What problem does it solve? Turning open questions into trustworthy research is slow and error-prone: prompts for deep-research tools are hard to write well, finished reports are hard to distill, and claims often lack sources or freshness checks. This Skill structures the entire research lifecycle so every conclusion is cited, verified, and reusable by downstream workflows. ## Core Features & Use Cases - Three research modes: Draft a deep-research prompt for external tools (ChatGPT, Gemini, Perplexity), Process a finished report into a distilled cited summary, or Run native research through parallel web fan-out with subagents. - Typed research packs: Shipped packs for market, domain, technical, competitive, user-voice, and academic literature research, each with prioritized dimensions, source craft, freshness bars, and two-source verification classes, plus a select shape for choose-between decisions. - Verification and lifecycle: Claims ledger with verified/disputed/unverified/overturned statuses, optional red-team passes, staleness tracking, and Refresh/Deepen intents to update existing run folders. - Use Case: Ask it to research whether to enter a new market; it plans dimensions, fans out web research, verifies load-bearing claims, and produces 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 competitive landscape for my product idea and produce a cited decision-ready report.
