使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/jakeschincariol/replica-skill --skill replica-brand开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
replica-brand
Nothing launches under the original's identity. This skill is the line between "a clone" and "your app".
Tool in this folder:
python3 sweep.py . --avoid "Original Name,Its Company" --domains original.com --colors "#006bff"
python3 sweep.py . --config replica/brand.json # same, from the brand fileWrites replica/brand.md and replica/brand.json (avoid, domains, colors, used by sweep.py, listing.py and replica-deploy).
Step 1: the name
Read the angle from replica/fixes.md. Generate 20 candidates across styles: descriptive (Booklink), compound (Slotwise), invented (Calvo), metaphor (Harbor), verb (Book). Then cut to 5 with these filters:
- Not confusingly similar to the original in sound, look or meaning, and
not to any other app in the same category. That is the test trademark offices use, so it is the test here. No puns on their name, no "-ly" twin.
- Short, spellable after hearing it once, no awkward meaning in big languages.
- Says something about the angle, or at least does not fight it.
Step 2: the checks, run, not assumed
For each of the 5, a row per check. Mark each to run, or the result with the date it was run. Never write "available" for a check nobody ran.
| check | where |
|---|---|
| US trademark | tmsearch.uspto.gov, the app's class (usually 9 and 42) |
| EU trademark | euipo.europa.eu eSearch, or TMview for many offices |
| Canada | ised-isde.canada.ca trademarks database |
| global | WIPO Global Brand Database |
| domain | whois name.com, or the registrar's search |
| App Store and Play | search the exact name |
| handles | X, Instagram, TikTok, GitHub |
| the web | search "name + category" |
These are screening checks, not legal clearance. Before spending money on the name, a trademark lawyer should do a proper search.
Step 3: palette
A new palette, written into the same token roles replica-design set up. Pick a primary brand hue from a different family than the original's (if theirs is blue, yours is not a nearby blue). Then:
python3 ../replica-design/contrast.py replica/design/tokens.jsonZero AA failures. Add the original's brand colours to brand.json so the sweep catches any that survive.
Step 4: logo brief
Not a logo, a brief for whoever makes it (the user, a designer, an image model):
- the idea in one line, tied to the name and angle
- mark type: wordmark, symbol plus wordmark, or monogram
- must work at 16px (favicon) and as a 1024px app icon
- deliverables: SVG, app icon 1024x1024 with no transparency for iOS,
favicon set, social image 1200x630
- must not resemble the original's mark: no shared shape, colour pair or
letterform trick. Put the original's logo next to the drafts and check.
Step 5: voice
Three words for how it sounds, with what each does not mean ("direct, not blunt"). Five do and don't pairs. Then rewrite the 10 most-seen strings in the clone (sign up, empty states, the main button, the confirmation, the error) in that voice. All fresh, none echoing the original's phrasing.
Step 6: the sweep
Replace every placeholder name, colour and string. Then:
python3 sweep.py . --config replica/brand.jsonIt searches file contents and file names for the original's name (also inside identifiers like CalendlyEmbed), domains and colours, skipping node_modules, build output and the replica/ planning folder. Exit 1 means something is left. Fix until it says clean. Also check by eye: the favicon, the page titles, the email templates, the OG image, the app icon.
Output
replica/brand.md (name with checks, palette, logo brief, voice), replica/brand.json, updated tokens, rewritten strings, and a clean sweep. Next: /replica-launch.
