webpage-capture-markdown

Name: webpage-capture-markdown
Availability: InStock
Author: yangshu2087

Capture live webpages and save them as local Markdown notes.

Updated Mar 24, 2026

Search Tags:#note-taking #markdown #archival #web-page #web-capture #offline-notes

Ready to run

npx skills add https://github.com/yangshu2087/Codex --skill webpage-capture-markdown

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: webpage-capture-markdown
Source: https://github.com/yangshu2087/Codex/tree/main/.agents/skills/webpage-capture-markdown
Command: npx skills add https://github.com/yangshu2087/Codex --skill webpage-capture-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables you to transform a live webpage into a reusable, local Markdown note, preserving the page content for offline reference and future use.

Core Features & Use Cases

Preserve headings, links, and key content from a webpage into a Markdown file.
Choose a capture method: lightweight web capture, Playwright for dynamic pages, or manual capture with user confirmation.
Use Case: create offline archives of research articles, project specs, or reference pages.

Quick Start

Capture the requested webpage and save it as a Markdown note including the URL, title, and captured_at timestamp.

Frequently Asked Questions about webpage-capture-markdown

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

FAQPage Schema

How do I save a web page as a Markdown file for offline reference?▼

To save a web page as a Markdown file, this skill captures the live URL and extracts the title, headings, links, and core content into a local Markdown note. The output is saved to a domain-specific folder for offline archival.

What is the best way to capture dynamic web pages that require JavaScript rendering?▼

The best way to capture dynamic web pages is using the Playwright-based capture method. This approach executes JavaScript to render dynamic content before extracting the page into a Markdown note.

Can I capture authenticated web pages that require user login?▼

Yes, you can capture authenticated web pages using the user-confirmed interaction method. This allows you to manually log in and confirm interactions before the skill saves the content as a Markdown note.

Does web page capture preserve the original links and headings in the Markdown output?▼

Yes, web page capture preserves original headings and links in the Markdown output. The generated file includes the source URL, page title, and a captured_at timestamp alongside the extracted content.

What limitations should I expect when archiving web pages into local notes?▼

A key limitation when archiving web pages is that lightweight capture may miss dynamic JavaScript content. For interactive or authenticated pages, you must use Playwright or manual user-confirmed interactions to ensure complete Markdown extraction.