Trade Hypothesis Ideator
FreeGenerate and rank trade strategy hypotheses from data.
Free · Opens the source repo
What Trade Hypothesis Ideator does
The Trade Hypothesis Ideator skill is designed for traders and analysts looking to derive actionable insights from their market data, trade logs, and journal entries. By processing structured input bundles, this skill generates a set of falsifiable hypotheses that can guide trading strategies. The output includes ranked hypothesis cards that detail experiment designs and criteria for success or failure, enabling users to make informed decisions before committing capital.
To utilize the skill, users must provide a JSON input bundle containing relevant evidence such as trade logs, market observations, or journal snippets. The skill processes this input through a series of normalization and evidence extraction steps, followed by hypothesis generation and critique. The final output not only ranks the hypotheses but also allows for optional exports into a format compatible with other trading tools, facilitating seamless integration into existing workflows.
This skill is particularly useful for traders who have qualitative insights but need to translate them into quantifiable strategies. It helps bridge the gap between subjective observations and objective testing, making it easier to validate new trading ideas. The structured output ensures that users have a clear path to follow when testing their hypotheses, including specific kill criteria that define when to abandon a strategy.
Overall, the Trade Hypothesis Ideator is an essential tool for those who want to enhance their trading strategies through data-driven insights and systematic experimentation.
When to use it
Use this skill after compiling evidence from trades or market observations to formulate testable hypotheses.
When not to use it
This skill is not suitable for unstructured data or when immediate trading decisions are required without hypothesis testing.
What you can build with it
Formulating New Trading Strategies
After analyzing recent trade logs, users can input their findings to generate and rank new trading hypotheses.
Validating Market Insights
Traders can use this skill to transform qualitative market observations into structured, testable hypotheses.
Preparing for Capital Allocation
Before investing in a new strategy, users can create hypotheses with clear kill criteria to minimize risk.
How to install Trade Hypothesis Ideator
View source1. Install with the skills CLI
npx skills add tradermonty/claude-trading-skills/trade-hypothesis-ideator --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by tradermontyTrade 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
pyyamlinstalled - No external API keys required (pure calculation skill)
Workflow
- Receive input JSON bundle.
- Run pass 1 normalization + evidence extraction.
- Generate hypotheses with prompts:
prompts/system_prompt.mdprompts/developer_prompt_template.md(inject{{evidence_summary}})
- Critique hypotheses with
prompts/critique_prompt_template.md. - Run pass 2 ranking + output formatting + guardrails.
- Optionally export
pursuehypotheses via Step H strategy exporter.
Scripts
- Pass 1 (evidence summary):
python3 skills/trade-hypothesis-ideator/scripts/run_hypothesis_ideator.py \
--input skills/trade-hypothesis-ideator/examples/example_input.json \
--output-dir reports/
- Pass 2 (rank + output + optional export):
python3 skills/trade-hypothesis-ideator/scripts/run_hypothesis_ideator.py \
--input skills/trade-hypothesis-ideator/examples/example_input.json \
--hypotheses reports/raw_hypotheses.json \
--output-dir reports/ \
--export-strategies
Output
hypothesis_cards_<date>.json— Ranked hypothesis cards with verdicts (pursue,revise,discard)hypothesis_cards_<date>.md— Human-readable summary with experiment designs and kill criteriastrategy_<hypothesis_id>.yaml— (Optional) Edge-finder-compatible strategy export forpursuecardsmetadata_<hypothesis_id>.json— (Optional) Provenance metadata for exported strategies
Resources
references/hypothesis_types.md— Taxonomy of hypothesis patterns (mean-reversion, momentum, event-driven, etc.)references/evidence_quality_guide.md— Criteria for rating evidence strength and sample size requirements
Frequently asked questions about Trade Hypothesis Ideator
Similar skills
Spring Boot Testing
Master testing techniques for Spring Boot 4 applications.
GitHub Issues
Manage GitHub issues efficiently with MCP tools.
Geofeed Tuner
Optimize your IP geolocation feeds in CSV format.
Batch Files
Master Windows batch scripting for automation and task management.
Adobe Illustrator Scripting
Automate your Illustrator workflows with ExtendScript.
Plugin Structure
Create and organize Claude Code plugins effectively.