FinViz Screener translates requests such as “oversold large caps with high ROE” or “高配当で成長している小型株” into FinViz filter codes, themes and sub-themes. It shows the chosen filters in a table for you to confirm, then builds the screener URL.
A Python script opens the URL in Chrome, with OS-specific fallbacks, or only prints it. The public screener needs no key, and FINVIZ Elite mode is detected from an environment variable. The skill builds a screen from criteria you state and gives no investment advice.
What You Get
- A FinViz screener URL built from your criteria
- A confirmation table listing each filter code and its meaning
- The URL opened in Chrome, or printed when you ask for URL-only output
- Suggested next steps such as changing the view or sort order
Common Use Cases
- Describing a screen in everyday words and getting the matching FinViz page
- Starting from a recipe such as dividend growth or a trend template and refining it
- Screening by theme and sub-theme, for example AI cloud and compute
What Makes It Unique
It carries a bilingual concept table and a 142-code industry list, supports range tokens such as fa_div_3to8, and validates every filter strictly to prevent URL injection. Theme and sub-theme tokens go through their own arguments. The recipes are written from repeated use and teach an iterative way to tighten or relax a screen.
Under The Hood
The agent reads reference files, then runs a Python script that uses only the standard library to build the URL. It opens the URL in a local Chrome browser or prints it. If the FINVIZ_API_KEY environment variable is set, the script switches to Elite mode, and the screener page itself is fetched by your browser. The agent runs shell commands and may launch a browser. It writes no files.