/skills/replica-launch/SKILL.md

replica-launch

Skill1 starsChanged 18 days agoMITView on GitHub

Write the launch of an app clone: the landing page built on the positioning angle, pricing set against the original's public prices and its users' complaints, and the store listings for App Store, Google Play and RuStore linted against each store's limits and copycat rules. Use for 'landing page', 'pricing', 'how much should I charge', 'App Store listing', 'RuStore listing', 'launch plan'; RU: лендинг, цены, сколько брать, описание для RuStore, описание для App Store, план запуска.

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start from listing.example.json.

    line 16
  2. Very specific:

    Read replica/region.txt (written by /replica-recon): ru, global or both.

    line 20
  3. Distinctive:

    No fake proof: No invented testimonials, user counts, ratings, press logos or "trusted by".

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

replica-launch

Reads replica/fixes.md, replica/brand.md, replica/brand.json. Writes replica/launch/: landing.md, pricing.md, listing.json, launch-plan.md.

python3 listing.py replica/launch/listing.json          # all stores in the file
python3 listing.py replica/launch/listing.json --store rustore

Start from listing.example.json. Limits live in stores.json (checked October 2026).

Region

Read replica/region.txt (written by /replica-recon): ru, global or both. It decides the stack, the stores, the laws and the trademark checks. python3 ../replica-architect/stack.py --region <region> prints them. No file yet: ask where the app will be sold and write it.

The rules

  • No fake proof. No invented testimonials, user counts, ratings, press logos or "trusted by". An empty proof section beats a fake one. Real beta users, with permission, are fine.
  • No reviewer quotes as testimonials.
  • The original's name stays out of your name, listing, keywords and ads.

Landing page

Hero (the angle as a headline, one line, one button, a real screenshot), the problem (the top two hate themes, paraphrased), how it works (three steps), features led by the fixes (parity is the price of entry), pricing, FAQ (the real objections, including importing from the old tool), the final call to action. In the brand voice, in every language you sell in, contrast-checked.

Pricing

The original's public pricing and two or three alternatives in one table, with URLs and the date read; what reviewers said about price, with counts; the model (free plan or trial, flat or per seat, monthly and annual); three tiers at most, named by who they are for; one-click cancel and clear renewal emails. Currency and tax by region: roubles with 54-FZ receipts for ru; for global, sales tax and VAT handled by you or by a merchant of record.

Store listings

Fill listing.json for every store you ship to, then listing.py: App Store (name 30, subtitle 30, promotional text 170, keywords 100, description 4,000), Google Play (title 30, short 80, full 4,000), RuStore (name 50, short 80, full 4,000), with ranking and price claims, emoji, caps, wasted keywords and the original's name flagged. Locales lint the same way.

Copycat rules are what review checks: Apple's guideline 4.1, Google Play's impersonation policy, RuStore moderation. Make your fixes and your brand visible in the first screenshots and the first lines of the description. Also prepare current screenshot sizes from each console, privacy labels and Google's data safety form, privacy policy and support URLs, age rating, review notes with a demo account.

ru, paid features: Google Play does not pay out to Russian bank accounts since 26 December 2024. Ship the free app there if you like; sell through RuStore's payments or the web.

Launch plan

Waitlist or beta before launch, analytics and error tracking live, where the original's unhappy users talk (the threads and chats from the research), a launch post that leads with the fix (Product Hunt or Hacker News for global; VC.ru, Habr and Telegram channels for ru), and the first ten users talked to by hand.

Next: /replica-deploy.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free