OBSERVABILITY / Arize AI
Arize Instrumentation Health
Read-only audit of exported Arize spans for nine instrumentation defects, including missing token counts behind empty cost dashboards.
“Audits instrumentation health of existing Arize traces. Runs deterministic checks over a bounded span sample (orphaned/uncategorized/duplicate spans, flat structure, blank root I/O, unset status, missing token counts or children) and returns a ranked report. Use when the user asks why traces look empty/flat/broken, wants to verify instrumentation is healthy, find instrumentation issues, or why evals or token/cost dashboards show n/a or zero. To debug app behavior or errors, use arize-trace.”
01 / THE REASONING
Why this made the selection.
- The audit is read-only by default and treats exported span content as untrusted data, never following instructions found inside span attributes.
- Most checks need at least 20 traces and below that the file requires reporting insufficient data; references/checks.md gives each check a trigger and a guardrail that downgrades confidence.
02 / THE REVIEW RECORD
What we actually inspected.
Source review has boundaries.
A clear record is more useful than a “safe” badge.
Material inspected
- skills/arize-instrumentation-health/SKILL.md (workflow, reading exported spans, checks summary, minimum data, output)
- skills/arize-instrumentation-health/references/checks.md (span-kind classification, severity, checks 1 to 5)
- README.md (installation)
- LICENSE MIT, copyright 2025 Arize AI, Inc.
Our findings
- An unknown span kind is not treated as healthy for AI or workflow spans, per references/checks.md.
- Each finding is attributed to app instrumentation, an instrumentor limitation or the product UI.
Not established by this review
- The installer was not run, and the skill was not executed against a project or service. No spans were exported and no check was run.
- The arize-trace skill, checks 6 to 9 and the tests/ fixtures were not opened.
- Not executed: it was not installed or run.
The review applies to the material and revision named here. A newer upstream release can change its behavior.
03 / PUT IT TO WORK
Add a skill to your workflow.
DOCUMENTED COMMAND
npx skills add Arize-ai/arize-skills Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.
- The README's interactive form is npx skills add Arize-ai/arize-skills; its non-interactive form installs every skill with --skill "*" --yes. Install arize-trace alongside this skill.
- Neither command pins revision f92b15a001790a4894f5b17e34d3f8f3c5e13514. Compare the installed SKILL.md and references/checks.md with that revision.
Before you start
- Node.js and npm for the documented Skills installer
- The ax CLI and a configured Arize profile
04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
- Skill definition ↗Checked
https://github.com/Arize-ai/arize-skills/blob/f92b15a001790a4894f5b17e34d3f8f3c5e13514/skills/arize-instrumentation-health/SKILL.md
Supports: summary, upstreamDescription, whySelected, limitations, access, review
https://github.com/Arize-ai/arize-skills/blob/f92b15a001790a4894f5b17e34d3f8f3c5e13514/skills/arize-instrumentation-health/references/checks.md
Supports: whySelected, review
https://github.com/Arize-ai/arize-skills/blob/f92b15a001790a4894f5b17e34d3f8f3c5e13514/README.md
Supports: install, compatibility
- Repository licence ↗Checked
https://github.com/Arize-ai/arize-skills/blob/f92b15a001790a4894f5b17e34d3f8f3c5e13514/LICENSE
Supports: license
https://raw.githubusercontent.com/Arize-ai/arize-skills/f92b15a001790a4894f5b17e34d3f8f3c5e13514/skills/arize-instrumentation-health/SKILL.md
Supports: upstreamDescription, review.notTested, limitations
https://raw.githubusercontent.com/Arize-ai/arize-skills/f92b15a001790a4894f5b17e34d3f8f3c5e13514/README.md
Supports: install.command