dtsola

Xiaoyaoclaw Web Clipper — Documentation skill for Claude Code

Documentation community

OpenClaw web clipper skill: save any web page as clean local Markdown with frontmatter.

How to install Xiaoyaoclaw Web Clipper

This entry records only its repository, not the path inside it, so there is no exact command to give. Open dtsola/xiaoyaoclaw-web-clipper and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Xiaoyaoclaw Web Clipper does

OpenClaw web clipper skill: save any web page as clean local Markdown with frontmatter. Dual-engine extraction, Chinese-safe filenames, batch clipping with dedup, output lands in knowledge/clippings/ ready for kb-retriever indexing. 中文：OpenClaw 网页剪藏工具，双引擎正文提取、中文友好、批量去重，输出直通知识库建索引。

Alternatives in Documentation

Translate Doc Zh — Translate English documentation to Chinese 5.7k ★
Save — Save the current conversation or a specific insight into the wiki vault as a structured note 3.3k ★
Hyperresearch — Agent-driven research knowledge base 2.4k ★

README

OpenClaw Web Clipper 📎

网页剪藏（知识喂料机） | 🌐 English

OpenClaw Web Clipper — save any web page as clean local Markdown with frontmatter. Dual-engine extraction (readability + trafilatura), Chinese-friendly filenames, batch clipping with dedup, output lands in knowledge/clippings/ ready for kb-retriever indexing.

网页「知识喂料机」：发送链接 → 提取正文 → 保存本地 Markdown（frontmatter 齐全）→ 直通 knowledge/ 建索引可检索。双引擎提取、中文友好、批量去重。 OpenClaw web clipper: save any web page as clean local Markdown with YAML frontmatter. Dual-engine extraction (readability-lxml + trafilatura fallback), Chinese-safe filenames, batch clipping with dedup, output ready for kb-retriever indexing.

![license](https://img.shields.io/badge/license-MIT-green) [![ClawHub downloads](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fclawhub.ai%2Fapi%2Fv1%2Fskills%2Fxiaoyaoclaw-web-clipper&query=skill.stats.downloads&label=ClawHub%20downloads&color=blue)](https://clawhub.ai/dtsola/skills/xiaoyaoclaw-web-clipper)

为什么需要

看到好文章想存下来，但：

🔖 浏览器收藏夹越攒越乱，永远不再打开
📝 复制粘贴到笔记，格式稀碎、没有来源、没有日期
🌐 剪藏工具（印象笔记/Cubox）数据在云端，还得付费、怕泄露
🧠 收藏了想喂给 AI 知识库，格式不统一没法检索

这个 skill 解决：**一个命令，网页 → 干净的本地 Markdown**，自动带标题/来源/作者/日期 frontmatter，直接进 knowledge/ 建索引，AI 随时可检索。

特性

🔧 双引擎提取：readability-lxml（快）+ trafilatura（学术级）自动降级链，质量分不足自动切换，bs4 兜底
🇨🇳 中文友好：微信公众号/知乎/CSDN 容器适配、GBK/UTF-8 编码自动判定、中文标题文件名安全保留
📋 批量剪藏：URL 列表文件一次剪完，汇总报告（成功/跳过/失败）
🔁 自动去重：.clips-index.json 索引，重复 URL 自动跳过
📦 frontmatter 齐全：标题/来源/作者/日期/标签，Obsidian 兼容
🔗 知识库闭环：默认输出 knowledge/clippings/，配合 kb-retriever 一键建索引即可检索
🖥️ 双平台：Windows / macOS 行为一致（纯 Python）
🔒 纯本地：不调用外部 API，数据不出本机

安装

# ClawHub（推荐）
clawhub install xiaoyaoclaw-web-clipper

# 或从 GitHub 手动安装
git clone https://github.com/dtsola/xiaoyaoclaw-web-clipper
# 把 SKILL.md、scripts/ 放到你的