No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by boyang-hu · Codex Skill · ★ 776
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is website-rebuild-skill safe to install? View the security audit →
website-rebuild-skill 中文 | English 给一个网址，让你的 AI agent 把那个网站逐行复刻出来，并且能证明复刻得对。 它不是"做一个看起来很像的页面"。它把源站的实现当作规格书：先把整站抓成只读证据，再从压缩过的代码里逐行还原逻辑，最后用一整套自动验收门证明"复刻侧和源站在做同一件事"——包括逐像素比对。 遵循 Agent Skills 开放规范，为任何支持 skills 的智能体设计。跨运行时不是口号而是实测：验证清单里既有 Claude Code 跑完的目标，也有 Codex 全程跑完的目标（Hashgraph VC，166/166 响应字节一致）——同一份 skill 目录，放进哪个 runtime 都能走完整条管线。 目录 特性 效果对比：源站 vs 复刻 快速开始 它怎么工作 适用范围 这和"扒站"有什么不一样 已验证过的网站 仓库结构 关于版权 路线图 更新记录 贡献 许可 友情链接 特性 判级先行——开工前先探测目标属于哪一类、能不能做；做不了会直接说明原因，不会硬跑产出垃圾 取证式镜像——整站抓成只读快照（逐文件 sha256 账本、引用闭包校验、真实性检查），断网也能跑 行号可溯源的逆向——复刻里的每一行都能指回源站 bundle 的哪一行；bug 与怪写法照抄不修 量化验收——控制台 / 网络 / DOM / 几何 / 逐像素五层自动比对，差异要么修掉、要么登记，不许糊过去 源码化交付——逐字移植的产物重写成人能读的工程（拆模块、按证据命名、补溯源头注），复制到任何地方断网可跑 零依赖工具链——61 个 Node 脚本（48 个工序脚本与验收门 + 8 个共用库 + 5 个源码化/反推重构器），源码化之前整条流水线不装任何 npm 包 死站也能救——Wayback 存档抢救：锚点+时间窗选一个连贯时刻、原始字节落成标准镜像、永久洞如实登记；五次死站抢救实测（四个复活、其一走完 L3；一个画面层确证全
| Stars | 776 |
| Forks | 158 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 61.8068978374071/100 |
| Last Updated | 2026-09-02 |
| Created | 2026-08-11 |
| Platforms | browser, claude-code, codex, node |
| Est. Tokens | ~17k |
These tools work well together with website-rebuild-skill for enhanced workflows:
Looking for a website-rebuild-skill alternative? If you're comparing website-rebuild-skill with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl
Universal Claude Code workflow plugin with agents, skills, hooks, and commands
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies
471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the cc
Explore other popular codex skill tools:
website-rebuild-skill is 复刻网站的 Agent Skill：抓只读镜像、从压缩代码逐行还原、自动比对验收。An agent skill that mirrors a website, rebuilds it from the minified code, and verifies the result with automated diffs.. It is categorized as a Codex Skill with 776 GitHub stars.
website-rebuild-skill is primarily written in JavaScript. It covers topics such as agent-skills, ai-agents, claude.
You can find installation instructions and usage details in the website-rebuild-skill GitHub repository at github.com/boyang-hu/website-rebuild-skill. The project has 776 stars and 158 forks, indicating an active community.
website-rebuild-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to website-rebuild-skill on Agent Skills Hub include Claude-Code-Everything-You-Need-to-Know, claude-workflow-v2, deepcontext-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: