← 返回 Skills 市场

defuddle-web-cleaner

Name: defuddle-web-cleaner
Author: extrastu

作者 extrastu · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

1816

总下载

当前安装

版本数

在 OpenClaw 中安装

/install defuddle

功能描述

Extract and clean readable article content, metadata, and markdown from URLs or HTML for research, note taking, and web scraping.

安全使用建议

Safe for normal article-cleaning use. Before processing private pages or copied HTML, confirm whether your agent will use the external defuddle.md service, a local Defuddle CLI, or another parser.

能力评估

✓ Purpose & Capability

The purpose is coherent: extract readable article text, Markdown, and metadata from user-provided URLs, HTML, or page text.

ℹ Instruction Scope

The invocation wording is broad for URL/HTML cleanup and related research workflows, but the described actions remain limited to parsing and returning cleaned content.

ℹ Install Mechanism

The artifact has no executable code or install script, but its reference mentions a Defuddle web endpoint and CLI without declaring a specific packaged implementation.

ℹ Credentials

Network fetching or use of an external Defuddle service is proportionate for URL-to-article conversion, but users should avoid sending private HTML unless they know where it is processed.

✓ Persistence & Privilege

The artifacts do not request credentials, privileged paths, local profile/session access, background workers, or persistent storage.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install defuddle
安装完成后，直接呼叫该 Skill 的名称或使用 /defuddle 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of Defuddle Web Cleaner skill. - Extracts main article content from web pages, removing ads, navigation bars, sidebars, and other clutter. - Supports input as URL, raw HTML, or web page text. - Outputs clean Markdown content or structured JSON with metadata (title, author, site, description, published date, content). - Useful for web scraping, research workflows, note-taking, and converting web articles for Obsidian or LLM processing.

元数据

Slug defuddle

版本 1.0.0

许可证 MIT-0

累计安装 42

当前安装数 42

历史版本数 1

常见问题

defuddle-web-cleaner 是什么？

Extract and clean readable article content, metadata, and markdown from URLs or HTML for research, note taking, and web scraping. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1816 次。

如何安装 defuddle-web-cleaner？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install defuddle」即可一键安装，无需额外配置。

defuddle-web-cleaner 是免费的吗？

是的，defuddle-web-cleaner 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

defuddle-web-cleaner 支持哪些平台？

defuddle-web-cleaner 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 defuddle-web-cleaner？

由 extrastu（@extrastu）开发并维护，当前版本 v1.0.0。