“Firecrawl”

Deep web scraping and structured lead research via Firecrawl web-agent.

Scrapes websites and extracts content using Firecrawl API.

auth.md protocol — agent registration and authentication for external services (Cloudflare, Firecrawl, Resend, Monday.com).

Multi-structure research via graphify, repos, Obsidian, Perplexity, Firecrawl, Playwright

Token-budgeted web fetch for AI agents — auto-routes Jina, FireCrawl, Trafilatura, PDF.

firecrawl 및 exa MCP를 사용한 다중 소스 심층 조사.

Read tweets, threads, bookmarks, articles, and user timelines on X (formerly Twitter) using an authenticated GraphQL flow.

Telegram archive: chats, messages, contacts, folders, search; import from Telegram Desktop/macOS.

Web scraping + research toolkit for AI agents: scrape, crawl, monitor URLs with anti-bot bypass.

GTM leads, enrichment, outreach, Plays, developer signals/Reo.dev.

Collect the URLs behind one start page with Crawl (new): create a crawl, wait for it, read the kept URLs and optionally each page's HTML, stop it.

Offboard an agent or a person — what they own and block surfaces first, then reassignment, then the archive.

Opt-in Firecracker profile only — provision, verify, reset, and destroy Firecracker microVM sub-agents.

Park or offboard a role — archived with a note, never deleted.

Collect public web pages for research or a documented dataset.

Call Exa Contents (POST /contents) for LLM-ready extraction from known URLs: text, highlights, summaries, links, image links, subpages, freshness-controlled…

Call Exa Search (POST /search) for semantic web retrieval with ranked results, filters, freshness, highlights/text, structured output, or streaming.

Fetch and crawl web pages as markdown locally, fast, with no browser session.

Extract and verify OCR text from images, screenshots, scanned pages, PDFs, Korean or mixed Korean-English UI captures, receipts, signs, ebook captures…

Build layer 3 intelligence: meetings, a brief they will read, always-on in the pocket, and the research shelf.

Explore a codebase and write or update a dense, factual CODEBASE.md context document for other skills to consume.

Extract LinkedIn profiles, jobs, and posts into raw/.

Crawl a website to discover pages and map its structure.

Ingest websites into QMD wiki collections for semantic search via /search and /explore.