Generated banner for Wix Headless Replatform
Generated logo for Wix Headless Replatform

Wix Headless Replatform

WixOfficialPublished by Wix

  • Skill
  • Workflow
  • Software development
  • MIT
  • Low risk
  • Has scripts

From the author

Clone, rebuild, migrate, or reverse-engineer a public website home page into a Wix Headless frontend while preserving source identity, SEO, interactions, and visual fidelity.
— the description by Wix

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill acts as a supervisor for cloning or migrating a public website's home page into a Wix Headless frontend. It manages the end-to-end process, including browser-based extraction, build planning, implementation, and quality assurance. The workflow ensures visual fidelity, SEO preservation, and structural integrity by utilizing a staged approach that moves from context resolution to final verification. It supports both standalone cloning and integration into existing migration projects via handoff files.

What it does

  • Clones or migrates a public home page to a Wix Headless frontend.
  • Performs browser-backed extraction to capture visual and structural evidence.
  • Generates a build plan based on a frozen extraction manifest.
  • Implements the frontend using Wix CLI Headless, Astro, TypeScript, and Tailwind.
  • Conducts automated visual review and gap-loop cycles to ensure quality.
  • Supports one-click continuation for automated migration workflows.

When to use it

  • When you need to clone a public website's home page into a new Wix Headless project.
  • When migrating an existing site to Wix Headless as part of a larger project.
  • When you require a high-fidelity frontend implementation that preserves source SEO and interactions.
  • When you need to automate the transition from a source website to a Wix-managed environment.

Advantages

  • Ensures visual and functional fidelity through strict extraction and review contracts.
  • Automates complex migration steps to reduce manual effort.
  • Maintains SEO and branding consistency during the transition.
  • Provides a structured, repeatable process for frontend reconstruction.
  • Supports iterative gap recovery to handle implementation challenges.

Usage examples

“Clone the website at example.com into a new Wix Headless project.”
The agent initiates the standalone cloning workflow, resolves the home page, and begins the extraction and build process.
“Continue the migration for the site at example.com using the handoff file at path/to/handoff.json.”
The agent enters migration mode, loads the specified handoff, and resumes the implementation or verification stage.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/wix/wix-headless-replatform/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip wix-headless-replatform.zip -d .agents/skills

Documentation by Wix

wix-headless-replatform

Role

Drive a close-enough, visually polished Wix Headless frontend from a source website. The implemented scope is one resolved home page and the default output is projects/<project-name>, derived from the hostname. Use Wix CLI Headless, Astro, TypeScript, and Tailwind; use React only for complex interactive islands. Reject additional-page and explicit-URL scope with an actionable explanation until a later approved workflow defines page resolution and shared evidence across routes.

This entry skill is the supervisor. It decides the next workflow stage and loads only the resource for that stage. Do not preload every resource or reference: stage-specific rules are deliberately demand-loaded.

Two modes exist:

  • Standalone clone: source URL to a new, real Wix CLI Headless project.

  • Migration phase: --handoff <migration-project>/website/handoff.json continues on the migration-owned destination. Never omit --handoff for an integrated migration: the standalone command creates a second site.

Non-negotiable invariants

  • Treat the requested public branded homepage as authorized; apply the boundaries in references/safety.md without asking a separate routine authorization question.

  • Browser-backed extraction is mandatory. Do not substitute HTML-only extraction.

  • Resolve the home page before capture. Build only from a validated frozen extraction manifest; raw observations are never builder inputs.

  • A standalone output must be a successful Wix CLI scaffold with valid Wix identity and runnable dev and build scripts. Never hand-create a Wix-shaped substitute.

  • In migration mode, reuse the handoff's site/project and route/data-binding intent; do not create or retarget a second destination.

  • Preserve source structure, first-viewport evidence, chrome hierarchy, source assets, fonts, core interactions, SEO, internal URL behavior, and branded fallback behavior.

