Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Site Clone Migration

ASecurity

Use when cloning any existing website into a new stack with Claude Code: extract screenshots plus HTML/fonts/colors, download assets, rebuild section by section with parallel agents, and verify with visual diff. Triggers on \"clone website\", \"site clone\", \"wordpress migration\", \"restack site\". Non-triggers: designing a new site from scratch (use cloud-design-prototyping). Outcome: a Next/React plus Tailwind plus TS repo that matches the source layout section by section.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgoreactapi

Works with

claude codeapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill site-clone-migration --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Site Clone Migration?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Site Clone Migration
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-site-clone-migration/badge)](https://www.skillsdirectory.com/skills/majinmagros-site-clone-migration)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: site-clone-migration
description: "Use when cloning any existing website into a new stack with Claude Code: extract screenshots plus HTML/fonts/colors, download assets, rebuild section by section with parallel agents, and verify with visual diff. Triggers on \"clone website\", \"site clone\", \"wordpress migration\", \"restack site\". Non-triggers: designing a new site from scratch (use cloud-design-prototyping). Outcome: a Next/React plus Tailwind plus TS repo that matches the source layout section by section."
metadata:
  origin: ECC
---

# Site Clone Migration

Clone any site into a clean, owned stack: extract the source, rebuild it
section by section with parallel agents, verify with visual diff, and ship
a Next/React + Tailwind + TS repo. Includes a WordPress -> repo exit path.

## When To Activate

- The user says clone this site, copy this layout, restack, migrate from
  WordPress, or rebuild a page pixel by pixel.
- There is a live URL to reproduce plus a target stack (Next or React with
  Tailwind and TS).
- A visual check is required before calling the clone done.
- The source uses WordPress and the goal is a code repo instead.

## Non-Goals

- No brand-new design work; this reproduces an existing layout.
- No content scraping for republishing third-party copy or images without
  rights; get permission or replace assets first.

## Workflow

1. Capture the source: for each route, save full-page screenshots (desktop
   plus mobile), HTML, computed fonts, color tokens, and spacing scale.
   Record the URL, viewport, and date per capture.
2. Inventory assets: list images, fonts, icons, and videos. Download only
   licensed or replaceable files into a local vendor folder with a manifest
   (source URL -> local path -> license note).
3. Define sections: split the page into sections (header, hero, proof,
   pricing, FAQ, footer). One section = one work unit with its own
   acceptance screenshot.
4. Rebuild in parallel: assign one agent per section against the new stack
   (Next or React + Tailwind + TS). Shared tokens (colors, type, spacing)
   are frozen before agents start.
5. Visual diff: compare each rebuilt section against its source screenshot
   side by side. Log mismatches (layout, type, spacing, color) and fix in
   the section owner only.
6. Responsive pass: re-run the diff at mobile width. Fix overflow, tap
   targets, and type scale before merging sections.
7. WordPress exit (when needed): map posts, pages, and media to repo
   content files, redirect old slugs, and verify every migrated URL returns
   200 in the new app.
8. Ship gate: full-page diff plus link check plus build pass. No merge
   while any section diff is open.

## Section Acceptance

- Layout matches at desktop and mobile widths.
- Fonts, colors, and spacing use shared tokens, not hard-coded values.
- Images load from the local vendor folder, not hotlinked.
- Links and forms resolve; no dead routes.

## Anti-Patterns

- Copying third-party text, images, or fonts without rights.
- One giant agent rebuilding the whole page at once -> slow and blurry.
- Skipping the token freeze -> every section drifts to its own palette.

## Exemplo

```text
URL + stack Next/Tailwind/TS → captura (screenshots desktop+mobile, HTML, fontes, tokens)
6 seções, 1 agente cada (tokens congelados) → visual diff por seção → mobile pass
Gate: diff zerado + links 200 + build verde; WordPress: posts→arquivos + redirects
```

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →