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 evaluators for LLM applications v1.0.0

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

New

  • 459 downloads
  • 174 likes
  • 154 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 decides what to evaluate, then writes code evaluators for verifiable criteria and LLM evaluators for nuance. It draws on Phoenix's pre-built evaluators and proposes custom templates. It recommends validating judges against human review.

Mostly picked by

Updated November 2, 2026

Card for the “Build evaluators for LLM applications” skill

Details

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

Similar resources

View all

What you get

  • references/evaluators-code-python.md and -typescript.md: code evaluators
  • references/evaluators-llm-python.md and -typescript.md: LLM evaluators and templates
  • references/error-analysis.md: error analysis from traces

Good fit for

  • You want automated checks on your agent's answers
  • You compare two prompt versions on a dataset

Not for

    Tags

    • phoenix
    • evaluators
    • llm
    • evaluation

    About

    You say

    “Write a Python evaluator that checks the answer cites at least one source from the corpus.”

    Card for the “Build evaluators for LLM applications” skill

    Skill published by github 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 and run evaluators for an AI application with Phoenix
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/axial-coding.md2.3 KB
    • references/common-mistakes-python.md7 KB
    • references/error-analysis-multi-turn.md1.3 KB
    • references/error-analysis.md4.2 KB
    • references/evaluate-dataframe-python.md4.4 KB
    • references/evaluators-code-python.md3 KB
    • references/evaluators-code-typescript.md1.2 KB
    • references/evaluators-custom-templates.md1.2 KB
    • references/evaluators-llm-python.md2.6 KB
    • references/evaluators-llm-typescript.md1.4 KB
    • references/evaluators-overview.md1.1 KB
    • references/evaluators-pre-built.md2.4 KB
    • references/evaluators-rag.md3.1 KB
    • references/experiments-datasets-python.md4.8 KB
    • references/experiments-datasets-typescript.md2.7 KB
    • references/experiments-overview.md1.7 KB
    • references/experiments-running-python.md2.9 KB
    • references/experiments-running-typescript.md3.1 KB
    • references/experiments-synthetic-python.md1.8 KB
    • references/experiments-synthetic-typescript.md2.2 KB
    • references/fundamentals-anti-patterns.md1.6 KB
    • references/fundamentals-model-selection.md1.4 KB
    • references/fundamentals.md1.8 KB
    • references/observe-sampling-python.md2.4 KB
    • references/observe-sampling-typescript.md3.9 KB
    • references/observe-tracing-setup.md3.3 KB
    • references/production-continuous.md3.6 KB
    • references/production-guardrails.md1.3 KB
    • references/production-overview.md2.3 KB
    • references/setup-python.md1.9 KB
    • references/setup-typescript.md1 KB
    • references/validation-evaluators-python.md1 KB
    • references/validation-evaluators-typescript.md4.4 KB
    • references/validation.md1.7 KB
    • SKILL.md4.5 KB

    Origin and licence

    Listed unmodified

    Author
    github
    Source
    github.com/github/awesome-copilot/tree/0fe6545b950671641b2b14b44eb56678fea6c6b4/skills/phoenix-evals
    Licence
    Apache-2.0

    Notice

    « phoenix-evals » (github, 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.