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

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/wix/wix-headless-replatform/download

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:

Resolve the source URL, output directory, and mode. In migration mode read website/handoff.json and docs/site-clone/frontend-automation-state.json first.
Select the first incomplete stage from the table below and read only that resource's SKILL.md plus the references it explicitly needs.
Execute that stage until it writes its required durable artifact, or records a specific genuine blocker with evidence and an exact unblock action.
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.

Stage	Load only when	Resource	Durable outcome
Context	mode, scope, project, or browser environment is unresolved	`resources/rp-project-context/SKILL.md`	valid context, approval record, runnable project/plan state, or blocker
Evidence	frozen home-page extraction is absent or stale	`resources/rp-source-evidence/SKILL.md`	validated `extraction/latest.json` and frozen manifest, or global blocker
Implementation	frozen build plan exists and home UI is incomplete	`resources/rp-ui-implementation/SKILL.md`	manifest-hash-aware runnable home implementation
Verify and improve	build, QA, comparison, review, fix, report, release, or receipt is incomplete	`resources/rp-qa-gap-loop/SKILL.md`	accepted result, `done_with_gaps`, or global blocker
Optional facelift	normal clone accepted and automation state says facelift is requested	`resources/rp-facelift/SKILL.md`	accepted 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

.publish-manifest.json227 B
ATTRIBUTION.mdAdded by AutoGineer826 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md6.4 KiB
agents/openai.yaml259 B
references/control-and-visual-fidelity-contract.md2.1 KiB
references/extraction-schema.md8.6 KiB
references/interaction-runtime-contract.md5.3 KiB
references/layout-blueprint-contract.md2.1 KiB
references/output-contract.md4.0 KiB
references/post-build-gap-contract.md5.5 KiB
references/qa-checklist.md4.7 KiB
references/safety.md1.0 KiB
references/ui-normalization-contract.md2.8 KiB
references/workflow.md7.7 KiB
registry/README.md958 B
registry/approvals/button/shadcn-default-ac60ef5.json980 B
registry/items/button/shadcn-default-ac60ef5/button.tsxScript1.9 KiB
registry/items/button/shadcn-default-ac60ef5/capabilities.json2.7 KiB
registry/items/button/shadcn-default-ac60ef5/contract.md2.1 KiB
registry/licenses/shadcn-ui-ac60ef5-MIT.txt1.0 KiB
registry/registry.json1.4 KiB
schemas/build-plan.schema.json628 B
schemas/candidate.schema.json949 B
schemas/common.schema.json1.2 KiB
schemas/decision-patch.schema.json621 B
schemas/decision-request.schema.json825 B
schemas/extraction-gap.schema.json1.6 KiB
schemas/extraction-manifest.schema.json1.6 KiB
schemas/final-report.schema.json744 B
schemas/foundation.schema.json950 B
schemas/metadata.schema.json801 B
schemas/observation-packet.schema.json661 B
schemas/page-capture.schema.json1015 B
schemas/page-resolution.schema.json1.4 KiB
schemas/shared-chrome.schema.json940 B
schemas/unit.schema.json1.8 KiB
scripts/assemble-extraction.mjsScript36.1 KiB
scripts/benchmark-extraction.mjsScript9.1 KiB
scripts/browser-extraction-preflight.mjsScript1.2 KiB
scripts/build-extracted-homepage.mjsScript15.4 KiB
scripts/clear-wix-starter.mjsScript2.3 KiB
scripts/create-wix-project.mjsScript17.2 KiB
scripts/discover-urls.mjsScript4.4 KiB
scripts/extract-assets.mjsScript4.6 KiB
scripts/extract-design-system.mjsScript23.0 KiB
scripts/extract-interactions.mjsScript83.1 KiB
scripts/extract-page.mjsScript117.7 KiB
scripts/extract-seo.mjsScript848 B
scripts/extract-tokens.mjsScript2.6 KiB
scripts/finalize-extraction-report.mjsScript6.4 KiB
scripts/finalize-gap-review.mjsScript12.2 KiB
scripts/finalize-gap-review.test.mjsScript5.3 KiB
scripts/finalize-migration-website.mjsScript6.2 KiB
scripts/generate-control-state-contract.mjsScript9.1 KiB
scripts/generate-design-md.mjsScript11.7 KiB
scripts/generate-extraction-validators.mjsScript5.4 KiB
scripts/generate-layout-blueprint.mjsScript8.7 KiB
scripts/generate-repeater-cms.mjsScript4.9 KiB
scripts/generate-route-plan.mjsScript4.6 KiB
scripts/generate-scene-contract.mjsScript16.2 KiB
scripts/generate-ui-normalization.mjsScript13.3 KiB
scripts/generate-visual-assets.mjsScript6.3 KiB
scripts/lib/browser-tooling.mjsScript19.5 KiB
scripts/lib/common.mjsScript9.0 KiB
scripts/lib/component-capabilities.mjsScript7.9 KiB
scripts/lib/component-registry.mjsScript12.3 KiB
scripts/lib/content-boundary.mjsScript2.8 KiB
scripts/lib/extraction-contract.mjsScript18.8 KiB
scripts/lib/extraction-detectors.mjsScript11.4 KiB
scripts/lib/extraction-validators.generated.mjsScript25.2 KiB
scripts/lib/font-contract.mjsScript10.0 KiB
scripts/lib/frontend-automation-state.mjsScript6.6 KiB
scripts/lib/gap-analysis.mjsScript26.1 KiB
scripts/lib/html-extract.mjsScript5.7 KiB
scripts/lib/interaction-bootstrap.mjsScript296 B
scripts/lib/interaction-runtime.mjsScript8.1 KiB
scripts/lib/interaction-timeline.mjsScript13.9 KiB
scripts/lib/layout-blueprint/classifiers.mjsScript7.8 KiB
scripts/lib/layout-blueprint/geometry.mjsScript1.8 KiB
scripts/lib/layout-blueprint/vocabulary.mjsScript872 B
scripts/lib/ui-normalization.css1.5 KiB
scripts/optimize-svg.mjsScript895 B
scripts/post-build-gap.mjsScript16.4 KiB
scripts/provision-repeater-cms.mjsScript2.8 KiB
scripts/record-gap-decision.mjsScript2.3 KiB
scripts/replay-extraction.mjsScript5.3 KiB
scripts/resolve-home-page.mjs3.9 KiB
scripts/site-clone.mjs35.5 KiB
scripts/validate-font-contract.mjs1.3 KiB
scripts/verify-interactions.mjs29.1 KiB
scripts/visual-qa.mjs20.6 KiB

