replica-brand is the step that makes a clone your own app. It proposes names, lists the trademark, domain, store and handle checks to run for each, builds a palette from a different colour family than the original, and writes a logo brief and a voice guide.
A bundled Python script, sweep.py, then searches your codebase for the original’s name, domain and colours and exits with an error until none are left.
What You Get
- Five name candidates with a check table, where each check is marked to run or carries the date it was run
- A new palette in the same token roles, checked for AA contrast with the design skill’s script
- A logo brief with mark type, size targets, deliverables and a rule against resembling the original
- A voice guide with three words, do and don’t pairs and the ten most-seen strings rewritten
replica/brand.mdandreplica/brand.jsonwith the avoid list, domains and colours
Common Use Cases
- Picking a name and brand for a clone before the landing page is written
- Finding hard-coded original names, domains or colours inside identifiers and file names
- Preparing a brief for a designer or image model to make a logo
What Makes It Unique
Name checks are never written as available unless someone ran them, and the skill says they are screening and not legal clearance. The sweep script matches names inside identifiers such as a class named after the original, matches short hex colours, and blocks the deploy step until clean.
Under The Hood
The skill’s instructions run sweep.py, a standard-library Python script that walks your project folders and reads text files, matching the original’s names, domains and hex colours. It makes no network calls and writes nothing. The agent also runs the design skill’s contrast script and writes the brand markdown and JSON files. The name checks name outside sites such as trademark databases, but the agent only lists them for you to run.