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.

DSPy: signatures and modules to optimize prompts v1.0.0

Use this resource to structure an LLM system and optimize its prompts through evaluation

New

  • 417 downloads
  • 237 likes
  • 137 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install dspy-prompt-optimization-framework

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 input and output signatures, assembles modules, then optimizes prompts from evaluation data. You get a reproducible, version-controllable DSPy program.

Mostly picked by

Updated November 2, 2026

Card for the “DSPy: signatures and modules to optimize prompts” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: signatures, reasoning modules, pipelines and compilation
  • metadata.json: skill metadata

Good fit for

  • A prompt gives uneven results and must be measured
  • You want to version prompts as code

Not for

    Tags

    • dspy
    • prompts
    • optimization
    • llm

    About

    You say

    “Write a DSPy signature that extracts the customer and the amount from an invoice.”

    Card for the “DSPy: signatures and modules to optimize prompts” skill

    Skill published by bobmatnyc under the MIT 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 structure an LLM system and optimize its prompts through evaluation
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • metadata.json3.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md45.1 KB

    Origin and licence

    Listed unmodified

    Author
    bobmatnyc
    Source
    github.com/bobmatnyc/claude-mpm-skills/tree/718070a7d622921b01687799a1f9613f36c6f615/toolchains/ai/frameworks/dspy
    Licence
    MIT

    Notice

    « dspy » (bobmatnyc, MIT) 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.