web-page-capture

Capture web pages into JSON, Markdown, and handoff artifacts with local images.

Updated Apr 23, 2026
One-click install
npx skills add https://github.com/Ocean326/Agents --skill web-page-capture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-page-capture
Source: https://github.com/Ocean326/Agents/tree/main/skills/global/web-page-capture
Command: npx skills add https://github.com/Ocean326/Agents --skill web-page-capture

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Capture a single web page into structured, reusable local artifacts (JSON, Markdown, handoff notes, and downloaded images) to accelerate downstream agent work while keeping cookies private and avoiding undeclared caches.

Core Features & Use Cases

  • Auto-detects the source site (Zhihu, X, Xiaohongshu, or generic pages) and captures page content, images, and metadata into a portable bundle.
  • Outputs stable artifacts including JSON, Markdown, and handoff files, plus a local images directory for offline review.
  • Privacy-friendly: cookies are sourced from private storage or environment variables and are never embedded in final artifacts.

Quick Start

Run the bundled capture script to process a target URL and write results to a designated output directory.

Frequently Asked Questions about web-page-capture

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

FAQPage Schema
How do I capture web pages into structured Markdown and JSON for offline agent workflows?

Web page capture extracts page content, metadata, and images into structured JSON and Markdown files for offline agent workflows. It auto-detects sites and outputs portable artifacts to a user-specified directory.

Can I download local images from Xiaohongshu or Zhihu pages without embedding private cookies?

Yes, you can download local images from Xiaohongshu or Zhihu while keeping private cookies secure. Cookies are sourced from private storage or environment variables and are never embedded in the final output artifacts.

What is the best way to extract content from X posts into reusable local artifacts?

The best way to extract X posts into reusable local artifacts is using an auto-detection capture script. It processes the URL and writes deterministic JSON, Markdown, handoff notes, and local images to your output directory.

Does web page extraction work with generic articles or only specific supported sites?

Web page extraction works with both specific supported sites and generic articles. It auto-detects Zhihu, X, Xiaohongshu, and generic pages to capture content and images into a portable bundle.

How do I set up environment variables for privacy cookies when capturing web pages?

To set up privacy cookies for capturing web pages, source them from private storage or environment variables. This ensures sensitive authentication data remains separate and is never written into the final captured artifacts.

Why does my web page capture output include handoff files alongside JSON and Markdown?

Web page capture output includes handoff files alongside JSON and Markdown to accelerate downstream agent work. These structured notes provide context for offline workflows, ensuring deterministic and reusable local artifacts.