Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.

Edge Pipeline Orchestrator Coordinate all edge research stages into a single automated pipeline run. When to Use Run the full edge pipeline from tickets (or OHLCV) to exported strategies Resume a partially completed pipeline from the drafts stage Review and revise existing strategy drafts with feedback loop Dry run the pipeline to preview results without exporting Workflow 1. Load pipeline configuration from CLI arguments 2. Run auto detect stage if from ohlcv is provided (generates tickets from raw OHLCV data) 3. Run hints stage to extract edge hints from market summary and anomalies 4. Run concepts stage to synthesize abstract edge concepts from tickets and hints 5. Run drafts stage to design strategy drafts from concepts 6. Run review revision feedback loop: Review all drafts (max 2 iterations) PASS verdicts accumulated; REJECT verdicts accumulated REVISE verdicts trigger apply revisions and re review Remaining REVISE after max iterations downgraded to research probe 7. Export eligible drafts (PASS + export ready v1 + exportable entry family) 8. Write pipeline run manifest.json with full execution trace CLI Usage Output All artifacts are written to output dir : Claude Code LLM Augmented Workflow Run the LLM augmented pipeline entirely within Claude Code: 1. Run auto detect to produce market summary.json + anomalies.json 2. Claude Code analyzes data and generates edge hints 3. Save hints to a YAML file: 4. Run orchestrator with llm ideas file and promote hints : Optional Flags as of YYYY MM DD — forwarded to hints stage for date filtering strict export — export eligible drafts with any warn finding get REVISE instead of PASS max synthetic ratio N — cap synthetic tickets to N × real ticket count (floor: 3) overlap threshold F — condition overlap threshold for concept deduplication (default: 0.75) no dedup — disable concept deduplication Note: llm ideas file and promote hints are effective only during full pipeline runs. resume from drafts and review only skip hints/concepts stages, so these flags are ignored. Resources references/pipeline flow.md — Pipeline stages, data contracts, and architecture references/revision loop rules.md — Review revision feedback loop rules and heuristics

edge-pipeline-orchestrator