Arize Trace Skill
技能 已验证 活跃Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting traces by ID, spans by ID, sessions by ID, and root-cause investigation using the ax CLI. Use when the user wants to look at existing trace data, see what their LLM app is doing, export traces, download spans, investigate errors, or analyze behavior regressions.
To enable users to inspect and debug their LLM applications by exporting and analyzing trace and span data from Arize.
功能
- Export Arize traces by ID
- Export Arize spans by ID
- Export Arize sessions by ID
- Investigate root causes using ax CLI
- Filter trace and span data
使用场景
- Looking at existing trace data
- Seeing what an LLM app is doing
- Exporting traces for offline analysis
- Investigating runtime errors
- Analyzing behavior regressions
非目标
- Modifying Arize data
- Real-time monitoring of live traces
- Configuring Arize itself
工作流
- Identify the need to inspect Arize traces/spans.
- Determine the appropriate `ax` command (e.g., `spans export`, `traces export`) based on the data needed.
- Construct the command with necessary arguments (PROJECT, IDs, filters, time ranges).
- Execute the command, handling authentication and profile setup as needed.
- Analyze the exported JSON data for debugging or understanding application behavior.
先决条件
- Requires the ax CLI
- Requires a configured Arize profile
安装
npx skills add github/awesome-copilot通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Arize Link
99Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Produces clickable URLs for sharing Arize resources with team members. Use when the user wants to link to or open a trace, span, session, dataset, evaluator, or annotation config in the Arize UI.
LangSmith Observability
99LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Arize Instrumentation
95Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation after user confirmation. Use when the user wants to instrument their app, add tracing from scratch, set up LLM observability, integrate OpenTelemetry or openinference, or get started with Arize tracing.
Arize Prompt Optimization
100Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
Arize Experiment
100Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.
Arize Evaluator
100Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.