edge-strategy-designer

1# Edge Strategy Designer
2 
3## Overview
4 
5Translate concept-level hypotheses into concrete strategy draft specs.
6This skill sits after concept synthesis and before pipeline export validation.
7 
8## When to Use
9 
10- You have `edge_concepts.yaml` and need strategy candidates.
11- You want multiple variants (core/conservative/research-probe) per concept.
12- You want optional exportable ticket files for interface v1 families.
13 
14## Prerequisites
15 
16- Python 3.9+
17- `PyYAML`
18- `edge_concepts.yaml` produced by concept synthesis
19 
20## Output
21 
22- `strategy_drafts/*.yaml`
23- `strategy_drafts/run_manifest.json`
24- Optional `exportable_tickets/*.yaml` for downstream `export_candidate.py`
25 
26## Workflow
27 
281. Load `edge_concepts.yaml`.
292. Choose risk profile (`conservative`, `balanced`, `aggressive`).
303. Generate per-concept variants with hypothesis-type exit calibration.
314. Apply `HYPOTHESIS_EXIT_OVERRIDES` to adjust stop-loss, reward-to-risk, time-stop, and trailing-stop per hypothesis type (breakout, earnings_drift, panic_reversal, etc.).
325. Clamp reward-to-risk at `RR_FLOOR=1.5` to prevent C5 review failures.
336. Export v1-ready ticket YAML when applicable.
347. Hand off exportable tickets to `skills/edge-candidate-agent/scripts/export_candidate.py`.
35 
36## Quick Commands
37 
38Generate drafts only:
39 
40```bash
41python3 skills/edge-strategy-designer/scripts/design_strategy_drafts.py \
42  --concepts /tmp/edge-concepts/edge_concepts.yaml \
43  --output-dir /tmp/strategy-drafts \
44  --risk-profile balanced
45```
46…