skills.rest
doctorduke
doctordukeOFFICIAL
Explore all skills by this author →
WebsiteGitHub

doc-to-skill-scraper

Scrape external documentation and generate SKILL.md files with YAML frontmatter.

Updated Aug 27, 2026
Search Tags:#documentation#skill generation#AI learning#meta-skill#API docs#scraping#knowledge integration
One-click install
npx skills add https://github.com/doctorduke/seashells --skill doc-to-skill-scraper
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-to-skill-scraper
Source: https://github.com/doctorduke/seashells/tree/main/.claude/skills/doc-to-skill-scraper
Command: npx skills add https://github.com/doctorduke/seashells --skill doc-to-skill-scraper

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires beautifulsoup4, requests, pyyaml, markdown.

What problem does it solve?

This meta-skill automates the tedious and time-consuming process of manually converting external documentation (like API references or library docs) into structured Claude Agent Skills. It rapidly integrates new knowledge and capabilities into your AI, saving countless hours of manual parsing and formatting.

Core Features & Use Cases

  • Automated Documentation Scraping: Parses HTML/Markdown documentation from URLs, extracting titles, sections, and code examples.
  • Skill Generation: Automatically generates SKILL.md files with proper YAML frontmatter (name, description) and structured instructions based on the scraped content.
  • Knowledge Integration: Quickly builds domain-specific skills from third-party knowledge sources, making external APIs and libraries immediately usable by your AI.
  • Use Case: You need to integrate the Stripe API into your project. Instead of manually writing a skill, you provide the Stripe API documentation URL. This skill scrapes the docs, extracts key methods and examples, and generates a stripe-payment-intents skill, ready to process payments.

Quick Start

1. Scrape documentation from a URL

(Assumes scrape_docs.py is a script using the skill's logic)

python scrape_docs.py https://stripe.com/docs/api/payment_intents

2. Generate SKILL.md from the scraped data

(Assumes generate_skill.py is a script using the skill's logic)

python generate_skill.py scraped_data.json

Frequently Asked Questions about doc-to-skill-scraper

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

FAQPage Schema
How do I convert API documentation into Claude Agent Skills?▼

Convert API documentation by scraping HTML or Markdown docs, extracting structure and examples, then generating SKILL.md files with YAML frontmatter and formatted instructions. This skill automates that pipeline—parse the documentation URL, and it outputs a ready-to-use skill file.

Can I scrape documentation from multiple formats like HTML and Markdown?▼

Yes. This skill parses both HTML and Markdown documentation, extracting titles, sections, and code examples from either format. It handles diverse doc sources—API references, library docs, protocol specs—converting them uniformly into structured skills.

What's the fastest way to integrate third-party APIs into my AI without manual work?▼

Provide the API documentation URL to this skill; it scrapes the docs, extracts methods and examples, and generates a complete SKILL.md file. Knowledge integration happens automatically, bypassing manual parsing and formatting.

Does this skill work with any documentation source or are there limitations?▼

This skill works with publicly accessible HTML and Markdown documentation sources—API references, library docs, and protocol specifications. It requires the documentation to be URL-accessible and structured enough to parse meaningful sections and examples.

What dependencies do I need to run documentation scraping?▼

The skill requires beautifulsoup4 for HTML parsing, requests for fetching documentation, pyyaml for frontmatter generation, and markdown for processing markdown-formatted docs. These handle web retrieval, content extraction, and SKILL.md assembly.

Related Skills

Explore More Software Engineering Skills→
0xMassi0xMassi
2.1k

webclaw

Extract text, metadata, and structured data from web pages into Markdown and JSON.

Community
Advanced
pradyumnasagarpradyumnasagar
6

roadmap-author

Guide authors through creating and validating ORS SKILL.md files.

Community
Intermediate
walter-lawalter-la

dummy-02-extract

Extract structured data from unstructured text using a shared JSON schema.

Community
Basic
co-cddoco-cddo

Builder

Create custom agents, workflows, and templates for BMAD-based environments.

Official
Basic