# AI use cases for Replica Skill (Jakeschincariol/replica-skill) Repo: [Jakeschincariol/replica-skill](https://github.com/Jakeschincariol/replica-skill) | Use cases: 4 | Page: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/ A set of eleven free Claude skills and six standard-library Python tools that reverse-engineer, rebuild, test, and rebrand a clone of an existing app's features and flows. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Scope an app clone before you build it: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/scope-clone-before-building/ - Score a rebuilt clone against the original app: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/score-clone-against-original/ - Rank the complaints users have about an app: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/rank-user-complaints-from-reviews/ - Check a rebranded clone before you launch it: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/check-rebrand-before-launch/ ## How to scope an app clone before you build it with Replica Skill Repo: [Jakeschincariol/replica-skill](https://github.com/Jakeschincariol/replica-skill) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Map an app's screens and flows, then check what its users complain about. **Who it is for:** A founder or developer who is thinking about cloning a scheduling or similar app and wants to know the size of the job before committing time. **The problem:** It is hard to tell how big a clone is, and whether it is worth building, without mapping the screens and flows first. **The outcome:** A recon map with screens, flows, components, and an inferred data model, plus a ranked list of user complaints to decide on. ### Steps 1. In Claude Code, run `/plugin marketplace add Jakeschincariol/replica-skill` 2. Run `/plugin install replica-skill@replica-skill` 3. Run `/replica-recon` with the target app's URL 4. Run `/replica-entrepreneur` on the same app 5. Read `replica/recon.md` and the complaint summary before deciding whether to build ### Prompt to paste into your agent ```text Using the replica-skill repo (github.com/Jakeschincariol/replica-skill), run the replica-recon and replica-entrepreneur skills on . Expected output: replica/recon.md listing screens, flows, components, and out-of-scope items, plus a complaint summary. Verify that every complaint in the summary links to a source. ``` ### Caveat The skill rebuilds features and flows clean-room style and does not copy the target's code, logos, copy, or content. Risk, reverse engineering: Recon is meant to use only public pages, store listings, and your own account, so check the target's terms before you rely on the output. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/scope-clone-before-building/ ## How to score a rebuilt clone against the original app with Replica Skill Repo: [Jakeschincariol/replica-skill](https://github.com/Jakeschincariol/replica-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Get a layout diff and a parity score for your clone. **Who it is for:** A developer who has rebuilt screens from a recon map and needs to see what is still missing before a release. **The problem:** Judging a clone by eye hides missing must-have features and layout gaps. **The outcome:** A pixel-region layout diff and a parity score with a list of missing features. ### Steps 1. Save a screenshot of the original screen as `original.png` and your clone as `clone.png` 2. Run `python3 replica-diff/imgdiff.py original.png clone.png --out diff.png` 3. Make sure your feature matrix is at `replica/features.csv` 4. Run `python3 replica-diff/parity.py replica/features.csv` 5. Fix any missing must-haves, since the tool marks them as not shippable ### Prompt to paste into your agent ```text Using the replica-skill repo (github.com/Jakeschincariol/replica-skill), compare with using imgdiff.py and score with parity.py. Expected output: diff.png and a parity score with a missing list. Verify that the missing list includes every must-have that is not done. ``` ### Caveat The scores only reflect the features you list in features.csv and the screenshots you provide. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/score-clone-against-original/ ## How to rank the complaints users have about an app with Replica Skill Repo: [Jakeschincariol/replica-skill](https://github.com/Jakeschincariol/replica-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Turn a CSV of linked reviews into ranked, sourced complaint themes. **Who it is for:** A product person or founder looking for a positioning angle in an existing app's weak spots. **The problem:** Reading hundreds of reviews by hand is slow, and quotes without sources are easy to misquote. **The outcome:** Ranked complaint themes with quotes, each tied to the URL of its source row. ### Steps 1. Collect the reviews into `replica/reviews.csv` with a link on every row 2. Run `python3 replica-entrepreneur/reviews.py replica/reviews.csv` 3. Check the sample size and the themes marked thin 4. Use the top themes to pick fixes and a positioning angle ### Prompt to paste into your agent ```text Using the replica-skill repo (github.com/Jakeschincariol/replica-skill), run reviews.py on . Expected output: ranked complaint themes with linked quotes. Verify that every quote printed matches a row in the input file and carries that row's URL. ``` ### Caveat The tool only ranks reviews you supply, and the README says it drops any review without a link. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/rank-user-complaints-from-reviews/ ## How to check a rebranded clone before you launch it with Replica Skill Repo: [Jakeschincariol/replica-skill](https://github.com/Jakeschincariol/replica-skill) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Sweep the code for leftover original names and lint the store listing. **Who it is for:** A developer who has rebranded a clone and needs to confirm nothing of the original remains before publishing. **The problem:** Original names, domains, or colours can hide in code identifiers and listing text. **The outcome:** A sweep report of any leftover original references and a listing check against store limits. ### Steps 1. Run `python3 replica-brand/sweep.py . --avoid "Original App"` from your project root 2. Remove or rename every hit it reports 3. Write your store listing to `replica/launch/listing.json` 4. Run `python3 replica-launch/listing.py replica/launch/listing.json` 5. Fix any store limit or copycat warnings before you deploy ### Prompt to paste into your agent ```text Using the replica-skill repo (github.com/Jakeschincariol/replica-skill), run sweep.py on avoiding and listing.py on . Expected output: a sweep report and a listing report. Verify that the sweep finds no original name, domain, or colour, including inside identifiers. ``` ### Caveat The README says these checks do not replace the trademark checks, and it is not legal advice, so you still need to check trademarks and talk to a lawyer before launch. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-replica-skill/check-rebrand-before-launch/