Skip to main content
Skills are Driven’s pre-built investing workflows. Each one packages an analytical framework, a set of data sources, a sequence of steps, and quality checks, so the analysis is consistent and auditable rather than improvised. This section documents each built-in Skill: what it does, when to reach for it, the data it draws on, and how to get the best results. A Skill is not a prompt. It is a repeatable capability built on a specific, citable framework, and it runs as real code. The Skills below are built in, but they are not the limit: you can build your own Skills to capture the workflows and frameworks you rely on. For the concept behind Skills and the two ways to invoke them, see Skills.

The catalog

SkillUse it for
Deep ResearchMulti-source research on a company, sector, or theme with cited evidence and an exportable report
Market PulseA fast read on what the market is doing right now
Sector RadarScanning a sector for leaders, laggards, and what’s moving
Stock ScreenerFinding stocks that match fundamental, technical, or flow criteria
Stock AnalysisA balanced, structured analysis of one company
Competitor AnalysisComparing a company against its peers
Valuation MatrixStructured valuation with cross-checks against peers and guidance
Smart MoneyTracking institutional holdings, insider activity, and capital flows
Portfolio MonitorChecking the health, concentration, and risk of your holdings

How Driven picks a Skill

By default, Driven reads your question and routes it to the right Skill automatically. You do not need to name the Skill. If you ask to value a company, it runs the valuation workflow; if you describe screening criteria, it runs the screener. You can also invoke any Skill explicitly through the menu or command line when you want a specific workflow or want to override the automatic choice. See Skill routing logic for how selection works.

Getting better results from any Skill

Three habits improve the output of every Skill:
  1. Be specific. “Analyze NVDA’s data center margins and the risks to them” beats “tell me about NVDA.”
  2. Ask for evidence. Request sources, assumptions, and flagged data gaps so you can audit the answer.
  3. Iterate in place. Push back in the same conversation: ask for the bear case, ask it to date claims, ask it to tighten scope.