Firecrawl Scrape
- 472 installs
- 3.9k repo stars
- Updated January 26, 2026
- parcadei/continuous-claude-v3
firecrawl-scrape is a Claude Code skill that scrapes public URLs or search queries through Firecrawl MCP and returns LLM-ready markdown, HTML, or plain text for developers who need clean web content inside agent sessions
About
firecrawl-scrape is a Claude Code skill in parcadei/continuous-claude-v3 that runs a Python harness against Firecrawl MCP to scrape pages or run web searches on demand. Developers pass `--url` for a direct page or `--search` for query-based retrieval, then choose `--format` as markdown (default), html, or text. The workflow uses `uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py` with Bash and Read tools, making it suited when agents need structured page content for RAG, docs ingestion, or competitive research without hand-writing scrapers.
- Converts any URL into clean markdown optimized for LLMs
- Handles JavaScript-rendered pages and paywalls via Firecrawl
- Returns structured data when schema is provided
- Built for agentic workflows that need fresh web content
- Zero browser management - pure API integration
Firecrawl Scrape by the numbers
- 472 all-time installs (skills.sh)
- +2 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #1,833 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill firecrawl-scrapeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 472 |
|---|---|
| repo stars | ★ 3.9k |
| Last updated | January 26, 2026 |
| Repository | parcadei/continuous-claude-v3 ↗ |
How do you scrape a URL into markdown for agents?
Let their Claude-powered agent scrape, clean, and convert any public webpage into clean LLM-ready markdown on demand.
Who is it for?
Developers building Claude agents that must ingest live web pages or search results as structured text without maintaining custom scrapers.
Skip if: Developers who need authenticated scraping, private intranet pages, or production crawl pipelines with scheduling and rate governance.
When should I use this skill?
A developer or agent needs to fetch or search a public webpage and convert it to markdown, HTML, or text via Firecrawl.
What you get
Markdown, HTML, or plain-text page extracts and search-result content ready for LLM prompts or RAG pipelines.
- markdown page extract
- html or text scrape output
By the numbers
- Supports 3 output formats: markdown, html, and text
- Exposes 2 input modes: direct URL scrape and search query
Files
Firecrawl Scrape Skill
When to Use
- Scrape content from any URL
- Extract structured data from web pages
- Search the web and get content
Instructions
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
--url "https://example.com" \
--format "markdown"Parameters
--url: URL to scrape--format: Output format -markdown,html,text(default: markdown)--search: (alternative) Search query instead of direct URL
Examples
# Scrape a page
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
--url "https://docs.python.org/3/library/asyncio.html"
# Search and scrape
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
--search "Python asyncio best practices 2024"MCP Server Required
Requires firecrawl server in mcp_config.json with FIRECRAWL_API_KEY.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Choose firecrawl-scrape when you want Firecrawl-backed page extraction inside Claude agent sessions instead of ad-hoc curl plus HTML cleanup scripts.
FAQ
What output formats does firecrawl-scrape support?
firecrawl-scrape accepts `--format` values of markdown, html, or text, with markdown as the default. Pass `--url` for a direct page scrape or `--search` for query-based retrieval through the Firecrawl MCP Python harness.
How do you run firecrawl-scrape from Claude Code?
firecrawl-scrape runs with `uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py --url "https://example.com" --format "markdown"`. The skill allows Bash and Read tools to execute the harness and consume returned content.