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

replica-test

Skill1 starsChanged 18 days agoMITView on GitHub

Test an app clone for bugs: a test plan from the recon flows with happy paths and edge cases (Cyrillic input, time zones, double submit, a second user's data), Playwright end-to-end specs, a click-through for the rest, and bug reports by severity until no S1 or S2 is open. Use for 'test my clone', 'find bugs', 'QA this', 'write e2e tests'; RU: протестируй, найди баги, тесты, проверь приложение.

  • Installs packages

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

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test your clone, never the original: No load testing, fuzzing or scripting against the original's servers.

    line 13

≈ “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-test

Reads the flows in replica/recon.md. Writes replica/test-plan.md, replica/bugs.md and specs in e2e/ (templates in this folder).

The rule

Test your clone, never the original. No load testing, fuzzing or scripting against the original's servers. Using it by hand to see how it behaves is fine.

Step 1: the plan

For every flow: the happy path; the edge cases that apply (empty input, very long input, emoji, Cyrillic and accents, two tabs, double submit, back and refresh mid-flow, slow network, offline, expired session, a second user's data must be invisible, time zones and daylight saving, 390px, keyboard only, screen reader labels); the negative cases (wrong password, payment declined with the provider's test card, permission denied, deleted record). Number them: F01-H1, F01-E3, F01-N2.

Step 2: automate

Playwright, one spec per flow, against the local dev server with seed data, selectors by role and label. Every spec fails on console errors and on any 5xx, and runs an axe accessibility scan on each screen.

npm i -D @playwright/test @axe-core/playwright && npx playwright install chromium
npx playwright test

Step 3: click through the rest

Emails arriving, real OAuth, payments end to end, visual glitches: a manual pass, with a browser tool on the local clone if one is available, screenshots per step, or a checklist for the user.

Step 4: bugs

bugs.md in the bug-report.md format. S1 data loss, security, payments, core flow blocked; S2 broken without a workaround; S3 with a workaround or visibly wrong; S4 cosmetic. Only what you reproduced; "might be" goes to a separate list.

Step 5: fix loop

S1 and S2 first. Failing test, fix, pass, keep the test, re-run the suite. Ship nothing with an open S1. Next: /replica-diff.

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