@arize-ai

arize-link generates clickable deep links into arize ui artifacts (traces, spans, sessions, datasets, queues, evaluators, annotation configs) by collecting required ids, verifying base64 encoding, computing time windows, and substituting into url templates.

arize-trace exports and inspects LLM application traces and spans from Arize for debugging and observability. handles space/project resolution, span filtering, and security guardrails for untrusted user-generated content in exported data.

arize-ai-provider-integration manages crud operations on llm provider credentials stored within arize accounts, enabling evaluators and downstream features to invoke language models via standardized authentication patterns.

arize-compliance-audit scans ai apps against eu ai act, gdpr, nist ai rmf and other frameworks, producing tailored checklists and remediation guidance. outputs are advisory only and require legal review.

arize-prompt-optimization provides concepts and configuration reference for extracting and analyzing prompts from trace data, but lacks actionable procedures and concrete usage examples for the claimed optimization workflow.

phoenix-cli provides command-line access to llm observability and trace inspection, but the skill definition is incomplete, offering syntax examples without actionable procedures or error handling context.

phoenix-evals provides minimal scaffolding for building llm evaluators. the skill.md is incomplete, offering only a title and broad tagline without actionable procedure or decision logic.

Open-source AI observability platform for tracing, evaluating, and improving LLM applications with OpenTelemetry integration

Adds Arize AX tracing to an LLM application for the first time. Detects the stack, routes to the single matching integration doc, wires auto-instrumentation…

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to…

Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human…

Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks,…

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and…

Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the…