agentleFS
Sign inStart free
MahanaicoachMahanaicoach/ai-site-cloner/.github/skills/restyle/SKILL.md

restyle

Skill31 starsChanged 3 months agoMITView on GitHub

Rebrand a cloned website with your own identity — swaps colors, fonts, logo, favicons, and rewrites all copy for your brand while keeping the cloned layout, spacing, animations, and interactions pixel-intact. Run after /clone-website. Reads BRAND.md at the repo root. Use when the user wants to "make it mine", rebrand, restyle, or customize the clone.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read BRAND.md at the repo root.

    line 16
  2. Very specific:

    If the user has brand assets (logo files, product screenshots), ask them to drop the files into public/brand/ and tell you the filenames.

    line 18
  3. Very specific:

    Check every page route, not just /.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Restyle

Turn the cloned site into the user's site: their brand, their words, their logo — on top of the cloned structure. Layout, spacing, animations, and interactions stay untouched. That separation works because the clone pipeline keeps all content in src/data/*.ts and all brand tokens in globals.css — you swap those layers only.

$ARGUMENTS

Step 1 — Read the brand

Read BRAND.md at the repo root. If it's missing or has unfilled TODO fields, ask the user for what's missing (max 3 questions at a time). Never ask for secrets in chat — anything sensitive belongs in env files, not BRAND.md.

If the user has brand assets (logo files, product screenshots), ask them to drop the files into public/brand/ and tell you the filenames.

Step 2 — Take "before" screenshots

npm run dev   # background
node scripts/extract/screenshot.mjs http://localhost:3000 --name before-restyle

These are your regression reference: after restyling, layout must still match them structurally.

Step 3 — Swap the brand layers (in this order)

  1. Colors — src/app/globals.css: replace the cloned palette in :root / .dark with the brand colors from BRAND.md. Keep the same token names so no component changes. Preserve relative contrast: if the original had a dark section, keep it dark in the new palette.
  2. Fonts — src/app/layout.tsx: swap next/font families to the brand fonts. Keep the size/weight structure the clone extracted — only families change.
  3. Logo & icons — replace LogoIcon in src/components/icons.tsx (or the logo <img> asset) with the brand logo from public/brand/. Keep the rendered dimensions of the original logo so the header layout doesn't shift.
  4. Favicons & SEO — regenerate public/seo/ (favicon, apple-touch-icon, OG image if provided), update layout.tsx metadata: title, description, OG tags — from BRAND.md positioning.
  5. Copy — rewrite every string in src/data/*.ts for the brand: same structure, same approximate length (±20% — long copy breaks cloned layouts), brand voice from BRAND.md. Headlines sell the user's offer, not the original company's. Placeholder patterns like testimonials get realistic brand-appropriate content clearly marked as placeholders unless BRAND.md provides real ones.
  6. Images — where the clone shows the original company's product shots, swap in files from public/brand/ if provided; otherwise leave the cloned image and list it in the report as "needs replacement".

Step 4 — Verify

  1. npm run build — must pass
  2. node scripts/extract/screenshot.mjs http://localhost:3000 --name after-restyle
  3. Compare before/after at all 3 viewports: layout identical, only brand layers changed. Overflowing text = shorten the copy, never change the layout.
  4. Check every page route, not just /.

Report

  • What was swapped (colors, fonts, logo, favicon, N copy blocks across M data files)
  • Images still showing the original site's content (need user-provided replacements)
  • Any copy that had to be shortened/lengthened to fit
  • Anything in BRAND.md still marked TODO

Download now (ZIP)

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. fair-acc/gnuradio4★ 116same name
    2. amondnet/yoonmoon★ 17same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free