This automates web research by pulling topics from your markdown files and scraping content through FireCrawl's API. You feed it a markdown file with headers or tagged items, and it generates separate research documents for each topic with full scraped content from multiple sources. It's surprisingly complete: includes rate limiting for the free tier, generates BibTeX bibliographies from results, and bundles Pandoc and MyST templates for academic writing. The 12 second delay between topics means researching 10 topics takes about 2 minutes, which is the right trade-off if you're actually writing papers and need proper citations instead of quick summaries. Good fit for literature reviews or maintaining an Obsidian research vault where you want full source text, not just links.
npx skills add https://github.com/glebis/claude-skills --skill firecrawl-research