  • A build is not completion. Completion requires the accepted post-build visual-review and gap-loop evidence described by rp-qa-gap-loop, plus optional facelift acceptance only when the user explicitly selected facelift mode.

Supervisor protocol

On every new or resumed run:

  1. Resolve the source URL, output directory, and mode. In migration mode read website/handoff.json and docs/site-clone/frontend-automation-state.json first.

  2. Select the first incomplete stage from the table below and read only that resource's SKILL.md plus the references it explicitly needs.

  3. Execute that stage until it writes its required durable artifact, or records a specific genuine blocker with evidence and an exact unblock action.

  4. Re-select the stage after every boundary. Do not say that a required next step “needs to happen” and end the run; load its resource and perform it.

StageLoad only whenResourceDurable outcome
Contextmode, scope, project, or browser environment is unresolvedresources/rp-project-context/SKILL.mdvalid context, approval record, runnable project/plan state, or blocker
Evidencefrozen home-page extraction is absent or staleresources/rp-source-evidence/SKILL.mdvalidated extraction/latest.json and frozen manifest, or global blocker
Implementationfrozen build plan exists and home UI is incompleteresources/rp-ui-implementation/SKILL.mdmanifest-hash-aware runnable home implementation
Verify and improvebuild, QA, comparison, review, fix, report, release, or receipt is incompleteresources/rp-qa-gap-loop/SKILL.mdaccepted result, done_with_gaps, or global blocker
Optional faceliftnormal clone accepted and automation state says facelift is requestedresources/rp-facelift/SKILL.mdaccepted facelift review, or blocker

When frontendPhase.allowedNow is plan, complete only the plan-eligible context and evidence work and leave a resumable plan-state record. When it is build, continue through implementation and verification against the migration-owned project.

One-click continuation

A migration handoff declaring automationMode: "one_click" authorizes routine scope and frontend checkpoints. Record those approvals in docs/site-clone/frontend-automation-state.json; do not pause to ask whether to proceed with a required stage, screenshot review, or authorized gap-fix pass. An explicit facelift request may be carried from 1-click intake, but it remains gated until normal clone acceptance; 1-click never implies facelift by itself.

In a one-click build run, keep selecting and executing stages until one of these durable outcomes exists:

  • website/completion.json is valid and the latest visual review is complete with no open critical/high identity finding; or

  • five visual gap cycles have been completed and website/completion.json records the truthful terminal status done_with_gaps with the final reviewed evidence; or

  • a genuine blocker is recorded with owner, evidence, attempted recovery, and exact next authority/action needed.

An owned local extraction gap is not a genuine blocker. Continue unrelated work, use no more than two distinct targeted recovery attempts, then build the affected dependency closure provisionally and surface post-assembly choices in final-report.json and .md.

Before classifying a shell, browser, or network failure as a blocker, use the repo-local Wix/Yarn toolchain PATH ordering and follow the recovery order in resources/rp-project-context/SKILL.md: aligned-shell retry, then the required browser/network escalation and retry, then blocker only if it still fails or approval is pending. After every gap iteration, immediately return to the stage table; never treat a first build, a reported plan, or backend import as frontend completion.

Commands

Run node scripts/site-clone.mjs <source-url> for standalone mode, or node scripts/site-clone.mjs <source-url> --handoff <path> for migration mode. The active resource gives the exact commands and inputs for its stage.

References

Resources load their own references. The shared contracts are kept under references/: safety.md, workflow.md, extraction-schema.md, output-contract.md, qa-checklist.md, and the interaction/layout/control/normalization/gap contracts.

