firecrawl-knowledge-base

What problem does it solve? Turning scattered web documentation and topic content into structured, LLM-ready material requires manual scraping, cleanup, and organization. This Skill automates collecting web sources into reference docs, RAG chunks, training datasets, or documentation mirrors. ## Core Features & Use Cases - Multi-Mode Output: Produces reference markdown with sources.json, RAG chunks with manifest.json, training data as training-data.jsonl, or full documentation mirrors. - Firecrawl Collection Plan: Uses Firecrawl map for documentation sites, search for topic corpora, and scrape for markdown conversion while preserving code examples and tables. - Parallel Collection: Supports splitting work across sub-agents by docs section, source type, or pipeline stage. - Use Case: Point it at a framework's documentation site and receive a complete local markdown mirror with a table of contents, source URLs in frontmatter, and a rerun manifest. ## Quick Start Ask the agent to build a RAG-ready knowledge base from a documentation URL using Firecrawl and save it under the .firecrawl directory.