Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

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.

Declarative language-model programming with DSPy v1.0.0

Use this resource to build LLM systems from signatures and modules, with automatic prompt optimisation

New

  • 412 downloads
  • 208 likes
  • 150 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install declarative-llm-programs-dspy

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 an input-output signature, a module and a DSPy optimiser, then configures the language model used. You get a modular LLM program whose prompts can be optimised from data.

Mostly picked by

Updated November 2, 2026

Card for the “Declarative language-model programming with DSPy” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: installation, a question-answering example and signatures
  • references/: modules, optimisers and examples

Good fit for

  • You are building a RAG system or classifier and want more reliable prompts
  • You want to replace hand-written prompts with a maintainable program

Not for

    Tags

    • dspy
    • prompts
    • llm
    • optimisation
    • modules

    About

    You say

    “Build a support-ticket classifier with DSPy and optimise it on these 200 examples.”

    Card for the “Declarative language-model programming with DSPy” skill

    Skill published by Orchestra Research 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 build LLM systems from signatures and modules, with automatic prompt optimisation
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/examples.md18.5 KB
    • references/modules.md12.1 KB
    • references/optimizers.md14.6 KB
    • SKILL.md14.9 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/nousresearch/hermes-agent/tree/0c74cc682dc81bf78b78a1737b3ee77a820ccb79/optional-skills/mlops/research/dspy
    Licence
    MIT

    Notice

    « dspy » (Orchestra Research, 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.