
Arize Evaluator
Fix Arize ax CLI profile and API key setup so evaluation and observability workflows can authenticate before running eval jobs.
Overview
arize-evaluator is an agent skill most often used in Build (also Operate errors, Ship testing) that configures Arize ax CLI profiles and API keys so evaluation tooling can authenticate.
Install
npx skills add https://github.com/arize-ai/arize-skills --skill arize-evaluatorWhat is this skill?
- Inspect current ax profile state with ax profiles show before changing config
- Patch-only updates via ax profiles update preserving unrelated fields
- API keys referenced through ARIZE_API_KEY env var—never raw keys on CLI flags
- Region correction for wrong endpoint (e.g. us-east-1b) without rotating secrets
- Reactive use on 401, missing profile, or misconfigured region—not proactive busywork
Adoption & trust: 811 installs on skills.sh; 31 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent or terminal cannot run Arize ax eval commands because the profile is missing, the API key is unset, or you get 401 Unauthorized with the wrong region.
Who is it for?
Indie builders using Arize ax in the terminal who need a minimal, secret-safe profile fix after auth errors.
Skip if: Teams defining eval rubrics, datasets, or production dashboards without any ax CLI authentication problem.
When should I use this skill?
Authentication fails for ax (401, missing profile, missing API key) or a profile has incorrect API key or region—do not run these checks proactively.
What do I get? / Deliverables
After the skill runs, ax profiles show reflects a valid profile with API key via ARIZE_API_KEY and correct region, unblocking evaluator and observability CLI workflows.
- Working ax profile with correct region
- Documented env-var-based API key binding
- Diagnosis from ax profiles show output
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ax profile configuration is the first gate when wiring agent evaluation tooling during build, and again when ops/debugging auth in production-like runs. Profile and region setup for ax belongs with agent-tooling integrations that connect coding agents to Arize evaluation infrastructure.
Where it fits
Wire ax CLI on a new laptop before running local LLM regression evals against staging prompts.
Unblock CI eval smoke tests that fail with 401 because ARIZE_API_KEY was never bound to the active profile.
Patch expired or wrong-region profile when nightly eval jobs start failing without code changes.
How it compares
CLI profile bootstrap for ax—not a full LLM eval framework skill or hosted notebook tutorial.
Common Questions / FAQ
Who is arize-evaluator for?
Solo builders and small teams using Arize’s ax CLI who need profiles, API keys, and regions corrected before running evaluations.
When should I use arize-evaluator?
At Build when wiring agent eval tooling and you see missing profiles or 401s; at Operate when CI or local eval jobs fail auth; at Ship when pre-release eval smoke tests need a working ax profile.
Is arize-evaluator safe to install?
Follow its rule to never paste API keys into flags; review the Security Audits panel on this Prism page and rotate keys if an agent logged them.
SKILL.md
READMESKILL.md - Arize Evaluator
# ax Profile Setup Consult this when authentication fails (401, missing profile, missing API key). Do NOT run these checks proactively. Use this when there is no profile, or a profile has incorrect settings (wrong API key, wrong region, etc.). ## 1. Inspect the current state ```bash ax profiles show ``` Look at the output to understand what's configured: - `API Key: (not set)` or missing → key needs to be created/updated - No profile output or "No profiles found" → no profile exists yet - Connected but getting `401 Unauthorized` → key is wrong or expired - Connected but wrong endpoint/region → region needs to be updated ## 2. Fix a misconfigured profile If a profile exists but one or more settings are wrong, patch only what's broken. **Never pass a raw API key value as a flag.** Always reference it via the `ARIZE_API_KEY` environment variable. If the variable is not already set in the shell, instruct the user to set it first, then run the command: ```bash # If ARIZE_API_KEY is already exported in the shell: ax profiles update --api-key $ARIZE_API_KEY # Fix the region (no secret involved — safe to run directly) ax profiles update --region us-east-1b # Fix both at once ax profiles update --api-key $ARIZE_API_KEY --region us-east-1b ``` `update` only changes the fields you specify — all other settings are preserved. If no profile name is given, the active profile is updated. ## 3. Create a new profile If no profile exists, or if the existing profile needs to point to a completely different setup (different org, different region): **Always reference the key via `$ARIZE_API_KEY`, never inline a raw value.** ```bash # Requires ARIZE_API_KEY to be exported in the shell first ax profiles create --api-key $ARIZE_API_KEY # Create with a region ax profiles create --api-key $ARIZE_API_KEY --region us-east-1b # Create a named profile ax profiles create work --api-key $ARIZE_API_KEY --region us-east-1b ``` To use a named profile with any `ax` command, add `-p NAME`: ```bash ax spans export PROJECT -p work ``` ## 4. Getting the API key **Never ask the user to paste their API key into the chat. Never log, echo, or display an API key value.** If `ARIZE_API_KEY` is not already set, instruct the user to export it in their shell: ```bash export ARIZE_API_KEY="..." # user pastes their key here in their own terminal ``` They can find their key at https://app.arize.com/admin > API Keys. Recommend they create a **scoped service key** (not a personal user key) — service keys are not tied to an individual account and are safer for programmatic use. Keys are space-scoped — make sure they copy the key for the correct space. Once the user confirms the variable is set, proceed with `ax profiles create --api-key $ARIZE_API_KEY` or `ax profiles update --api-key $ARIZE_API_KEY` as described above. ## 5. Verify After any create or update: ```bash ax profiles show ``` Confirm the API key and region are correct, then retry the original command. ## Space There is no profile flag for space. Save it as an environment variable — accepts a space **name** (e.g., `my-workspace`) or a base64 space **ID** (e.g., `U3BhY2U6...`). Find yours with `ax spaces list -o json`. **macOS/Linux** — add to `~/.zshrc` or `~/.bashrc`: ```bash export ARIZE_SPACE="my-workspace" # name or base64 ID ``` Then `source ~/.zshrc` (or restart terminal). **Windows (PowerShell):** ```powershell [System.Environment]::SetEnvironmentVariable('ARIZE_SPACE', 'my-workspace', 'User') ``` Restart terminal for it to take effect. ## Save Credentials for Future Use At the **end of the session**, if the user manually provided any credentials during this conversation **and** those values were NOT already loaded from a saved profile or environment variable, offer to save them. **Skip this entirely if:** - The API key was already loaded from an existing profile or `ARIZE_API_KEY` env var - The space was already set via `ARIZE_SPACE` env var - The user only used base64 pr