Arize Trace

Downloads and inspects Arize traces using their ax CLI so you can debug LLM apps or investigate what went wrong at runtime. Export spans by trace ID, session ID, or arbitrary filters, then analyze the JSON output to understand chains of LLM calls, tool invocations, and retrieval steps. The bulk export mode with `--all` handles large traces that exceed the 500-span default cap. One sharp edge: results come back in arbitrary order, not by recency, so you need to pass `--start-time` explicitly if you want recent data. Useful when you're staring at error logs and need to reconstruct what your agent actually did.

Install to Claude Code

npx -y skills add github/awesome-copilot --skill arize-trace --agent claude-code