Use arize-toolkit CLI to manage Arize ML observability resources from the terminal: create, list, update, delete models, monitors, prompts, evaluators, dashboards, and spaces, plus handle profiles and admin tasks. Retrieve recent traces or by ID, inspect spans, analyze latency, tokens, costs, and export data for debugging LLM applications.
npx claudepluginhub duncankmckinnon/arize_toolkit --plugin arize-toolkitManage Arize platform resources using the arize_toolkit CLI. Use when users want to list, create, update, or delete Arize resources (models, monitors, prompts, evaluators, custom metrics, dashboards, spaces, organizations, users, or data imports) via the command line, configure CLI profiles, or perform platform administration tasks. Triggers on "list models", "create monitor", "arize_toolkit", "CLI", "arize cli", or any request to manage Arize platform resources from the terminal. Always use the "arize_toolkit" command, never "ax".
Retrieve and debug trace data from the Arize ML observability platform. Use when users want to list recent traces, look up a specific trace by trace ID, get all spans within a trace, analyze trace performance (latency, tokens, cost), or export trace data. Triggers on "list traces", "show traces", "look at traces", "get traces", "trace ID", "show me the spans", "see the spans", "dig into a trace", "trace detail", "trace performance", "what traces", "debug trace", "span lookup", "trace latency", "trace tokens", "trace cost", "export traces". Prefer this skill over arize-toolkit-cli when the request is specifically about traces or spans.
Developer workflows for contributing to the Arize Toolkit codebase
Share bugs, ideas, or general feedback.
Add Arize AX observability to LLM applications — auto-instrumentation, trace export, dataset management, experiment workflows, prompt optimization, and deep linking via the ax CLI.
Langfuse observability - query traces, debug exceptions, analyze sessions, manage prompts via MCP tools
Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.
Track and analyze AI experiments with a web dashboard and MCP tools
ML experiment tracking with metrics logging and run comparison