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 application architecture v1.0.0

Use this resource to design an LLM application ready for production

New

  • 515 downloads
  • 110 likes
  • 187 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-application-architecture-2

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 proposes an architecture for an LLM application: a RAG pipeline with ingestion, storage and retrieval, agents that reason and act, tool calls and multi-agent collaboration. It adds prompt management, versioning and monitoring. You get a justified architecture plan.

Mostly picked by

Updated November 2, 2026

Card for the “LLM application architecture” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: overview, use cases and architecture choices
  • sub-skills/: ingestion, embedding storage, retrieval strategies, agent patterns and versioned prompts

Good fit for

  • You build an application that relies on a language model
  • You must choose between a simple RAG pipeline and an agent

Not for

    Tags

    • llm
    • rag
    • agents
    • architecture

    About

    You say

    “Design an assistant architecture that answers from our client contracts, with versioned prompts.”

    Card for the “LLM application architecture” skill

    Skill published by dokhacgiakhoa 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 design an LLM application ready for production
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE2.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.1 KB
    • sub-skills/11-document-ingestion.md0.7 KB
    • sub-skills/12-embedding-storage.md1.3 KB
    • sub-skills/13-retrieval-strategies.md1.2 KB
    • sub-skills/14-generation-with-context.md0.8 KB
    • sub-skills/21-react-pattern-reasoning-acting.md1.5 KB
    • sub-skills/22-function-calling-pattern.md1.6 KB
    • sub-skills/23-plan-and-execute-pattern.md0.9 KB
    • sub-skills/24-multi-agent-collaboration.md1.1 KB
    • sub-skills/31-prompt-templates-with-variables.md1 KB
    • sub-skills/32-prompt-versioning-ab-testing.md0.9 KB
    • sub-skills/33-prompt-chaining.md1.3 KB
    • sub-skills/41-metrics-to-track.md0.7 KB
    • sub-skills/42-logging-tracing.md1.5 KB
    • sub-skills/43-evaluation-framework.md1.4 KB
    • sub-skills/51-caching-strategy.md1 KB
    • sub-skills/52-rate-limiting-retry.md1 KB
    • sub-skills/53-fallback-strategy.md1.5 KB
    • sub-skills/overview.md1 KB

    Origin and licence

    Listed unmodified

    Author
    dokhacgiakhoa
    Source
    github.com/dokhacgiakhoa/agent-skills-4-vibe-coding-cli/tree/c4a059bbf7a8d6b2162071f0fbfe74053faa6d20/.agent/skills/llm-app-patterns
    Licence
    MIT

    Notice

    « llm-app-patterns » (dokhacgiakhoa, 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.