This is a wrapper around Google Gemini's Deep Research agent that lets Claude kick off autonomous research tasks. It takes 2-10 minutes and costs $2-5 per run, but you get back cited reports with actual depth instead of quick summaries. Good for market analysis, competitive research, or technical literature reviews when you need more than a single LLM can produce from its training data. You can stream progress, check status on running tasks, or fire and forget. The cost and wait time mean you'll want to be selective, but when you need something researched properly and don't want to do it yourself, it delivers.
npx skills add https://github.com/sanjay3290/ai-skills --skill deep-research