claude-skill-web-clone
A methodology and toolkit for cloning websites, ranging from static pages to complex WebGL-based frontends. It provides a structured workflow for reconnaissance, source code analysis, project scaffolding, and content replacement while emphasizing the use of original source code over AI-generated guesses.
Is claude-skill-web-clone safe to install?
Review the source first: our audit of claude-skill-web-clone's source files found 15 shell commands, 1 external URL, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes arbitrary shell commands and scripts on the local machine, interacts with GitHub APIs, and performs network requests to crawl and mirror external websites.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and researchers performing local website cloning for learning, study, or personal project development.
What can you do with it?
- Cloning static HTML/CSS websites
- Reconstructing React, Vue, or Next.js content sites
- Reverse engineering complex WebGL, Canvas, and Three.js interactions
- Creating local mock servers for data-driven SPA or SaaS sites
- Performing visual and structural audits of cloned websites
How good is this skill?
Quality score: 9/10. The skill provides a highly detailed, disciplined, and professional workflow for web cloning. It includes clear safety warnings, specific script usage, and a strong emphasis on verification and legal compliance.
What does the skill file contain?
# Web Clone · 网站复刻方法论 把"复刻一个网站"做成可重复的流程。配套工程区:`~/projects/website-clones/`(每个复刻是一个子目录)。 ## 头号铁律:真源码至上,绝不信 AI 推测的代码 > 任何 AI 生成的"复刻分析/施工图",**正文的概念骨架可以参考,但里面的可执行代码块默认全是臆造的**,必须逐行用真源码核对,否则照抄必崩。 **实证(marbles 案例)**:一份 AI 分析文档把原站"解析法求光线-球体交点 + 把光学结果编码成位移图、交给 SVG `feDisplacementMap` 去扭曲真实 DOM"的真架构,臆造成了"ray-marching + SDF + 把 DOM 当纹理采样"——两套完全不同的实现,照抄做不出原效果且慢 N 倍。详见 `references/marbles-case.md`。 所以第一动作永远是:**拿到真源码**。 ## 决策树(按顺序走,不许跳) ### Step 0 · 先建标准工程骨架 ```bash node /Users/jane/.shared-skills/web-clone/scripts/init-clone.mjs <站名> --url <原站URL> ``` 该脚本会创建 `~/projects/website-clones/<站名>-clone/`...
Frequently asked questions
Should I trust AI-generated code for website cloning?
No. The skill mandates that AI-generated code blocks are treated as guesses. Users must verify all code against the original source code.
What is the purpose of the design-dna.json file?
It stores design tokens like fonts, colors, and framework effects to facilitate visual cloning or content modification while maintaining the original site's aesthetic identity.
Can this skill clone websites with login or payment systems?
No. The skill does not support cloning backend business logic, authentication, or payment systems. It focuses on frontend reproduction.
Related skills
lark-workflow-meeting-summary
219.7KUsers who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem
The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.
programmatic-seo
83.5KContent strategists, SEO specialists, and marketers building large-scale, data-driven website content
The programmatic-seo skill provides a framework for generating SEO-optimized pages at scale using templates and data. It guides users through keyword research, data sourcing, template design, internal linking, and indexation strategies while emphasizing content uniqueness to avoid search engine penalties.
ad-creative
64.0KPerformance marketers, growth teams, and advertisers who need to produce ad copy at scale or optimize existing ad creative
The ad-creative skill generates, iterates, and scales ad copy for paid advertising platforms including Google, Meta, LinkedIn, TikTok, and Twitter. It provides frameworks for creating ad headlines, descriptions, and primary text based on product context and performance data.
recipe-save-email-attachments
16.9KUsers who manage email attachments and Google Drive storage using the Google Workspace CLI
This recipe automates the process of locating Gmail messages containing attachments and saving those files to a specified Google Drive folder.