CANSLIM Screener applies William O’Neil’s growth stock method to a list of US stocks. A Python script pulls quote, earnings, price history and institutional data from the Financial Modeling Prep API, scores the seven components (current earnings, annual growth, new highs, supply and demand, leadership, institutional sponsorship and market direction) and combines them into a 0 to 100 composite.
When institutional ownership data is missing from FMP, the script scrapes the figure from Finviz. Reports list the market condition first and then the top candidates with a breakdown per component. The output is a screening aid and not investment advice.
What You Get
- A ranked list of stocks with composite scores and rating bands from Above Average to Exceptional+
- A breakdown of each component per stock, including multi-period relative strength
- A market condition summary that flags a bear market through the M component
- A JSON file for other tools and a Markdown report, both timestamped
Common Use Cases
- Screening a custom list of tickers against O’Neil’s growth criteria
- Checking which large caps rank highest on earnings growth and relative strength
- Using a different relative strength benchmark than the S&P 500
- Running a faster pass with the relative strength component disabled
What Makes It Unique
It covers all seven CANSLIM components, not a subset, and handles incomplete data openly: stocks with missing or invalid price closes for the relative strength calculation are marked unavailable and left out of the ranking, with dated data gaps in the report. The API budget is spelled out (about 7 FMP calls per stock plus 3 for market data), so a free-tier user can size a run with the max-candidates flag.
Under The Hood
The agent runs a Python script that calls the Financial Modeling Prep API over the network with the user’s API key (set in the FMP_API_KEY environment variable or passed on the command line). It also scrapes Finviz web pages for institutional ownership when FMP data is incomplete, with a short pause between requests. The skill asks the user to install requests, beautifulsoup4 and lxml with pip. It writes a JSON file and a Markdown report into an output folder, and the agent runs shell commands to find and read them.