web

Convert web pages to Markdown with optional screenshots and JavaScript execution.

16|1|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/michalvavra/agents --skill web-michalvavra
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web
Source: https://github.com/michalvavra/agents/tree/main/skills/web
Command: npx skills add https://github.com/michalvavra/agents --skill web-michalvavra

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @mozilla/readability, jsdom, node-html-markdown, puppeteer, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill turns web pages into Markdown-ready content, enables optional screenshot capture, JavaScript execution, and interactive element picking for AI consumption.

Core Features & Use Cases

  • Markdown extraction: Convert page content into clean, readable Markdown.
  • Dynamic content & interactions: Execute JavaScript and wait for selectors to handle SPAs and dynamic pages.
  • LiveView and session support: Detects Phoenix LiveView pages and maintains sessions with profiles.
  • Interactive Element Picker: Select precise CSS selectors from a page for targeted extraction.

Quick Start

Fetch a page as Markdown: {baseDir}/scripts/web.js https://example.com, optionally saving a screenshot with --screenshot and running pre-extraction JavaScript with --js.