Theme Detector finds which market themes are moving, such as AI or clean energy, by combining momentum, volume, uptrend ratio and breadth across industries. Each theme gets a heat score from 0 to 100, a lifecycle stage from Emerging to Exhausting, and a confidence level.
It runs a Python orchestrator against FINVIZ, in Elite mode with a key or by scraping public pages, and can add FMP valuation data, daily stock scan hits and a history file. A web search step then checks the narrative for the top themes. The output describes market conditions and is not investment advice.
What You Get
- A ranked list of bullish and bearish themes with heat scores and lifecycle stage
- A confidence rating per theme, capped at medium from data alone and raised only by narrative confirmation
- Representative stocks and leader candidates for each theme with the evidence behind them
- Theme history and acceleration metrics when you pass a history file
Common Use Cases
- Asking which themes are hot or cold this week before planning research
- Spotting crowded late-stage themes against emerging ones
- Checking whether a theme such as defense or clean energy still has momentum
What Makes It Unique
It scores three separate things, heat, lifecycle maturity and confidence, so a strong but exhausted theme reads differently from an early one. Bearish themes are scored the same way as bullish ones, and optional stock-leadership and basket-match evidence show how specific each theme match is.
Under The Hood
The skill runs a Python script from the shell. The script fetches industry and stock data from FINVIZ, either through the Elite export with an API key or by scraping public pages at a slow rate, and can call the Financial Modeling Prep API for valuation data when a key is set. It also uses market data libraries for price history. Reports are written as files in a reports folder. After the script finishes, the agent uses web search to confirm the narrative for the top themes. API keys are read from environment variables or command flags.