Research & data toolkit
Turn web pages, files and spreadsheets into clean input, and let an agent write the research report.
MarkItDown converts PDFs and Office files to Markdown. For the web, use Crawl4AI if you want to self-host, or Firecrawl MCP if you want a hosted service. GPT Researcher runs the whole research loop and writes a cited report. The xlsx skill handles the spreadsheet at the end.
Skills in Research & data toolkit
- 184.1K
MarkItDown
Microsoft · Tool / CLI
Microsoft's lightweight Python tool that converts PDFs, Office files and more into clean Markdown for LLMs.
DataAny agent / LLMActive. Last activity Sep 14, 2026 - 83.5K
Crawl4AI
unclecode · Tool / CLI
An open-source, LLM-friendly web crawler and scraper that turns pages into clean Markdown and structured data.
DataAny agent / LLMActive. Last activity Sep 14, 2026 - 7.5K
Firecrawl MCP
Firecrawl · MCP server
The official Firecrawl MCP server. Search, scrape and crawl the live web from any MCP agent and get clean content back.
DataClaude Code, Cursor +1Active. Last activity Sep 14, 2026 - 29.5K
GPT Researcher
assafelovic · Agent
An open deep-research agent that searches the web and your local files and writes a detailed report with citations.
DataAny agent / LLM, Claude CodeActive. Last activity Aug 27, 2026 - 176.4K
Excel Spreadsheets (xlsx) Skill
Anthropic · Skill
The Anthropic skill for opening, fixing and building spreadsheets with working formulas and clean formatting.
DataClaude Code, Claude.ai / DesktopActive. Last activity Sep 10, 2026