mcpField
T
trade-hypothesis-ideator

trade-hypothesis-ideator

github.com/tradermontyOther3.4k3.3k installsUpdated 2d ago
Repository

About trade-hypothesis-ideator

Trade Hypothesis Ideator is a Python skill that turns structured trading observations and evidence into ranked, falsifiable hypothesis cards. It is intended for traders designing strategy experiments, and can optionally export pursue-rated ideas as strategy and metadata files.

Key features

  1. 01Normalize inputs and extract evidence
  2. 02Generate one to five hypothesis cards
  3. 03Critique and rank hypotheses
  4. 04Include experiment designs and kill criteria
  5. 05Export pursue cards to strategy files

Use cases

  1. 01Turn journal observations into testable ideas
  2. 02Design experiments before committing capital
  3. 03Rank candidate trading hypotheses
  4. 04Export selected ideas for strategy workflows

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/tradermonty/claude-trading-skills --skill trade-hypothesis-ideator

After installing, type/trade-hypothesis-ideatorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

requirements.txt
examples/
example_input.json
example_output.json
sample_input.json
prompts/
critique_prompt_template.md
developer_prompt_template.md
system_prompt.md
references/
evidence_quality_guide.md
hypothesis_types.md
schemas/
hypothesis_card.schema.json
input_bundle.schema.json
output_bundle.schema.json
raw_hypotheses.schema.json
scripts/
run_hypothesis_ideator.py
scripts/pipeline/
__init__.py
evidence_extractor.py
format_output.py
normalize.py
ranking.py
strategy_exporter.py
scripts/tests/
conftest.py
test_evidence_extractor.py
test_format_output.py
test_guardrails.py
test_normalize.py
test_ranking.py
test_strategy_exporter.py

Details

From the project README

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)

Workflow

  1. Receive input JSON bundle.
  2. Run pass 1 normalization + evidence extraction.
  3. Generate hypotheses with prompts:
    • prompts/system_prompt.md
    • prompts/developer_prompt_template.md (inject {{evidence_summary}})
  4. Critique hypotheses with prompts/critique_prompt_template.md.
  5. Run pass 2 ranking + output formatting + guardrails.
  6. Optionally export pursue hypotheses 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 criteria
  • strategy_<hypothesis_id>.yaml — (Optional) Edge-finder-compatible strategy export for pursue cards
  • metadata_<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

Comments

Markdown supported