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.

LLM architecture: prompts, agents and structured output v1.0.0

Use this resource to design a reliable LLM application with controlled costs

New

  • 358 downloads
  • 165 likes
  • 196 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-application-architecture

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 reviews your need and proposes an architecture around RAG, structured outputs and agents, with context and cost management. You get reasoned design choices and hallucination risks to cover.

Mostly picked by

Updated November 2, 2026

Card for the “LLM architecture: prompts, agents and structured output” 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: agent role and working rules
  • references/patterns.md: recommended methods and templates
  • references/validations.md: checks to run before delivery

Good fit for

  • Your LLM prototype answers differently on each run
  • You are moving to several agents and must frame how they interact

Not for

    Tags

    • llm
    • architecture
    • agents
    • structured output

    About

    You say

    “Design an assistant that answers from our contracts, with validated JSON output and controlled cost per request.”

    Card for the “LLM architecture: prompts, agents and structured output” skill

    Skill published by omer-metin 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 design a reliable LLM application with controlled costs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/patterns.md8.1 KB
    • references/sharp_edges.md23.4 KB
    • references/validations.md6.3 KB
    • SKILL.md2.4 KB

    Origin and licence

    Listed unmodified

    Author
    omer-metin
    Source
    github.com/omer-metin/skills-for-antigravity/tree/e8dcf4e8737921a10088bd5c9eb65e81f74c051f/skills/llm-architect
    Licence
    Apache-2.0

    Notice

    « llm-architect » (omer-metin, 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.