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.

Agent evaluation and quality loop v1.0.0

Use this resource to evaluate an agent, analyze its failures and improve its scores

New

  • 558 downloads
  • 167 likes
  • 187 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-evaluation-quality-loop

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 guides dataset preparation, the evaluation run, failure analysis and then fixes, using metrics and an LLM judge. You get a repeatable evaluation cycle for an agents-cli project.

Mostly picked by

Updated November 2, 2026

Card for the “Agent evaluation and quality loop” 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: evaluation loop and agents-cli commands
  • references/metrics-guide.md and dataset_schema.md: metric choice and data schema
  • references/: live, multimodal and user-simulation evaluation

Good fit for

  • Your agent's answers are uneven and you want to measure them
  • You compare two versions of an agent on the same test set

Not for

    Tags

    • evaluation
    • agent
    • metrics

    About

    You say

    “Evaluate my support agent on the test set and explain the failures.”

    Card for the “Agent evaluation and quality loop” skill

    Skill published by google 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 evaluate an agent, analyze its failures and improve its scores
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/advanced-commands.md2.4 KB
    • references/builtin-tools-eval.md6.2 KB
    • references/dataset_schema.md8.6 KB
    • references/live-eval.md2.7 KB
    • references/metrics-guide.md10.2 KB
    • references/multimodal-eval.md5.4 KB
    • references/user-simulation.md6.4 KB
    • SKILL.md24.7 KB

    Origin and licence

    Listed unmodified

    Author
    google
    Source
    github.com/google/agents-cli/tree/f4e994044164ff6617f0799900dba0fc091ef0e3/skills/google-agents-cli-eval
    Licence
    Apache-2.0

    Notice

    « google-agents-cli-eval » (google, 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.