01
It starts by itself
daily error digest. Runs in Claude Code routine.
- ↻ daily error digest
0 7 * * *
A daily digest of failing traces.
Install the Arize Trace skill and make it a habit: follow https://gethabit.dev/skills/arize-ai/arize-trace.md
3K installs65 starsMIT licenceSource on GitHub ↗

Arize Trace
by arize-ai · 3K installs
The skill
The arize trace skill downloads and inspects Arize traces, spans and sessions with the ax CLI to see what an LLM app is doing, debug errors and find regressions.
Only when you ask.
The habit
A daily digest of failing traces.
↻ Runs by itselfdaily error digest
When does it start? How does it check its work? What does it remember?
Stops after one day's export per run, with at most one retry on an auth or project error.
Your agent gets the current UTC time and sets --start-time at least 12 hours back to cover index lag.
It runs ax traces export with a status_code ERROR filter into .arize-tmp-traces.
It states the span count and flags a result that hits the limit as likely truncated.
It reads attributes.error.type and attributes.error.message on each error span.
It writes the day's error types and trace ids to the digest and run log.
It writes only in its own folder and asks you before anything goes out.
Read both lists. If the left one sounds like you, the Arize Trace skill helps.
No. The skill treats span content as untrusted data for display and analysis only.
Time-scoped queries lag 6 to 12 hours, so a complete window starts at least 12 hours back.
Copy the prompt at the top into your agent. It installs the skill from arize-ai/arize-skills and sets up the habit. Or run npx skills add arize-ai/arize-skills --skill arize-trace.
Yes. It is published under MIT. Habit is free too.
Install the Arize Trace skill and make it a habit: follow https://gethabit.dev/skills/arize-ai/arize-trace.md
All arize-ai skills →More ops skills →
Works in
Made by arize-ai, published under MIT. Habit links to the original and never changes it. Is this your skill?