Stats
Actions
Tags
From godmode
Manages MLOps workflows: deploys models, handles versioning/A/B testing/drift detection/retraining/monitoring. Generates YAML configs and git commits. Supports flags like --deploy, --status, --drift.
How this command is triggered — by the user, by Claude, or both
Slash command
/godmode:mlopsgodmode/The summary Claude sees in its command listing — used to decide when to auto-load this command
# /godmode:mlops MLOps and model deployment management. Handles model serving infrastructure, inference optimization, model versioning, A/B testing, drift detection, and automated retraining. Supports TensorFlow Serving, Triton Inference Server, SageMaker, and custom serving solutions. ## Usage ## What It Does 1. Assesses model readiness (evaluation, bias, latency, size, error handling, compliance) 2. Configures serving infrastructure (TensorFlow Serving, Triton, SageMaker, FastAPI/Ray Serve) 3. Optimizes inference (FP16/INT8 quantization, ONNX, TensorRT, pruning, distillation, batchi...
MLOps and model deployment management. Handles model serving infrastructure, inference optimization, model versioning, A/B testing, drift detection, and automated retraining. Supports TensorFlow Serving, Triton Inference Server, SageMaker, and custom serving solutions.
/godmode:mlops # Interactive model deployment workflow
/godmode:mlops --status # Production monitoring dashboard
/godmode:mlops --deploy <model> # Deploy a specific model version
/godmode:mlops --promote # Promote canary to champion
/godmode:mlops --rollback # Rollback to previous champion
/godmode:mlops --drift # Run drift detection analysis
/godmode:mlops --retrain # Trigger retraining pipeline
/godmode:mlops --ab-test # Configure or check A/B test
/godmode:mlops --optimize # Run inference optimization benchmarks
/godmode:mlops --scale <replicas> # Scale serving infrastructure
/godmode:mlops --versions # Show model version registry
configs/mlops/<model>-serving.yamlconfigs/mlops/<model>-monitoring.yaml"mlops: <model> v<version> — <action> (<platform>)"Train (ml) → Readiness Check → Deploy Canary (5%) → A/B Test → Promote Champion
↓
Monitor → Drift Detection → Retrain
If deployed: /godmode:mlops --status to monitor health.
If drift detected: /godmode:ml to review retraining results.
If A/B test done: /godmode:mlops --promote or --rollback.
/godmode:mlops --deploy ticket-classifier-v3.2 # Deploy a model
/godmode:mlops --status # Check production health
/godmode:mlops --drift # Run drift analysis
/godmode:mlops --rollback # Emergency rollback
npx claudepluginhub arbazkhan971/godmode/build-ml-pipelineBuilds end-to-end ML pipeline from data ingestion, preprocessing, training, evaluation, to production deployment with MLOps, given problem description.
/shipAssesses deployment readiness of a trained model, generates standardized model card with 8 sections, and produces readiness decision (Ready/Conditionally/Not Ready).
/fal-deployDeploys custom ML models to fal.ai serverless infrastructure with GPU support. Generates fal.App Python code including setup, endpoints, scaling, dependencies, and deployment commands.
/deploy-modelAnalyzes context to execute AI/ML tasks: generates code with validation and error handling, provides metrics and insights, saves artifacts, and creates documentation.