How does the skill handle local development environments?

It uses specific environment variables (like OFFICIAL_DOCS_DEV_ROOT) to redirect the scraping scripts to your local repository paths rather than the installed production plugins.

How does Headless mode differ from Sequential mode?

Sequential mode runs each ecosystem one after another in your current session using /compact to manage memory. Headless mode generates commands to run scraping tasks in parallel across multiple terminal windows.

Can I scrape only one specific ecosystem?

Yes, you can provide a single ecosystem name as an argument, such as '/batch-scrape claude', to run the workflow for just that platform.

What ecosystems can I scrape using this skill?

The Batch Scrape skill currently supports automated documentation workflows for the Claude, Cursor, Duende, Google (Gemini), and OpenAI ecosystems.

Does Batch Scrape perform quality control on the data?

Yes. It includes steps for content diff analysis, filter effectiveness reviews, index validation, and automatic markdown linting before committing changes.

Batch Documentation Scraper

Name: Batch Documentation Scraper
Author: melodic-software

bymelodic-software

•

Web Scraping & Data Collection

Automates multi-ecosystem documentation scraping, validation, and maintenance workflows using local development configurations.

Batch Scrape is a specialized developer utility designed for maintaining documentation-driven plugins within the Claude Code ecosystem. It streamlines the process of refreshing local documentation stores for multiple platforms—including Claude, Cursor, Gemini, and OpenAI—by handling environment variable routing, sequential or parallel execution, and automated cleanup. This skill ensures that scraped content remains accurate and high-quality through integrated audit, markdown linting, and content diff analysis steps, making it an essential tool for developers managing complex documentation pipelines.

Key Features

01Multi-ecosystem scraping for Claude, Cursor, Duende, Google, and OpenAI

0238 GitHub stars

03Automated content validation, index rebuilding, and age-based cleanup

04Headless execution support for parallel scraping across terminal windows

05Dev mode redirection to local plugin paths via environment variables

06Integrated audit and fix workflow with markdown linting and git commits

Use Cases

01Simultaneously refreshing documentation across all supported AI ecosystem plugins

02Performing bulk cleanup of aged or outdated documentation articles

03Testing local scraping logic changes before deploying to production

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add melodic-software/claude-code-plugins batch-scrape

For use in Claude.ai and ChatGPT

Download Skill