references/post-build-gap-contract.md

Post-build gap analysis and fix contract

The first successful build is a comparison candidate, not the end of the clone.

Run the result extraction

Start the generated project and keep its local URL available, then run:

node scripts/post-build-gap.mjs <source-url> \
  --out projects/<project-name> \
  --result-url http://localhost:<port>/

The command reuses the capture primitives for the home result route. It captures the result's desktop/tablet/mobile screenshots, page and section evidence, assets, fonts, SEO, interactions, design tokens, scene contract, control-state contract, visual assets, layout blueprint, and UI normalization evidence. Source contracts are read through extraction/latest.json and its immutable frozen manifest; builders and QA do not read or recapture source observations as a substitute for a missing spec fact. Result evidence is isolated under the numbered gap iteration and never replaces the frozen extraction.

If Chromium launch is blocked by the execution environment, that is a recovery case before it is a blocker: rerun the command with the required browser-launch escalation (or from a normal local shell/session that permits Playwright to launch) before treating the gap run as failed.

Deterministic comparison vocabulary

Findings use these categories:

dimensions: full-page/section height, normalized region geometry, important text width, line count, and logo size;
images: source image/video/logo identity, count, role, and placement;
layout: route and section coverage, section order, composition, background model, and media ownership;
text: visible headings, body copy, labels, tabs, and CTAs;
interactions: source core behavior not observed in the running result.

Severity means:

critical: missing route or identity-bearing brand media;
high: source intent or a major layout/interaction is wrong;
medium: meaningful supporting geometry/style differs beyond tolerance;
low: review or cleanup that does not materially change identity.

Exact requirements and tolerance ranges are embedded in gap-analysis.json. Do not turn this into a universal pixel-diff gate. Consent infrastructure, different video frames, font antialiasing, timestamps, and small crop/compositing differences are non-blocking unless they change layout or page intent.

Required screenshot judgment

The deterministic report creates screenshotPairs[] with source and result paths. Open every pair at original size, at all captured viewports. Review the page section by section and add only identity-affecting visual findings to the canonical iteration report referenced by latest.json.paths.reportJson, using the same finding schema.

Write iterations/<NNN>/visual-review.json using this shape (one record for every pair):

{
  "pairs": [
    {
      "pairId": "home-desktop",
      "viewport": "desktop",
      "observation": "Hero dog is substantially larger than the source and obscures the title.",
      "verdict": "findings-recorded",
      "findingIds": ["gap-041"]
    },
    {
      "pairId": "home-mobile",
      "viewport": "mobile",
      "observation": "Header hierarchy, hero composition, and visible section order match source identity.",
      "verdict": "no-identity-gap",
      "rationale": "Only harmless antialiasing differences remain."
    }
  ]
}

After review, run:

node scripts/finalize-gap-review.mjs <source-url> \
  --out projects/<project-name>

The finalizer rejects missing, duplicate, unknown, or incomplete records; verifies linked finding IDs against the canonical report; synchronizes the canonical report, latest pointers, and iteration manifest; and recomputes acceptance.

Gap fix phase

Use gap-fix-plan.md in this order:

missing page/section;
text, logos, and source media;
major section composition and background/media ownership;
important dimensions, line counts, and responsive geometry;
core interactions and initial states;
supporting spacing and styling.

Fix the implementation rather than weakening tolerances or editing extracted result evidence. For a new iteration following open critical/high findings, complete the generated visual-progress.json. It must give every prior blocking finding a named section target plus the matching canonical source, prior-result, and current-result screenshot paths; record visible before/after observations and an improved, no-visible-improvement, or regressed verdict. The finalizer rejects incomplete or untraceable proof, and an accepted resolution requires improved. Build again, rerun post-build-gap.mjs to create the next immutable iteration, inspect its new screenshot queue, and finalize the review. Run at most two fix passes by default. Each owned extraction gap receives at most two distinct targeted recovery attempts. Repeating the same tactic without new evidence is not progress. After exhaustion, keep the unit provisional and continue unrelated work. Report what could not be imported reliably, why, and the user's post-assembly choices instead of treating a local gap as a global blocker.

Completion requires:

the latest build succeeds;
visual review is reviewed (or legitimately not-applicable);
no open critical or high findings remain;
interaction QA passes for core scenes;
residual medium/low and provisional extraction gaps are summarized rather than hidden;
final-report.json and .md identify every unresolved/user-accepted gap;
local gaps end as done_with_gaps; only a global blocker ends as blocked.

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

2026-11-08

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