Edge Strategy Designer
SkillCommerce & financeTurn an abstract trading edge concept into concrete strategy draft variants your AI can work with. Once a draft looks right, the skill can also produce an exportable ticket YAML so the idea moves to edge-candidate-agent for validation.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then describe your edge concept in plain terms and ask for draft variants. When you are happy with a draft, request a ticket YAML to hand it off to edge-candidate-agent.
Then ask your AI: use the Edge Strategy Designer skill
What your AI can do with it
- Convert abstract edge concepts into strategy draft variants
- Produce multiple draft variants from a single idea
- Generate exportable ticket YAMLs from strategy drafts
- Prepare tickets for edge-candidate-agent export and validation
What this skill tells your AI
The instructions your AI receives, as published by baggat236/ai-trading-skills in skills/edge-strategy-designer/SKILL.md and read by ahel’s review.
Overview
Translate concept-level hypotheses into concrete strategy draft specs. This skill sits after concept synthesis and before pipeline export validation.
When to Use
- You have
edge_concepts.yamland need strategy candidates. - You want multiple variants (core/conservative/research-probe) per concept.
- You want optional exportable ticket files for interface v1 families.
Prerequisites
- Python 3.9+
PyYAMLedge_concepts.yamlproduced by concept synthesis
Output
strategy_drafts/*.yamlstrategy_drafts/run_manifest.json- Optional
exportable_tickets/*.yamlfor downstreamexport_candidate.py
Workflow
- Load
edge_concepts.yaml. - Choose risk profile (
conservative,balanced,aggressive). - Generate per-concept variants with hypothesis-type exit calibration.
- Apply
HYPOTHESIS_EXIT_OVERRIDESto adjust stop-loss, reward-to-risk, time-stop, and trailing-stop per hypothesis type (breakout, earnings_drift, panic_reversal, etc.). - Clamp reward-to-risk at
RR_FLOOR=1.5to prevent C5 review failures. - Export v1-ready ticket YAML when applicable.
- Hand off exportable tickets to
skills/edge-candidate-agent/scripts/export_candidate.py.
Quick Commands
Generate drafts only:
python3 skills/edge-strategy-designer/scripts/design_strategy_drafts.py \
--concepts /tmp/edge-concepts/edge_concepts.yaml \
--output-dir /tmp/strategy-drafts \
--risk-profile balanced
Generate drafts + exportable tickets:
python3 skills/edge-strategy-designer/scripts/design_strategy_drafts.py \
--concepts /tmp/edge-concepts/edge_concepts.yaml \
--output-dir /tmp/strategy-drafts \
--exportable-tickets-dir /tmp/exportable-tickets \
--risk-profile conservative
Resources
skills/edge-strategy-designer/scripts/design_strategy_drafts.pyreferences/strategy_draft_schema.mdskills/edge-candidate-agent/scripts/export_candidate.py
Signals
- GitHub stars
- 122
- Forks
- 960
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
edge-strategy-designer- Source
- github.com/baggat236/ai-trading-skills