메뉴
USE THIS SKILL WHEN: the user wants to scrape a URL, crawl a website, map site URLs, or extract structured data from web pages. Provides pay-per-use web scraping via Firecrawl through the Obul proxy.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/polymerdao/pay-plugin --skill obul-firecrawl명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
USE THIS SKILL WHEN: the user wants to search X/Twitter, look up a Twitter user profile, read a specific tweet, browse a user's timeline, search users, or explore communities. Provides pay-per-use X/Twitter data via twit.sh through the Obul proxy.
USE THIS SKILL WHEN: the user wants to convert media files, transcribe audio or video, extract text from images via OCR, or download and convert content from YouTube, TikTok, Instagram, or other platforms. Provides pay-per-use media conversion and transcription via cnvrt.ing through the Obul proxy.
USE THIS SKILL WHEN: the user wants to proxy a request through Obul, call an x402 API directly, or needs to understand the Obul proxy URL pattern. Handles x402 payment negotiation automatically.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | obul-firecrawl |
| description | USE THIS SKILL WHEN: the user wants to scrape a URL, crawl a website, map site URLs, or extract structured data from web pages. Provides pay-per-use web scraping via Firecrawl through the Obul proxy. |
| homepage | https://www.firecrawl.dev |
| metadata | {"obul-skill":{"emoji":"🔥"}} |
| registries | {} |
Firecrawl provides pay-per-use web scraping, crawling, site mapping, and structured data extraction with built-in JavaScript rendering, anti-bot handling, and proxy rotation. Through the Obul proxy, each request is paid individually — no Firecrawl account or API key required.
All requests use the obulx CLI, which handles proxy routing and authentication automatically.
Install and log in (one-time setup):
npm install -g @obul.ai/obulx
obulx login
Base URL: https://firecrawl.x402endpoints.com
Scrape a single URL with JavaScript rendering and anti-bot handling. Returns clean markdown by default, with optional HTML, raw HTML, links, and screenshot formats.
Pricing: $0.001
obulx -X POST -H "Content-Type: application/json" \
-d '{"url": "https://example.com", "formats": ["markdown"]}' \
"https://firecrawl.x402endpoints.com/v1/scrape"
Response: JSON object with scraped content in the requested formats. The markdown format returns clean,
well-structured markdown extracted from the page. Additional formats include html, rawHtml, links (list of all
URLs on the page), and screenshot (base64-encoded image).
Discover all URLs on a website. Returns a complete sitemap-style list of pages without scraping their content.
Pricing: $0.001
obulx -X POST -H "Content-Type: application/json" \
-d '{"url": "https://example.com"}' \
"https://firecrawl.x402endpoints.com/v1/map"
Response: JSON object with an array of all discovered URLs on the site. Use this to plan targeted scraping or crawling of specific pages.
Start an asynchronous crawl job that scrapes multiple pages on a website. The limit parameter is required and
determines both the maximum number of pages crawled and the total cost.
Pricing: $0.001 per page (total = limit × $0.001, max 1000 pages)
obulx -X POST -H "Content-Type: application/json" \
-d '{"url": "https://example.com", "limit": 10}' \
"https://firecrawl.x402endpoints.com/v1/crawl"
Response: JSON object with a crawl job id and status. The crawl runs asynchronously — use the returned job ID
to poll for results. Each crawled page is returned as clean markdown content.
Extract structured data from one or more URLs. Firecrawl scrapes the pages and returns data in a structured format, ideal for pulling specific fields from product pages, articles, or directories.
Pricing: $0.001
obulx -X POST -H "Content-Type: application/json" \
-d '{"urls": ["https://example.com/product/123"]}' \
"https://firecrawl.x402endpoints.com/v1/extract"
Response: JSON object with structured data extracted from the provided URLs. The extraction identifies and returns key fields like titles, prices, descriptions, and other structured content from the pages.
| Endpoint | Price | Purpose |
|---|---|---|
POST /v1/scrape | $0.001 | Scrape a single URL to clean markdown |
POST /v1/map | $0.001 | Discover all URLs on a website |
POST /v1/crawl | $0.001 per page | Async crawl a website (limit required) |
POST /v1/extract | $0.001 | Structured data extraction from URLs |
/v1/map first to discover available URLs, then crawl only the pages you need
instead of blindly crawling an entire site.limit (e.g., 10) and increase as needed. The cost scales
linearly with the limit, and the maximum is 1000 pages.markdown for most use cases. Use html when you need structure, links
when you only need URLs, and screenshot for visual verification./v1/scrape for individual URLs. Only use /v1/crawl when you
need multiple pages from the same site.| Error | Cause | Solution |
|---|---|---|
402 Payment Required | Payment not processed or insufficient | Verify your account has sufficient balance at my.obul.ai. Run obulx login if not authenticated. |
400 Bad Request | Missing or invalid request body | Ensure required fields (url, query, urls, limit) are present and correctly typed. |
422 Unprocessable Entity | Valid request but URL cannot be scraped | Verify the URL is accessible and not blocked. Try a different URL or format. |
429 Too Many Requests | Rate limit exceeded | Add a short delay between requests and avoid rapid-fire calls. |
500 Internal Server Error | Upstream Firecrawl service issue | Wait a few seconds and retry. If persistent, the service may be experiencing downtime. |
503 Service Unavailable | Firecrawl service temporarily down | Retry after a brief wait. |