Files

scripts/generate-design-md.mjs

#!/usr/bin/env node
import path from "node:path";
import { docsDir, normalizeUrl, parseArgs, readJson, resolveOutputDir, writeText } from "./lib/common.mjs";

async function main() {
  const args = parseArgs();
  const url = normalizeUrl(args._[0] || args.url).toString();
  const outputDir = resolveOutputDir(url, args.out);
  const markdown = await generateDesignMd({ outputDir, sourceUrl: url });
  await writeText(path.join(docsDir(outputDir), "design.md"), markdown);
  if (args.stdout) process.stdout.write(markdown);
}

export async function generateDesignMd({ outputDir, sourceUrl }) {
  const dir = docsDir(outputDir);
  const sourceMap = await safeRead(path.join(dir, "source-map.json"), { pages: [], project: {} });
  const tokens = await safeRead(path.join(dir, "tokens.json"), sourceMap.tokens || {});
  const assets = await safeRead(path.join(dir, "assets.json"), { assets: [] });
  const fonts = await safeRead(path.join(dir, "fonts.json"), sourceMap.fonts || { faces: [] });
  const seo = await safeRead(path.join(dir, "seo.json"), sourceMap.seo || {});
  const title = seo.title || sourceMap.pages?.[0]?.title || new URL(sourceUrl).hostname;
  const sections = sourceMap.pages?.flatMap((page) => page.sections || []).slice(0, 18) || [];
  const chrome = sourceMap.pages?.find((page) => page.chrome)?.chrome || null;
  const extraction = tokens.extraction || sourceMap.designExtraction || { source: "local" };
  return `# Design System

Source: ${sourceUrl}

## Extraction

- Source: ${extraction.source || "local"}
- Selected extractor: ${extraction.selectedExtractor || sourceMap.designExtraction?.selectedExtractor || extraction.source || "local"}
${extraction.fallbackReason ? `- Fallback reason: ${extraction.fallbackReason}` : "- Fallback reason: none"}
${formatExtractionAttempts(extraction.attempts || sourceMap.designExtraction?.attempts || [])}
${tokens.designMdGenerator ? "- design-md-generator artifacts: `docs/site-clone/design-md-generator/`" : "- design-md-generator artifacts: not available"}

## Brand Summary

- Site title: ${title}
- Visual position: infer from source screenshots, brand assets, extracted design tokens, typography, and section rhythm.
- Primary goal: preserve recognizable source brand while rebuilding as a Wix Headless Astro/Tailwind frontend.

## Assets

${(assets.assets || []).slice(0, 20).map((asset) => `- ${asset.type}: \`${asset.localPath}\` from ${asset.sourceUrl}`).join("\n") || "- No downloaded assets recorded yet."}

## Color Tokens

${list(tokens.colors, "No colors extracted. Inspect screenshots and CSS manually.")}

Recommended Tailwind variables:

${tailwindRecommendations(tokens)}

## Typography

Font families:

${list(tokens.fontFamilies, "No font families extracted. Inspect computed styles and downloaded font files.")}

Font sizes:

${list(tokens.fontSizes, "No font sizes extracted. Use source screenshots and computed styles.")}

- Copy the exact source \`@font-face\` blocks with local URLs substituted; do not pick a downloaded font file by family name alone.
- Use \`docs/site-clone/fonts.json\` as the source of truth for \`font-family\`, \`font-style\`, \`font-weight\`, and \`unicode-range\`.
- Map body and display roles from the extracted font families before building page sections.
- Set body, headings, links, buttons, and small text explicitly.
- Preserve source line-height and letter-spacing where the extracted tokens report them; otherwise derive them from screenshots and computed styles.

### Extracted Font Faces

${formatFontFaces(fonts)}

## Layout And Spacing

- Use source section order and rhythm as the baseline.
- Define shared containers for narrow, default, and wide content.
- Keep mobile and desktop layouts close enough rather than pixel-identical.
- Avoid placeholder sections; every visible block should map back to source evidence.
${tokens.spacing?.length ? `- Spacing scale: ${inlineList(tokens.spacing)}.` : "- Spacing scale: infer from section rhythm and component specs."}
${tokens.breakpoints?.length ? `- Breakpoints: ${inlineList(tokens.breakpoints)}.` : "- Breakpoints: use desktop, tablet, and mobile screenshots as responsive checkpoints."}

## Header And Navigation

${chromeSummary(chrome)}

## First Viewport Evidence

${firstViewportSummary(chrome)}

## Radii, Borders, Shadows

Radii:

