Edge Strategy Designer

interface:
  display_name: "Edge Strategy Designer"
  short_description: "Convert abstract concepts into strategy drafts"
  default_prompt: "Design concrete strategy draft variants from edge concepts and emit exportable tickets when v1-compatible."


# Strategy Draft Schema

`design_strategy_drafts.py` writes one YAML per concept variant.

```yaml
id: draft_edge_concept_breakout_behavior_riskon_core
as_of: "2026-02-20"
concept_id: edge_concept_breakout_behavior_riskon
variant: core
risk_profile: balanced
name: Participation-backed trend breakout (core)
hypothesis_type: breakout
mechanism_tag: behavior
regime: RiskOn
export_ready_v1: true
entry_family: pivot_breakout
entry:
  conditions:
    - close > high20_prev
    - rel_volume >= 1.5
  trend_filter:
    - price > sma_200
exit:
  stop_loss_pct: 0.07
  take_profit_rr: 3.0
  time_stop_days: 20
risk:
  position_sizing: fixed_risk
  risk_per_trade: 0.01
  max_positions: 5
validation_plan:
  period: 2016-01-01 to latest
  hold_days: [5, 20, 60]
  success_criteria:
    - expected_value_after_costs > 0
```

`risk_profile` is persisted in each draft for traceability of sizing/limits decisions.

## Export Ticket Output (Optional)

When `--exportable-tickets-dir` is provided, export-ready drafts produce minimal ticket YAML files compatible with `skills/edge-candidate-agent/scripts/export_candidate.py`.


#!/usr/bin/env python3
"""Design strategy drafts from abstract edge concepts."""

from __future__ import annotations

import argparse
import json
from datetime import datetime, timezone
from pathlib import Path
from typing import Any

import yaml

DEFAULT_EXPORTABLE_FAMILIES = {
    "pivot_breakout",
    "gap_up_continuation",
    "panic_reversal",
    "news_reaction",
}

ENTRY_TEMPLATE = {
    "pivot_breakout": {
        "conditions": [
            "close > high20_prev",
            "rel_volume >= 1.5",
            "close > ma50 > ma200",
        ],
        "trend_filter": [
            "price > sma_200",
            "price > sma_50",
            "sma_50 > sma_200",
        ],
    },
    "gap_up_continuation": {
        "conditions": [
            "gap_up_detected",
            "close_above_gap_day_high",
            "volume > 2.0 * avg_volume_50",
        ],
        "trend_filter": [
            "price > sma_200",
            "price > sma_50",
            "sma_50 > sma_200",
        ],
    },
    "panic_reversal": {
        "conditions": [
            "ret_1d <= -0.07",
            "rel_volume >= 1.8",
            "close > 0.85 * ma200",
        ],
        "trend_filter": [
            "price > sma_200 * 0.85",
            "no_fresh_breakdown_below_ma200",
        ],
    },
    "news_reaction": {
        "conditions": [
            "abs_reaction_1d >= 0.06",
            "rel_volume >= 2.0",
            "close_pos >= 0.4",
        ],
        "trend_filter": [
            "validate_follow_through_d2",
            "volume_confirmation_present",
        ],
    },
}

RISK_PROFILES = {
    "conservative": {
        "risk_per_trade": 0.005,
        "max_positions": 3,
        "stop_loss_pct": 0.05,
        "take_profit_rr": 2.2,
    },
    "balanced": {
        "risk_per_trade": 0.01,
        "max_positions": 5,
        "stop_loss_pct": 0.07,
        "take_profit_rr": 3.0,
    },
    "aggressive": {
        "risk_per_trade": 0.015,
        "max_positions": 7,
        "stop_loss_pct": 0.09,
        "take_profit_rr": 3.5,
    },
}

HYPOTHESIS_EXIT_OVERRIDES: dict[str, dict[str, Any]] = {
    "breakout": {
        "stop_loss_multiplier": 0.85,
        "rr_adjustment": 0.0,
        "time_stop_days": 20,
        "trailing_stop_hint": "ATR trailing recommended",
    },
    "futures_trigger": {
        "stop_loss_multiplier": 0.85,
        "rr_adjustment": 0.0,
        "time_stop_days": 20,
        "trailing_stop_hint": "ATR trailing recommended",
    },
    "earnings_drift": {
        "stop_loss_multiplier": 1.15,
        "rr_adjustment": -0.5,
        "time_stop_days": 10,
        "trailing_stop