What problem does it solve? Turning open-ended research questions into trustworthy, decision-ready findings is slow and error-prone: claims go uncited, sources go stale, and reports can't be reused. This Skill structures research around a specific decision, enforces citation and freshness discipline, and produces a canonical cited summary that downstream planning artifacts can consume directly. ## 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. - Typed research packs: Built-in packs for market, domain, technical, competitive, user-voice, and academic-literature research, each with prioritized dimensions, source craft, freshness bars, and two-source claim classes. - Verification and staleness tracking: A claims ledger in an append-only memlog, configurable validation levels (normal/high/max), optional red-team passes, and scripted staleness checks that flag claims needing re-verification. - Use Case: Before choosing between two vendors, ask for a selection-shaped competitive research run; the Skill screens candidates, scores them against your requirements frame, and delivers a weighted decision matrix with every contested cell cited. ## Quick Start Ask the assistant to run deep recon on your topic, for example: research the market for party management software to support our go-to-market decision.
