machine-learning-ops

Plugin machine-learning-ops from marketplace agent-powerups in yeaight7/agent-powerups. Commands read from the repo's manifest — 1 month ago.

Skills (7)

• baseline-comparison-review

  Use when a new or more complex ML model is proposed and its value over simple baselines is not yet demonstrated -- before approving a new architecture or replacing an existing heuristic.

• dataset-split-review

  Use when reviewing how data is split into train/validation/test sets -- especially with time-series data, repeated entities (users, patients, sessions), or imbalanced targets.

• experiment-tracking-review

  Use when reviewing ML training code to confirm a run could be reconstructed later -- hyperparameters, metrics, data references, and artifacts logged, not just printed to stdout.

• ml-leakage-check

  Use when reviewing ML preprocessing or feature pipelines for target leakage -- validation metrics look suspiciously good, transformers are fitted before splitting, or features may not exist at prediction time.

• model-evaluation-reporting

  Use when writing or reviewing a model evaluation report -- accuracy is being quoted alone, or stakeholders need failure modes, segment performance, and business trade-offs made explicit.

• reproducible-training-runs

  Use when reviewing or modifying ML training scripts that must produce identical results across runs or machines -- runs with the "same" config differ, or a past result must be reconstructed exactly.

• training-pipeline-debugging

  Use when an ML training run fails or misbehaves -- NaN losses, out-of-memory errors, shape mismatches, or a model that cannot fit even a single batch.

Slash commands (4)

• /machine-learning-ops:evaluation-report

  Generate a comprehensive evaluation report for a trained model, highlighting performance, baselines, and subgroup metrics.

• /machine-learning-ops:experiment-preflight

  Audit an ML training script or pipeline for reproducibility, tracking, and basic hygiene before a long run.

• /machine-learning-ops:leakage-check

  Audit data preprocessing and splitting logic for target leakage.

• /machine-learning-ops:ml-run-review

Subagents (4)

• leakage-auditor

  Specialized agent for detecting data leakage, train-test contamination, and temporal leakage in ML pipelines.

• ml-experiment-reviewer

  Evaluates ML experiment setups for rigorous baseline comparisons, proper metric tracking, and reproducibility.

• model-evaluation-analyst

  Audits evaluation code to ensure test sets are clean, metrics are appropriate for the problem, and confidence intervals are computed.

• training-pipeline-debugger

  Diagnoses and resolves training loop bottlenecks, memory leaks, vanishing gradients, and hardware underutilization.

Similar plugins