root-signals
2 verified skills2 total stars
scorable-integration
Integrate Scorable LLM-as-a-Judge evaluators into applications with LLM interactions. Use when users want to add evaluation, guardrails, or quality monitoring to their LLM-powered applications. Also use when users mention Scorable, judges, LLM evaluation, or safeguarding applications.
testing1
scorable-otel-evaluation
Wire end-to-end OpenTelemetry-based tracing and evaluation for an LLM application — instrument the application with OTEL via OpenInference, ship traces to Scorable's OTLP endpoint, then use the Scorable CLI to query traces and create evaluation filters that auto-run an evaluator or judge against matching traces. Use when users want OTEL/OpenTelemetry tracing for their LLM app, want to monitor production LLM traffic, want auto-evaluation on a fraction of traffic, mention OTLP, OpenInference, Arize, pydantic-ai, openai-agents, LangChain, or "tracing my agent."
tools1