Agent skill · research science · tradermonty
trade-hypothesis-ideator
Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets. Use when you have a structured input bundle and want ranked hypothesis cards with experiment designs, kill criteria, and optional strategy.yaml export compatible with edge-finder-candidate/v1.
Why this skill is useful
Adds executable scripts for generating and ranking trade hypotheses from structured market data that the AI cannot generate on its own.
What it needs
Requires python, pyyaml installed locally. About 1k tokens when loaded. Last updated 2026-08-06. 2,581 stars on the source repository.
What this skill does
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: tradelog, journalsnippets, marketdata, observations Python 3.9+ with pyyaml installed No external API keys required (pure calculation skill) Workflow 1. Receive input JSON bundle. 2. Run pass 1 normalization + evidence extraction. 3. Generate hypotheses with prompts: prompts/systemprompt.md prompts/developerprompttemplate.md (inject {{evidencesummary}}) 4. Critique hypotheses with prompts/critiqueprompttemplate.md. 5. Run pass 2 ranking + output formatting + guardrails. 6. Optionally export pursue hypotheses via Step H strategy exporter. Scripts Pass 1 (evidence summary): Pass 2 (rank + output + optional export): Output hypothesiscards<date>.json — Ranked hypothesis cards with verdicts (pursue, revise, discard) hypothesiscards<date>.md — Human-readable summary with experiment designs and kill criteria strategy<hypothesisid>.yaml — (Optional) Edge-finder-compatible strategy export for pursue cards metadata<hypothesisid>.json — (Optional) Provenance metadata for exported strategies Resources references/hypothesistypes.md — Taxonomy of hypothesis patterns (mean-reversion, momentum, event-driven, etc.) references/evidencequalityguide.md — Criteria for rating evidence strength and sample size requirements
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills tradermonty/trade-hypothesis-ideator