Loading...
Loading...
Found 82 Skills
Deploys infrastructure components via Helm charts on TrueFoundry. Supports any public or private OCI Helm chart including databases (Postgres, MongoDB, Redis), message brokers (Kafka, RabbitMQ), and vector databases (Qdrant, Milvus). Uses YAML manifests with `tfy apply`. Use when installing Helm charts or deploying infrastructure on TrueFoundry.
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
Event sourcing and CQRS expert for AI memory systemsUse when "event sourcing, event store, cqrs, nats jetstream, kafka events, event projection, replay events, event schema, event-sourcing, cqrs, nats, kafka, projections, event-driven, memory-architecture, ml-memory" mentioned.
Goldsky Turbo pipeline YAML reference — the authoritative source for field names, required vs optional fields, and valid values. Use whenever the user asks about specific YAML fields: what does `start_at: earliest` vs `latest` do, what fields does a postgres/clickhouse/kafka sink require, what is the `from:` field in a sink, how does `checkpoint` work, what's the syntax for `batch_size` or `primary_key`. Also use for validation errors like 'unknown field' or 'missing required field'. For interactive pipeline building end-to-end, use /turbo-builder instead.
Event-driven architecture patterns including message queues, pub/sub, event sourcing, CQRS, and sagas. Use for async messaging, distributed transactions, event stores, domain/integration events, data streaming, choreography/orchestration, or integrating with Kafka, RabbitMQ, Pulsar, SQS/SNS, or NATS.
Train ML models on Databricks. Use for: classification/regression/deep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod/@challenger aliases, batch scoring (spark_udf for plain models, fe.score_batch for feature-store-backed), custom PyFunc, custom ResponsesAgent (LangGraph + UC Function/Vector Search); UC feature tables + FeatureLookup + point-in-time joins + Lakebase online store; declarative Feature Views (create_feature, DeltaTableSource, RollingWindow/SlidingWindow/TumblingWindow, materialize_features, streaming Kafka features). NOT for: endpoint ops (databricks-model-serving), MLflow evaluation (databricks-mlflow-evaluation).
Diagnose ClickHouse INSERT performance, batch sizing, part creation patterns, and ingestion bottlenecks. Use for slow inserts and data pipeline issues.
Use when the user asks to document an implemented feature. Analyze the diff from the base branch, infer the feature boundary and name, and generate behavioral feature documentation under docs/features/.
Confluent integration. Manage data, records, and automate workflows. Use when the user wants to interact with Confluent data.
Automatically discover protocol skills when working with HTTP, TCP, UDP, QUIC, and network protocols