johnamcruz

Train Policy — Development skill for Claude Code

Development community

Sweep, retrain, and ship a prop-challenge policy (MaskablePPO) from a JSON config family; promote only with the user's go-ahead.

How to install Train Policy

Installs to ~/.claude/skills/johnamcruz-futures-trading-harness-train-policy/SKILL.md

Terminal

mkdir -p ~/.claude/skills/johnamcruz-futures-trading-harness-train-policy && curl -fsSL https://raw.githubusercontent.com/johnamcruz/futures-trading-harness/HEAD/commands/train-policy.md -o ~/.claude/skills/johnamcruz-futures-trading-harness-train-policy/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Train Policy does

description: Sweep, retrain, and ship a prop-challenge policy (MaskablePPO) from a JSON config family; promote only with the user's go-ahead. argument-hint: "_v1>"

Use the `policy-training` skill for: $ARGUMENTS

Alternatives in Development

Value Prop Statements — Generate value prop statements for marketing, sales, and onboarding 7.8k ★
Scipilot Figure Skill — SciPilot Skills family - Publication-grade scientific figure copilot for Claude Code 2k ★
Backpass — You don't write AGENTS.md 1.1k ★