arize-trace
INVOKE THIS SKILL when downloading or exporting Arize traces and spans. Covers exporting traces by ID, sessions by ID, and debugging LLM application issues using the ax CLI.
npx skills add majiayu000/claude-skill-registry --skill arize-trace --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Directs the agent to download or export Arize traces and spans, including exports by trace ID, span ID, and session ID, and to assist with debugging LLM issues via the ax CLI. It targets exporting traces by ID, sessions by ID, and provides guidance for exploratory exports and default output behavior.
How it works
- Use
ax spans exportto download individual spans orax traces exportto download complete traces. - For spans: can filter by
--trace-id,--span-id, or--session-idusing corresponding flags, and always set--output-dir .arize-tmp-tracesas default when exporting spans. - For traces: perform a two-phase approach (Phase 1: find spans with
--filterand limit; Phase 2: extract trace IDs and fetch all spans for those traces). - When exporting without specific IDs (exploratory export), start with a small sample using
-l 50and summarize findings before pulling more data. - Prerequisites include having the
axCLI, an API key, and a space ID; guidance is provided to verify environment and resolve common failures (API key, space ID, project). - Guidance examples show exact command syntax for exporting by trace ID, span ID, and session ID, and note that the
--output-dirdefaults to.arize-tmp-traces.
When to use it
Use when downloading or exporting Arize traces and spans, including debugging LLM applications with the ax CLI. Triggered for exporting by ID or during exploratory browsing of a project.
What it can touch
- Commands:
ax spans export,ax traces export. - Flags and parameters:
PROJECT,--trace-id,--span-id,--session-id,--filter,--space-id,--limit,--days,--start-time,--end-time,--output-dir,--stdout,--all,-p, --profile. - File outputs in directory:
--output-dir(default.arize-tmp-traces).
Caveats
- The provided guidance mentions environment checks and potential fallback to base64 project IDs if
401 Unauthorizedor limits occur when using a project name. - When using
--all, space-id is required and the--limitis ignored. - Arrow Flight networking notes indicate that Flight connects to
flight.arize.com:443and may require configuringax profilefields or environment variables for host/port/scheme.
# Arize Trace Skill ## Concepts - **Trace** = a tree of spans sharing a `context.trace_id`, rooted at a span with `parent_id = null` - **Span** = a single operation (LLM call, tool call, retriever, chain, agent) - **Session** = a group of traces sharing `attributes.session.id` (e.g., a multi-turn conversation) Use `ax spans export` to download individual spans, or `ax traces export` to download complete traces (all spans belonging to matching traces). **Resolving project for export:** The `PROJECT` positional argument accepts either a project name or a base64 project ID. When using a name, `--space-id` is required. If you hit limit errors or `401 Unauthorized` when using a project name, resolve it to a base64 ID: run `ax projects list --space-id SPACE_ID -l 100 -o json`, find the project by `name`, and use its `id` as `PROJECT`. **Exploratory export rule:** When exporting spans or traces **without** a specific `--trace-id`, `--span-id`, or `--session-id` (i.e., browsing/exploring a project), always start with `-l 50` to pull a small sample first. Summarize what you find, then pull more data only if the user asks or the task requires it. This avoids slow queries and overwhelming out
- Concepts
- Prerequisites
- Install ax
- Verify environment
- Export Spans: ax spans export
- By trace ID
- By span ID
- By session ID
- Flags
- Bulk export with --all
- Export Traces: ax traces export
- How it differs from ax spans export
- Filter Syntax Reference
- Common filterable columns
ax spans export PROJECT_ID --trace-id TRACE_ID --output-dir .arize-tmp-traces ax spans export PROJECT_ID --span-id SPAN_ID --output-dir .arize-tmp-traces ax spans export PROJECT_ID --session-id SESSION_ID --output-dir .arize-tmp-traces ax spans export PROJECT_ID --space-id SPACE_ID --filter "status_code = 'ERROR'" --all --output-dir .arize-tmp-traces Count matching spans without downloading them ax spans export PROJECT_ID --filter "status_code = 'ERROR'" -l 1 --stdout | jq 'length' If returns 1 (hit limit), run with --all If returns 0, no data matches -- check filter or expand --days Explore recent traces (start small with -l 50, pull more if needed) ax traces export PROJECT_ID -l 50 --output-dir .arize-tmp-traces
What does the arize-trace skill do?
INVOKE THIS SKILL when downloading or exporting Arize traces and spans. Covers exporting traces by ID, sessions by ID, and debugging LLM application issues using the ax CLI.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill arize-trace --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.