From Firecrawl Workflows
Scrapes web content into LLM-ready markdown knowledge bases for RAG, training, documentation mirrors, or reference corpora using Firecrawl.
How this skill is triggered — by the user, by Claude, or both
Slash command
/firecrawl-workflows:firecrawl-knowledge-baseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this to turn URLs or topics into organized LLM-ready content.
Use this to turn URLs or topics into organized LLM-ready content.
Infer the source, goal, depth, and output location from context. If the source and goal are clear, proceed immediately.
Ask at most 1-3 concise questions only if blocked, such as the source URL/topic, whether the output is reference/RAG/training/docs, or training format if training is requested.
Use Firecrawl map for documentation sites, search for topic-based corpora, scrape pages into markdown, and preserve code examples and tables.
For files, follow the Firecrawl download-style convention:
.firecrawl/
<hostname>/
<path>/
index.md
If appropriate, use sub-agents or equivalent parallel task runners:
index.md, and sources.json.manifest.json.training-data.jsonl and training-metadata.json.# Knowledge Base: [Source]
## Summary
[What was collected and why]
## Output Structure
[Files/directories created]
## Coverage
[Sections, source types, counts]
## Usage Notes
[How to use in RAG, docs, training, or agent context]
## Sources
[URLs collected]
## Rerun Inputs
workflow: firecrawl-knowledge-base
source: [url/topic]
goal: [reference/rag/train/docs]
depth: [quick/thorough/exhaustive]
output_dir: [.firecrawl/]
npx claudepluginhub firecrawl/firecrawl-workflows --plugin firecrawl-workflowsScrape single pages or crawl sites into LLM-ready markdown via Firecrawl JS library. Handles sync/async jobs, depth limits, path filters, JS rendering.
Scrapes URLs to markdown/HTML/JSON, crawls websites for multi-page extraction, searches the web, maps sites, and extracts structured data using Firecrawl MCP tools.
Ingests public or authenticated documentation portals using Firecrawl browser. Handles JS-heavy pages, login-gated content, paginated help centers, and structured markdown/JSON extraction.