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.

Optimizing agent prompts with evals v1.0.0

Use this resource to create, optimize and port agent prompts using evaluations

New

  • 492 downloads
  • 100 likes
  • 165 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install optimize-agent-prompts-evals

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 defines the prompt's contract, inventories external context, chooses a model strategy and rewrites the prompt. It loads only the references the task needs: a new prompt, an existing one, a port between model families or repeated failures. You get an improved prompt and the material to check it.

Mostly picked by

Updated November 2, 2026

Card for the “Optimizing agent prompts with evals” 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: contract, strategy and optimization steps
  • references/core-patterns.md: core prompt patterns
  • references/model-family-notes.md: notes per model family

Good fit for

  • A system prompt gives uneven answers and must become reliable
  • You want to port a prompt from OpenAI to Claude

Not for

    Tags

    • prompt
    • agents
    • evaluation
    • models

    About

    You say

    “Optimize my support agent's system prompt and port it to Claude.”

    Card for the “Optimizing agent prompts with evals” skill

    Skill published by getsentry 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, optimize and port agent prompts using evaluations
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.7 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/core-patterns.md5.5 KB
    • references/meta-optimization-loop.md3.8 KB
    • references/model-family-notes.md3.4 KB
    • references/transformed-examples.md3.7 KB
    • SKILL.md4.6 KB
    • SOURCES.md11.5 KB
    • SPEC.md5.2 KB

    Origin and licence

    Listed unmodified

    Author
    getsentry
    Source
    github.com/getsentry/skills/tree/d12f250460ffd961f549dbebf7eeb0cf4afd4c2e/skills/prompt-optimizer
    Licence
    Apache-2.0

    Notice

    « prompt-optimizer » (getsentry, 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.