Arize Evaluator
Build and run LLM-as-judge evaluators on Arize via the ax CLI, with column mapping and monitoring.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 1336030
Its troubleshooting table flags a 1-2 hour eval-index lag that silently scores 0 spans, and that trigger-run needs bare-ISO timestamps with no trailing Z — exactly the operational gotchas a baseline guess at the ax CLI would get wrong.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Arize Evaluator does
Wraps the Arize `ax` CLI to create/version evaluators, wire them to projects or experiments via column mappings, and trigger backfill or continuous runs. Triggers on requests to create an evaluator, run an LLM judge, score hallucination/correctness/relevance, or set up continuous monitoring on Arize spans or experiments.
How to install Arize Evaluator
git clone https://github.com/github/awesome-copilot
cd awesome-copilot
mkdir -p ~/.claude/skills
cp -r skills/arize-evaluator ~/.claude/skills/arize-evaluator
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Arize Evaluator
-
/arize-evaluatorBuild and run LLM-as-judge evaluators on Arize via the ax CLI, with column mapping and monitoring.
It also activates on plain-language prompts like these:
-
Set up an LLM-as-judge evaluator with the ax CLI -
Run an eval over my traced LLM spans in Arize -
Create a trigger-run eval for my agent's outputs
Frequently asked questions
- Is the Arize Evaluator skill free?
- Yes. The skill itself is free from github/awesome-copilot. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Arize Evaluator work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Its troubleshooting table flags a 1-2 hour eval-index lag that silently scores 0 spans, and that trigger-run needs bare-ISO timestamps with no trailing Z — exactly the operational gotchas a baseline guess at the ax CLI would get wrong.
- What is the Arize Evaluator SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Arize Evaluator?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Arize Evaluator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.