Edge Candidate Agent turns end-of-day OHLCV observations, anomalies and optional hints into reproducible research tickets for US equity long-side ideas. It then exports the exportable ones as a strategy.yaml and a metadata.json that match the edge-finder-candidate/v1 interface of a separate trade-strategy-pipeline repository.
Three Python scripts detect candidates, export them and validate them against the interface and the pipeline’s schema rules. In the split edge workflow it handles the final export and validation stage. It prepares research specs and gives no investment advice.
What You Get
- A strategies/<candidate_id>/ folder with strategy.yaml and metadata.json for each exportable ticket
- Daily detection files: daily_report.md, market_summary.json, anomalies.json and watchlist.csv
- Exportable and research-only ticket YAML files
- A pass or fail result with reasons from the interface validator
Common Use Cases
- Running a daily scan of end-of-day data to list new candidate ideas
- Converting a written research ticket into files a backtest pipeline accepts
- Checking a candidate against the v1 interface before a dry run
What Makes It Unique
It is built around a fixed interface contract and refuses candidates that break it: schema bounds, a folder name that differs from the id, empty conditions and missing interface metadata. The export rules limit v1 to two supported entry families and mark everything else research-only. It pairs with four sibling skills that cover the earlier stages.
Under The Hood
The agent runs Python scripts from the skill folder. Auto-detection reads a local OHLCV file and an optional hints file, and writes report and ticket files into an output directory. The export script writes candidate folders into the strategies directory of another repository. When you pass a pipeline root, the validator imports that repository’s schema code, and the agent may run uv there. An optional external command can supply ideas. The skill needs PyYAML and the target pipeline checkout.