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.

Behavioral evaluations of agent decisions v1.0.0

Use this resource to create, run and fix behavioral evaluations of the agent

New

  • 395 downloads
  • 104 likes
  • 158 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install behavioral-evals-agent-decisions

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 follows the decision tree, sets up the workspace, writes the assertions and checks results. You get regression tests on the agent's decisions, built from the repository templates.

Mostly picked by

Updated November 2, 2026

Card for the “Behavioral evaluations of agent decisions” 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: decision tree, quick checklist and bundled resources
  • references/creating.md, running.md, fixing.md and promoting.md: creation, running, fixing and promotion
  • assets/standard_eval.ts.txt and interactive_eval.ts.txt: evaluation templates

Good fit for

  • A prompt change alters which tool the agent picks
  • You want regression coverage on the agent's decisions

Not for

    Tags

    • evaluation
    • agent
    • regression

    About

    You say

    “Write an evaluation that checks the agent reads the file before editing it.”

    Card for the “Behavioral evaluations of agent decisions” skill

    Skill published by google-gemini 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 create, run and fix behavioral evaluations of the agent
    3. Review and adjust the result

    Content preview

    Files

    • assets/interactive_eval.ts.txt0.9 KB
    • assets/standard_eval.ts.txt1 KB
    • LICENSE11.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/creating.md4.5 KB
    • references/fixing.md4.6 KB
    • references/promoting.md1.9 KB
    • references/running.md2.5 KB
    • SKILL.md2.4 KB

    Origin and licence

    Listed unmodified

    Author
    google-gemini
    Source
    github.com/google-gemini/gemini-cli/tree/718e97c2448e0384cb582409cf4e479437bf50fe/.gemini/skills/behavioral-evals
    Licence
    Apache-2.0

    Notice

    « behavioral-evals » (google-gemini, 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.