Trade Hypothesis Ideator

This converts your messy trade journal notes and log files into falsifiable hypothesis cards with built-in kill criteria and experiment designs. You feed it a JSON bundle of observations, it runs two passes (evidence extraction, then critique and ranking), and spits out ranked cards marked pursue, revise, or discard. The workflow is unusually structured for a qualitative-to-quantitative bridge: it uses templated prompts, normalizes your evidence, and optionally exports pursue cards as strategy.yaml files compatible with edge-finder tooling. The honesty here is refreshing. It assumes you already have evidence and won't manufacture edge ideas from nothing, which is exactly the guardrail you want before risking capital on half-baked pattern hunches.

skills.sh installs: 3.4K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tradermonty/claude-trading-skills --skill trade-hypothesis-ideator --agent claude-code

Installs into .claude/skills of the current project.

Files

Trade Hypothesis Ideator

Generate 1-5 structured hypothesis cards from a normalized input bundle, critique and rank them, then optionally export pursue cards into strategy.yaml + metadata.json artifacts.

When to Use

After gathering trade logs, journal entries, or market observations that suggest a potential edge
When you have a structured input bundle (JSON) with evidence snippets and want falsifiable hypotheses
To bridge qualitative observations into quantitative experiment designs
Before committing capital to validate a new strategy idea with kill criteria

Prerequisites

Input JSON bundle with one or more of: trade_log, journal_snippets, market_data, observations
Python 3.9+ with pyyaml installed
No external API keys required (pure calculation skill)