Replica Pack, clone any app — reverse-engineer it, rebuild it, test it for bugs, then fix what its users hate

Prerequisites: Python 3; Node/npm + Playwright (+ @axe-core/playwright for e2e tests); user-created accounts and own keys in .env.local for backend (Stripe/Supabase/Resend/Google Cloud, test mode first); domain/host/DNS/Stripe-live/OAuth/store accounts for deploy; Xcode/Gradle/EAS for mobile builds. Install "Replica Pack, clone any app" for me. It gives my agent @Jakeschincariol's full Replica workflow, all eleven skills in order: replica-recon, replica-architect, replica-design, replica-build, replica-backend, replica-test, replica-diff, replica-entrepreneur, replica-brand, replica-launch and replica-deploy. Reverse-engineer an app into a recon map, plan the stack and schema, rebuild the design system and the app screen by screen, wire up the backend, test every flow, score parity, fix what the original's users hate, rebrand it, launch it and ship it live — clean-room style, features and flows only, never the original's code, assets, copy or private APIs. Repository: https://raw.githubusercontent.com/Jakeschincariol/replica-skill/77c9436fb3d18c3d58169efb8caf4fe906b0dc51/ Pinned version: install the code at commit 77c9436fb3d18c3d58169efb8caf4fe906b0dc51 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch each SKILL.md file (and the helper files listed below) from the repository path into a temporary folder: - replica-recon/SKILL.md, recon-map.md, features.csv - replica-architect/SKILL.md, architecture.md - replica-design/SKILL.md, tokens.json, contrast.py - replica-build/SKILL.md - replica-backend/SKILL.md - replica-test/SKILL.md, test-plan.md, bug-report.md, e2e.example.spec.ts - replica-diff/SKILL.md, imgdiff.py, parity.py - replica-entrepreneur/SKILL.md, reviews.py, themes.json - replica-brand/SKILL.md, sweep.py - replica-launch/SKILL.md, listing.py, listing.example.json - replica-deploy/SKILL.md, preflight.md 2. Safety check: review the SKILL.md files and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code: you create your own accounts and keys and put keys in .env.local, the agent writes .env.example with names only and never types a password, card or live key. Verify that holds here; STOP on any red flag and tell me. 3. Install them as skills: copy each SKILL.md and its helper files into the agent's skills directory, in folders named replica-recon, replica-architect, replica-design, replica-build, replica-backend, replica-test, replica-diff, replica-entrepreneur, replica-brand, replica-launch and replica-deploy. 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. pick the app and the slice to map; have a clone running locally for the test step; 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 is in the prerequisites above. Rules: don't touch anything outside the temp folder and the install targets. In Muse, invoke pack neighbour skills by name, not as /slash commands. If anything looks off, stop and ask me. After installation, ask me if I want to leave private feedback. Private for now: only the Skill Harbor team sees it. Sellers may be looped in later.