Stockbee 20% Study builds a durable event record of large US stock moves. A scan finds stocks that moved 20 percent up or down over a lookback window, with price and dollar-volume filters, using either the FMP API or an offline OHLCV JSON file.
Further commands enrich each event with a catalyst label and chart context, update 1, 3, 5, 10 and 20 day outcomes with MFE and MAE, summarize cohorts and back-fill history. It is a research and model-book workflow and does not produce buy or sell signals.
What You Get
- A JSON and Markdown daily report of 20 percent movers
- Enriched event records with catalyst and technical context labels
- Forward outcome updates with close return, MFE, MAE and continuation return
- Cohort summaries with rule candidates and an edge-hint YAML export
- A durable state/stockbee/20pct_study_events.jsonl file
Common Use Cases
- Running a daily study after the US close
- Back-filling years of movers from an OHLCV file to study what happened next
- Exporting edge hints to downstream strategy research skills
What Makes It Unique
It marks back-filled records for survivorship bias unless the data includes delisted symbols, and attaches overfitting controls and minimum sample sizes to its cohort rules. Offline mode works without any API key.
Under The Hood
A Python CLI reads offline OHLCV and catalyst JSON files, or calls the FMP stable API over the network using a key from the environment or a command-line option, through a bundled client loaded only for live runs. It writes JSON, Markdown and YAML reports and appends to a local JSONL state file. The SKILL.md has the model run these commands from the shell.