nats-jetstream-claude-skills

Use this skill whenever users are designing, modeling, or writing code for NATS JetStream — including stream configuration, subject namespace design, consumer types (pull vs push), ack policies, retention policies, delivery guarantees, messaging patterns (fanout, work queue, request-reply), idempotent publishing, exactly-once semantics, or JetStream code examples in Go, JavaScript, or Python. Use this skill even when the user doesn't say "JetStream" explicitly — if they're asking how to build a message queue, event stream, or worker system on NATS, this skill applies. Do NOT use for deployment/clustering/Kubernetes questions (use jetstream-deployment) or troubleshooting/monitoring (use jetstream-operations).

Use this skill whenever users need to deploy, configure, or secure a NATS JetStream server or cluster — including nats-server.conf configuration, Kubernetes Helm charts, StatefulSets, Docker Compose, multi-region super-clusters with gateways, leaf nodes, TLS/mTLS setup, NKey/JWT authentication, subject-level authorization, or infrastructure sizing. Use this skill even for general "how do I run NATS in production?" questions. Do NOT use for stream/consumer design or code examples (use jetstream-architecture) or troubleshooting/monitoring (use jetstream-operations).

Use this skill whenever users are operating, troubleshooting, or monitoring a running NATS JetStream system — including diagnosing consumer lag, messages not delivering, stream-full errors, performance tuning, Prometheus metrics, Grafana dashboards, alerting rules, JetStream advisory subjects, nats CLI usage, cluster health and leader election issues, or client connection/reconnection problems. Use this skill when something is broken or slow, or when the user wants to observe their system. Do NOT use for designing new streams/consumers (use jetstream-architecture) or deploying/configuring infrastructure (use jetstream-deployment).

Use this skill whenever users are building AI agents that communicate, register, or coordinate over NATS using the Synadia Agent Protocol or the Synadia Agents SDK — including exposing an agent as a discoverable NATS service, building a meta-agent/orchestrator that discovers and prompts other agents, fanning a prompt out to a fleet of agents and merging replies, streaming agent responses over NATS, human-in-the-loop mid-stream queries, agent heartbeats/liveness, or making a Go/other-language agent protocol-compliant. Triggers on the npm packages @synadia-ai/agents and @synadia-ai/agent-service, the PyPI packages synadia-ai-agents and synadia-ai-agent-service, the `agents.*` subject namespace, or phrases like "agent fabric", "agent discovery over NATS", "orchestrate a fleet of agents", "A2A on NATS", or "register my agent as a NATS service". Use this even when the user doesn't name Synadia — if they want heterogeneous AI agents to find and talk to each other over NATS, this skill applies. Do NOT use for plain