What problem does it solve? Turning open questions about markets, technologies, competitors, or users into trustworthy, decision-ready research is slow and error-prone: claims go uncited, sources go stale, and raw reports are hard for downstream planning artifacts to consume. This Skill structures the entire research lifecycle so every claim carries a source, freshness window, and verification status. ## Core Features & Use Cases - Three research modes: Draft a deep-research prompt for external tools (ChatGPT, Gemini, Perplexity), Process a finished report into a cited summary, or Run native research with parallel web-search subagents. - Six built-in research packs: market, domain, technical, competitive, user-voice, and academic literature, each with prioritized dimensions, source craft, freshness bars, and two-source claim classes, plus a selection mode for choosing between candidates. - Verification and lifecycle: claims ledger with verified/disputed/unverified/overturned statuses, optional red-team passes, staleness tracking, and Refresh/Deepen workflows on existing run folders. - Use Case: Before committing to a technology stack, ask for a technical research run; the Skill holds a plan gate, fans out researcher subagents behind a research firewall, verifies load-bearing claims, and delivers research.md with an executive summary, source appendix, and staleness map. ## Quick Start Ask the assistant to run deep recon on your topic, for example: research the market for AI code-review tools to decide whether to enter it.
