Stockbee Setup Fluency Trainer keeps a JSONL model book of Stockbee-style Momentum Burst setups. It ingests candidates from the momentum burst screener, then updates 3-day and 5-day forward results with close return, MFE, MAE, stop-hit status and an outcome tag such as STRONG_WINNER or FAILED_STOP, and summarizes cohorts by rating, trigger and setup tags.
A second script, decision_replay.py, captures your enter, wait or pass decisions on vcp-screener candidates, then replays a blind sample later and reveals the price path. It scores rule adherence separately from the outcome. It is a study tool and does not give investment advice.
What You Get
- A durable state/stockbee/model_book.jsonl with setup fields, human labels and outcomes
- Ingest, update and summary reports in JSON and Markdown
- Outcome tags and cohort statistics with rule candidates to review as evidence prompts
- Write-once decision capture records, blind replay views and reveal reports with four quadrants of adherence and outcome
Common Use Cases
- Reviewing failed and missed momentum burst candidates
- Deciding which setup tags to promote, downgrade or filter
- A weekend blind replay of your own VCP enter, wait or pass decisions
What Makes It Unique
The blind replay keeps what you decided separate from what the price did afterwards, so a rule-compliant decision with a bad outcome is shown as exactly that. Cases captured late or with unverified prices are excluded and counted.
Under The Hood
Python scripts read screener JSON reports and offline OHLCV files and write JSONL, JSON and Markdown files into local state and reports folders. Outcome updates can instead call the FMP API over the network with a key from the environment, through a bundled client loaded only for live runs; blind replay uses the standard library only and needs no key. The SKILL.md has the model run the scripts from the shell.