trade-hypothesis-ideator

Generate falsifiable trade strategy hypotheses with experiment designs and kill criteria.

1|Updated May 15, 2026
One-click install
npx skills add https://github.com/dnkrow/skill --skill trade-hypothesis-ideator-dnkrow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trade-hypothesis-ideator
Source: https://github.com/dnkrow/skill/tree/main/claude-global/trade-hypothesis-ideator
Command: npx skills add https://github.com/dnkrow/skill --skill trade-hypothesis-ideator-dnkrow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, yaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps you convert messy trading inputs (market context, trade logs, and journal snippets) into structured, falsifiable trade hypotheses you can actually test.

Core Features & Use Cases

  • Evidence-driven hypothesis generation: Produces 1–5 hypothesis cards by extracting winning/losing patterns and constraints from a normalized input bundle.
  • Critique and ranking with guardrails: Applies a critique pass, then ranks hypotheses into prioritized cards with explicit kill criteria and minimum viable experiments.
  • Optional strategy export (v1): Exports “pursue” hypotheses into strategy.yaml + metadata.json artifacts compatible with edge-finder-candidate/v1.
  • Use Case: When you refine an earnings setup (e.g., VWAP hold or breakout timing) you can generate hypothesis experiments that focus on objective invalidation rules rather than intuition.

Quick Start

Run pass 2 by providing a normalized input bundle JSON and a raw hypotheses JSON, then write ranked output artifacts to your chosen reports directory.

Frequently Asked Questions about trade-hypothesis-ideator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate falsifiable trade hypotheses from market context and trade logs?

You can generate falsifiable trade hypotheses by processing a normalized input bundle JSON containing market context, trade logs, and journal snippets to extract winning and losing patterns into prioritized, testable hypothesis cards.

What's the best way to structure trade notes for experiment design and data validation?

Structuring trade notes for experiment design requires a bundle JSON with defined objectives, constraints, market context, and performance inputs to satisfy schema-based validation and generate ranked recommendations.

Can I export trading strategy hypotheses into a YAML file for automated testing?

Yes, you can export prioritized trading hypotheses into strategy.yaml and metadata.json artifacts compatible with edge-finder-candidate/v1 for downstream automated testing workflows.

Do I need python3 and yaml to run hypothesis generation for trading strategies?

Yes, you need python3 and yaml dependencies installed in your environment to process the input bundle JSON, apply critique passes, and write the output strategy and metadata artifacts.

How does ranking and critique work when generating trade strategy hypotheses?

Ranking works by applying a critique pass to initially generated hypotheses, prioritizing them into 1–5 cards with explicit kill criteria and minimum viable experiments for objective invalidation.

When should I not use automated hypothesis generation for trading strategies?

You should avoid automated hypothesis generation when you lack a structured bundle JSON with objective, constraints, and market context, as schema-based validation guardrails require these inputs to produce reliable testable cards.