Replica Test , click through every flow of an app clone and find the bugs
The QA step of the Replica pack: test plan generated from the recon flows (happy paths, edge cases, negative cases), Playwright end-to-end tests, manual click-through for the rest, bug reports in a fixed format with severity
Curated by Skill Harbor: the QA step of the 11-skill Replica pack: click through every flow of an app clone and test it for bugs. It generates a test plan from the recon flows with numbered cases (happy paths, edge cases like double-click submit and expired sessions, negative cases like declined cards), automates what it can with Playwright (roles and labels for selectors, axe accessibility scans), click-throughs the rest by hand, and files every reproduced bug in a fixed format with severity. by @Jakeschincariol, listed here with credit to its creator. Honest caveats: one hard rule, test your clone, never the original (no load testing or hammering someone else's servers); pairs with replica-build, reads the flows from the recon map. Ship nothing with an open S1. Skill Harbor never reviews the code, review it yourself before use. Discovered via GitHub.
Version:
Quick answer
Replica Test is the QA step of the Replica pack, by Jakeschincariol. It generates a numbered test plan from your recon flows — happy paths, edge cases and negative cases — automates what it can with Playwright, click-throughs the rest by hand, and files every reproduced bug in a fixed format with a severity.
At a glance
| What it is | A testing skill for app clones: it turns the flows documented in a recon map into a test plan, runs automated and manual checks against your clone, and reports the bugs it reproduces. |
|---|---|
| Who it's for | Developers who built an app clone (with Replica Build or on their own) and want a systematic QA pass before calling it done. |
| What you give it | Your clone running on a local dev server, and the flows from your recon map. Automated tests need Node.js for Playwright. |
| What you get | A numbered test plan covering happy paths, edge cases (like double-click submits and expired sessions) and negative cases (like declined cards), Playwright end-to-end tests, accessibility scans, and bug reports in a fixed format with severity. |
| Works with | Muse, installed from this page with the copy-paste install prompt. It tests YOUR clone on your local machine — its hard rule is to never test the original app. |
| Cost | Free |
| Time | A few minutes to install. The QA pass itself depends on how many flows your clone has — a handful of flows is a short session, a full app takes longer. |
Example — a checkout flow under test
An example of the kind of run the skill is built for, based on the cases its own documentation lists:
- From the recon map, the skill drafts numbered cases for the clone's checkout flow: a clean purchase as the happy path, a double-click on the submit button as an edge case, and a declined card as a negative case.
- The automatable cases become Playwright tests that run against the clone on the local dev server; anything Playwright cannot cover is clicked through by hand.
- Each bug that actually reproduces is filed in the skill's fixed format with a severity, so you can fix by priority — and its rule is to ship nothing with an open top-severity bug.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 77c9436Prerequisites: a clone built with replica-build (or any local app) running on a local dev server; Node.js for Playwright. Install "Replica Test , click through every flow of an app clone and find the bugs" for me. It gives my agent @Jakeschincariol's QA workflow, the testing step of the Replica pack: numbered test plans from the recon flows, Playwright end-to-end specs with accessibility scans, manual click-through checklists, fixed-format bug reports with severity, and a fix loop (failing test first, then fix). Hard rule: test the clone, never the original's servers. Repository: https://raw.githubusercontent.com/Jakeschincariol/replica-skill/77c9436fb3d18c3d58169efb8caf4fe906b0dc51/replica-test/SKILL.md Pinned version: install the code at commit 77c9436fb3d18c3d58169efb8caf4fe906b0dc51 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files, including the test-plan, bug-report and e2e example templates) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "replica-test". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. have the clone running locally; install Playwright with npx playwright install chromium if I want automated e2e). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 77c9436 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
The Replica series
By the same creator, in the same series:
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.