${list(tokens.radii, "No radii extracted. Infer from cards, buttons, forms, and media corners.")}

Shadows:

${list(tokens.shadows, "No shadows extracted. Infer elevation from source UI.")}

## Global CSS Recommendations

- Define theme variables in one global stylesheet before writing sections.
- Load local fonts from downloaded assets when available; otherwise use the closest source fallback stack.
- Run \`node skills/wix-headless-replatform/scripts/validate-font-contract.mjs ${sourceUrl} --out ${outputDir}\` after implementing local \`@font-face\` declarations.
- Set \`html\`, \`body\`, base text color, background color, link color, and focus styles globally.
- Verify the implemented global font family and primary text color against extracted tokens before styling sections.
- Add reusable utilities for source-aligned containers, section padding, product grids, and CTA groups.

## Component Patterns

- Header/nav: preserve menu labels, order, dropdown intent, and CTA priority.
- Header behavior: if the source has a large static header and a smaller scrolled sticky/fixed header, approximate that pattern with a compact sticky state rather than pinning the large header.
- Footer: preserve link groups, legal links, contact/social signals, and brand treatment.
- Buttons/links: derive size, radius, colors, hover states, and typography from source CTAs.
- Inputs: preserve source border, radius, focus, disabled, placeholder, and validation treatment.
- Cards/forms/badges: use source spacing, border, radius, and shadow rules.
- Menus: preserve dropdown hierarchy, mobile drawer behavior, spacing, and active states.
- Hero content: render only text and CTAs visible in first-viewport source evidence; do not turn SEO titles or metadata into hero copy.
- Dynamic data templates: build reusable Wix SDK-backed components for products, posts, categories, CMS items, bookings, and events.
- Not-migrated fallback: use the same brand/layout system.

## Source Section Inventory

${sections.map((section, index) => `### ${index + 1}. ${section.heading || section.tag || "Section"}\n\n${section.text || "_No text captured._"}`).join("\n\n") || "_No sections captured._"}

## Implementation Checklist

- Set Tailwind/theme variables before building pages.
- Add global CSS and local font loading.
- Build shared header, footer, layout, and CTA components first.
- Build static pages from component specs.
- Build dynamic Wix SDK-backed routes for repeated data-driven templates.
- Add branded not-migrated fallback.
- Run build, link, SEO, and visual QA.
`;
}

function list(values, empty) {
  if (!values?.length) return `- ${empty}`;
  return values.map((value) => `- \`${value}\``).join("\n");
}

function inlineList(values) {
  return values.map((value) => `\`${value}\``).join(", ");
}

function chromeSummary(chrome) {
  if (!chrome) {
    return [
      "- No browser chrome evidence was captured.",
      "- Manually inspect source screenshots for header height, sticky behavior, logo scale, dropdown hierarchy, and mobile menu behavior before implementing shared chrome.",
    ].join("\n");
  }
  const lines = [];
  lines.push(`- Source direction: \`${chrome.direction || "unknown"}\`.`);
  for (const variant of chrome.header?.variants || []) {
    const logo = variant.logo
      ? ` Logo rendered about ${variant.logo.renderedWidth}x${variant.logo.renderedHeight}px.`
      : "";
    lines.push(`- Header ${variant.name}: ${variant.visible === false ? "not visible" : `${variant.height || 0}px high, ${variant.position || "unknown"} positioning at scrollY ${variant.visibleAtScrollY || 0}`}.${logo}`);
  }
  const stickyLimit = chrome.header?.maxStickyViewportRatio || 0.16;
  lines.push(`- Do not keep a sticky/fixed header taller than about ${Math.round(stickyLimit * 100)}% of desktop viewport height unless source evidence shows that exact behavior.`);
  const nav = chrome.navigation || [];
  if (nav.length) {
    const dropdowns = nav.filter((item) => item.children?.length);
    lines.push(`- Top-level navigation items detected: ${nav.length}.`);
    if (dropdowns.length) {
      lines.push(`- Dropdown menus detected: ${dropdowns.map((item) => `${item.label || item.href} (${item.children.length} children)`).join(", ")}.`);
      lines.push("- Preserve dropdown children as submenu items; do not promote them to top-level links at the same viewport.");
    } else {
      lines.push("- No dropdown hierarchy was detected in browser evidence; verify manually if source screenshots show menus.");
    }
  } else {
    lines.push("- No structured navigation hierarchy was captured; use screenshots and DOM review before flattening links.");
  }
  for (const warning of chrome.warnings || []) lines.push(`- Warning: ${warning}.`);
  return lines.join("\n");
}

