Skip to content
Get packs

Replica Clone Tester

Plans, automates and reports bugs for a cloned app's user flows, using Playwright tests and a click-through.

Source Download skill
Repository
Jakeschincariol/replica-skill
Stars
7,057
Licence
MIT
Files
4 files

What it does

When installed, the agent reads the user-flow map of an app clone and writes a numbered test plan covering happy paths, edge cases and failure cases. It turns what it can into Playwright end-to-end tests that run against a local dev server, checks each screen for console errors, server errors and accessibility problems, and records any bugs it actually reproduces in a standard severity-ranked report. Things that cannot be automated, such as real emails or live payments, become a manual checklist.

Great for

  • Developers who have built an app clone and want systematic QA before shipping
  • Teams who want Playwright tests written from an existing flow map instead of from scratch
  • Anyone who wants bug reports with severity, steps and evidence rather than vague notes

Skip it if

  • Testing a third-party app you do not own: the skill itself says never to load test or script the original app's servers, and it only should be used on your own clone (risk of misuse or hitting someone else's service)
  • Projects without a recon flow map (replica/recon.md) or a local dev server, since the skill depends on both
  • Production sites with real payments or customer data: the tests use seed data and a Stripe test card, but running them against live systems would be risky

Try asking

  • “Test my clone against the recon flows and write the test plan”
  • “Find bugs in the booking flow and write the bug report”
  • “Write e2e tests for the checkout flow with Playwright”
  • “Click through everything and tell me what's broken”
Step-by-step guide: how to use Replica Clone TesterInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    replica-test.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip replica-test.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip replica-test.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run it against your local clone with seed data, never against the original app's live servers
  • Review generated Playwright specs before running them, since they execute in your project and the install step downloads packages and a browser
  • Keep the bug report's S1 and S2 items as the priority list; the skill itself says to ship nothing with an open S1

What's inside

  • bug-report.md
  • e2e.example.spec.ts
  • SKILL.md
  • test-plan.md

Redistributed unmodified from Jakeschincariol/replica-skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-11-02. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.