edge-pipeline-orchestrator

Automating trading strategy research requires orchestrating multi-stage pipelines from market observations to validated exports. This Skill coordinates candidate detection, hint extraction, concept synthesis, strategy drafting, review cycles, revision handling, and export stages through structured subprocess execution.

Strategy quality control runs iterative PASS, REVISE, and REJECT review workflows with automated revision heuristics and downgrade handling. This ensures candidate strategies meet research standards before generating execution traces and export metadata.

Yes, pipeline orchestration requires YAML data contracts, subprocess execution, and PyYAML parsing to coordinate multi-stage research operations. You also need pipeline scripts and optionally OHLCV data or existing research tickets to generate validated strategy candidates.

Generating export-ready strategy artifacts involves coordinating automated movement from market signals and candidate ideas to reviewed outputs. This pipeline approach manages the transition from raw quantitative observations to validated strategy candidates with execution traces.

Automated pipeline orchestration is not suitable for isolated, single-step quantitative analysis or workflows lacking structured review cycles. It requires defined multi-stage research operations and standardized YAML data contracts to function properly.

Yes, you can provide existing research tickets instead of raw OHLCV market data. The pipeline accepts both inputs to process candidate detection, concept synthesis, and strategy drafting into validated strategy candidates with export metadata.