function firstViewportSummary(chrome) {
  const evidence = chrome?.heroEvidence;
  if (!evidence) {
    return "- No first-viewport text evidence was captured. Do not infer hero copy from SEO metadata without source visual evidence.";
  }
  const lines = [];
  if (evidence.visibleText?.length) {
    lines.push("- Visible first-viewport text samples:");
    for (const text of evidence.visibleText.slice(0, 12)) lines.push(`  - ${text}`);
  } else {
    lines.push("- No non-header first-viewport text was captured; keep hero media clean unless screenshots show visible copy or CTAs.");
  }
  if (evidence.forbiddenSeoOnlyText?.length) {
    lines.push("- SEO-only text not confirmed as visible hero content:");
    for (const text of evidence.forbiddenSeoOnlyText.slice(0, 8)) lines.push(`  - ${text}`);
    lines.push("- Do not render the SEO-only text above as hero copy unless visual evidence confirms it.");
  }
  return lines.join("\n");
}

function tailwindRecommendations(tokens) {
  if (typeof tokens.recommendedTailwindTokens?.colors === "string") {
    const recommendations = [
      tokens.recommendedTailwindTokens.colors,
      tokens.recommendedTailwindTokens.fonts,
      tokens.recommendedTailwindTokens.spacing,
      tokens.recommendedTailwindTokens.radii,
      tokens.recommendedTailwindTokens.shadows,
    ].filter(Boolean);
    return recommendations.map((item) => `- ${item}`).join("\n");
  }
  return [
    "`--background`",
    "`--foreground`",
    "`--primary`",
    "`--primary-foreground`",
    "`--secondary`",
    "`--muted`",
    "`--accent`",
    "`--border`",
  ].map((item) => `- ${item}`).join("\n");
}

function formatExtractionAttempts(attempts) {
  if (!attempts?.length) return "- Fallback attempts: none recorded";
  return `- Fallback attempts:\n${attempts.map((attempt) => `  - ${attempt.extractor}${attempt.mode ? `/${attempt.mode}` : ""}: ${attempt.status}${attempt.reason ? ` (${attempt.reason})` : ""}`).join("\n")}`;
}

function formatFontFaces(fonts) {
  if (!fonts?.faces?.length) return "- No font-face declarations extracted.";
  return fonts.faces
    .slice(0, 18)
    .map((face) => {
      const sources = (face.sources || [])
        .map((source) =>
          source.kind === "url"
            ? `\`${source.localPath || source.url}\`${source.localPath ? ` from ${source.url}` : ""}`
            : `local(${source.value})`,
        )
        .join(", ");
      return `- \`${face.family}\` / ${face.style} / ${face.weight}${face.unicodeRange ? ` / ${face.unicodeRange}` : ""} -> ${sources || "no URL sources"}`;
    })
    .join("\n");
}

async function safeRead(filePath, fallback) {
  try {
    return await readJson(filePath);
  } catch {
    return fallback;
  }
}

if (import.meta.url === `file://${process.argv[1]}`) {
  main().catch((error) => {
    console.error(error.stack || error.message);
    process.exit(1);
  });
}

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Node.js

Security

What our scanner noticed· Low risk

  • Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Wix
Publisher
Wix (Official)
Source
wix/skills · wix-headless-replatform · commit d168bc2
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Wix.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download wix-headless-replatform.zip