trade-hypothesis-ideator

To generate falsifiable trading strategy hypotheses from market data, provide a structured JSON input bundle containing trade logs and journal snippets. The skill normalizes evidence and prompts for structured hypothesis generation based on your market observations.

You can rank trading strategy hypotheses by evaluating generated cards against defined criteria including evidence strength, mechanism clarity, feasibility, expected payoff, novelty, and test efficiency. The skill critiques and scores each hypothesis automatically.

Automating hypothesis testing for algorithmic trading workflows involves using Python and YAML to process structured input bundles, normalize market data evidence, and export validated strategy definitions compatible with trading platforms for backtesting.

Yes, you need numpy and pyyaml to run hypothesis generation for trading strategies. The skill also requires requests and jsonschema libraries to parse input bundles, validate hypotheses, and perform evidence extraction and text processing.

Yes, you can export ranked trading strategy hypotheses to strategy files compatible with trading platforms. The skill optionally generates exportable strategy definitions from evaluated and ranked hypothesis cards.

The trade-hypothesis-ideator skill accepts structured JSON input bundles for market analysis. These bundles should contain market data, trade logs, and journal snippets with evidence observations to trigger hypothesis generation and evaluation workflows.