skill-crawler

Convert crawled documentation into structured SKILL.md files with validation.

3|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/benjaminwestern/google-engineer-skills --skill skill-crawler
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-crawler
Source: https://github.com/benjaminwestern/google-engineer-skills/tree/main/skills/skill-crawler
Command: npx skills add https://github.com/benjaminwestern/google-engineer-skills --skill skill-crawler

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the process of converting crawled documentation into structured, usable Skill Units, significantly reducing the manual effort required to create new agent capabilities.

Core Features & Use Cases

  • Analyze Documentation: Helps review and understand content extracted from crawling.
  • Structure Skills: Organizes information into logical sections for a Skill.md file.
  • Generate SKILL.md: Creates a well-formatted SKILL.md file based on best practices.
  • Validate Skills: Provides a checklist to ensure the generated skill meets quality standards.
  • Use Case: After using playwright-cli to crawl a complex API's documentation, this skill helps you quickly transform that raw data into a ready-to-use SKILL.md file for an AI agent.

Quick Start

Use the skill-crawler to generate a SKILL.md file for a new skill based on crawled documentation.

Frequently Asked Questions about skill-crawler

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

FAQPage Schema
How do I convert crawled documentation into a structured SKILL.md file?

To convert crawled documentation into a SKILL.md file, this skill analyzes raw web content, organizes it into logical sections, and generates a validated markdown file for AI agents. It automates content structuring for opencode-dev specifications.

What is the best way to generate AI agent skills from raw web documentation?

Generating AI agent skills from raw web documentation requires analyzing extracted content, organizing it into logical sections, and validating the output. This skill automates that workflow to produce ready-to-use agent capabilities.

Do I need playwright-cli to crawl documentation for skill generation?

Yes, playwright-cli is required for crawling web documentation. This skill processes the raw content extracted by playwright-cli, analyzing it to generate a structured SKILL.md file.

Can I use this skill to structure content from any crawled API documentation?

Yes, this skill structures content from any crawled API documentation by analyzing the raw data and organizing it into logical sections. It generates a SKILL.md file validated against quality standards for AI agents.

How does the skill validate the quality of a generated SKILL.md file?

Quality validation of a generated SKILL.md file is performed using a built-in checklist that ensures the organized content meets best practice standards. This validation step checks the structure and formatting of the skill sections.

What are the limitations of converting web content to skill units automatically?

Automatic conversion of web content to skill units depends on the quality of the crawled documentation. If the raw data is poorly structured, the generated SKILL.md file may require manual adjustments to meet quality validation standards.