ML
ml-backtest-dataset
Codex-local skill bundle for ML inference, dataset scripts, backtests, and advisory-only model boundaries.
Install
mkdir -p .claude/skills/ml-backtest-dataset && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13573" && unzip -o skill.zip -d .claude/skills/ml-backtest-dataset && rm skill.zipInstalls to .claude/skills/ml-backtest-dataset
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Codex-local skill bundle for ML inference, dataset scripts, backtests, and advisory-only model boundaries.106 charsno explicit “when” trigger
About this skill
ML Backtest Dataset
This is a Codex-local skill bundle, not a guaranteed auto-discovered official Codex skill.
Rules
- Scout first: map model inference code, dataset builders, feature generation, backtest scripts, stored artifacts, and tests.
- Keep ML output advisory unless a future explicitly approved task changes that product boundary.
- Avoid training/validation leakage and document any temporal split assumptions.
- Do not mutate production data or overwrite model artifacts without explicit user approval.
- Backtest evidence must include data range, assumptions, and limitations.
- Preserve risk-policy and paper-trading guardrails around predictions.
Evidence
- Dataset and feature paths inspected.
- Inference/backtest entrypoints identified.
- Advisory-only boundary preserved.
- Validation or backtest command proposed or run.