skills.rest
zjp1997720
zjp1997720COMMUNITY
Explore all skills by this author →
GitHub

web-clipper

Clip web articles into local Markdown with frontmatter and original URLs.

12|3|Updated Apr 9, 2026
Search Tags:#automation#markdown#frontmatter#web-scraping#web-clipper#article-clipping
One-click install
npx skills add https://github.com/zjp1997720/content-twin-toolkit --skill web-clipper-zjp1997720
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-clipper
Source: https://github.com/zjp1997720/content-twin-toolkit/tree/main/.claude/skills/web-clipper
Command: npx skills add https://github.com/zjp1997720/content-twin-toolkit --skill web-clipper-zjp1997720

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill covers two tasks: saving individual web articles to local Markdown with extracted metadata, and batch clipping from archives or index pages for multiple articles, ensuring output is structured for Obsidian-style vaults.

Core Features & Use Cases

  • Single-article clipping: input a URL, extract title, description, published date, and content, and save as Markdown with frontmatter.
  • Batch clipping: input an archive/index page and fetch multiple articles according to user preferences, saving them locally with consistent naming and metadata.
  • Fallback and safety: uses browser-assisted URL collection when needed and optional Metaso API fallback for anti-scraping sites.
  • Output-ready: Markdown with frontmatter suitable for vaults like Obsidian and Clippings.

Quick Start

Run the bootstrap wrapper from your project root to verify your environment and prepare the default clipping directory.

Frequently Asked Questions about web-clipper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I save web articles as Markdown with frontmatter for Obsidian?▼

To save web articles as Markdown with frontmatter, you provide a URL and the skill extracts the title, description, published date, and content, outputting a structured file ready for your Obsidian vault.

Can I batch clip multiple articles from an archive page into local Markdown?▼

Yes, you can batch clip multiple articles from an archive or index page. The skill fetches content according to your preferences and saves them locally with consistent naming and metadata.

What happens if direct web scraping fails due to anti-scraping mechanisms?▼

When direct web scraping fails due to anti-scraping mechanisms, the skill utilizes a Metaso API fallback and browser-assisted URL collection to ensure successful article extraction.

Does web clipping require any specific environment setup before saving articles?▼

Web clipping requires a verified environment setup. You run a bootstrap wrapper from your project root to check dependencies and prepare the default output directory before saving articles.

How does single-article web scraping preserve the original source URL?▼

Single-article web scraping preserves the original source URL by extracting it alongside the content and embedding it directly into the generated Markdown file's metadata.

What metadata is included when clipping web pages into local Markdown?▼

When clipping web pages into local Markdown, the skill includes extracted metadata such as the title, description, published date, content, original URL, and optional author and tag information.

Related Skills

Explore More Content & Communication Skills→
thermiteauthermiteau
10

init

Create the .maverick/ directory and default settings.json for Maverick projects.

Official
Intermediate
danmestasdanmestas
4

knowledge-base-overview

Organize markdown knowledge bases with Obsidian conventions and cross-links.

Community
Advanced
upmarkingupmarking

seo-firecrawl

Crawl websites via Firecrawl MCP to gather pages, metadata, and links.

Official
Advanced
enkira-aienkira-ai
2

wechat-reader

Extract WeChat Official Account article text and metadata from mp.weixin.qq.com pages.

Official
Intermediate