nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument evaluation metrics, quality scores, and feedback loops.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument evaluation metrics, quality scores, and feedback loops.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument safety checks, content filters, and guardrails for agent outputs.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument human approval workflows, feedback loops, and escalations.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Plan what to measure in AI agent systems using tiered approach.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument LLM API calls with proper spans, tokens, and latency.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument RAG retrieval, memory operations, and context management.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument multi-agent workflows, handoffs, and parent-child relationships.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Strategies for evaluating agents in production - sampling, baselines, and regression detection.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Track prompt versions, A/B test variants, and measure prompt performance.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument sessions, conversations, and multi-turn interactions.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Track token usage and costs across agents for budget management.
nexus-labs-automation/agent-observability
Skill Claude CodeCodex
Instrument agent tool executions with proper context and error handling.