Skip to content
SkillMixed975 tokens in use

replica-brand

Names and rebrands an app clone: candidate names with checks to run, a new palette, a logo brief, a voice guide and a sweep for leftovers.

10,140 stars on the repository MIT LicenseJakeschincariol/replica-skill · replica-brand
/plugin install replica-skill@replica-skill
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing replica-brand costs

123tokens idle
975tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: sweep.py.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure17/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 21

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity32
  • Maintenance4
  • Community64
  • Maturity12
  • Momentum40

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.md and replica/brand.json with 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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers