Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Build and validate evaluators for AI apps v1.0.0

Use this resource to build, run and validate evaluators for an AI application with Phoenix

New

  • 436 downloads
  • 139 likes
  • 166 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-evaluators-phoenix

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent writes code evaluators for simple checks and LLM judges for nuanced ones, in Python or TypeScript. It runs them over traces or dataframes, or as Phoenix experiments, and can check their agreement with human-labeled data.

Mostly picked by

Updated November 2, 2026

Card for the “Build and validate evaluators for AI apps” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: workflows and evaluator design principles
  • references/: pre-built, code and LLM evaluators in Python and TypeScript

Good fit for

  • You need to measure a chatbot's quality after each prompt change
  • You want automated checks instead of manual reviews

Not for

    Tags

    • evaluation
    • llm as judge
    • phoenix
    • quality

    About

    You say

    “Build an evaluator that checks the answer cites the documents provided, then run it on my traces.”

    Card for the “Build and validate evaluators for AI apps” skill

    Skill published by arize-ai under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to build, run and validate evaluators for an AI application with Phoenix
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE3.7 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/axial-coding.md2.4 KB
    • references/common-mistakes-python.md8.2 KB
    • references/error-analysis-multi-turn.md1.4 KB
    • references/error-analysis.md4.4 KB
    • references/evaluate-dataframe-python.md4.8 KB
    • references/evaluators-code-python.md3.1 KB
    • references/evaluators-code-typescript.md3 KB
    • references/evaluators-custom-templates.md1.2 KB
    • references/evaluators-llm-python.md2.6 KB
    • references/evaluators-llm-typescript.md2.9 KB
    • references/evaluators-overview.md1.1 KB
    • references/evaluators-pre-built.md7.9 KB
    • references/evaluators-rag.md3.7 KB
    • references/experiments-datasets-python.md5 KB
    • references/experiments-datasets-typescript.md3.7 KB
    • references/experiments-overview.md1.8 KB
    • references/experiments-running-python.md4.4 KB
    • references/experiments-running-typescript.md5.9 KB
    • references/experiments-synthetic-python.md1.8 KB
    • references/experiments-synthetic-typescript.md2.3 KB
    • references/filter-expressions.md15.2 KB
    • references/fundamentals-anti-patterns.md1.7 KB
    • references/fundamentals-model-selection.md1.5 KB
    • references/fundamentals.md1.9 KB
    • references/integrations-pytest.md8.1 KB
    • references/integrations-vitest-jest.md9.3 KB
    • references/observe-sampling-python.md3.4 KB
    • references/observe-sampling-typescript.md4.9 KB
    • references/observe-tracing-setup.md4.4 KB
    • references/production-continuous.md4.1 KB
    • references/production-guardrails.md1.4 KB
    • references/production-overview.md2.4 KB
    • references/setup-python.md2 KB
    • references/setup-typescript.md1.5 KB
    • references/validation-evaluators-python.md1.2 KB
    • references/validation-evaluators-typescript.md4.6 KB
    • references/validation.md3.8 KB
    • SKILL.md5.5 KB

    Origin and licence

    Listed unmodified

    Author
    arize-ai
    Source
    github.com/arize-ai/phoenix/tree/2196d813a80586c7bd3a3b91a6092d6a3fabb10c/.agents/skills/phoenix-evals
    Licence
    Apache-2.0

    Notice

    « phoenix-evals » (arize-ai, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.