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.

Application LLM calls: prompts, models, tracing v1.0.0

Use this resource to structure application LLM calls, with prompts, models and tracing

New

  • 546 downloads
  • 183 likes
  • 181 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-call-structure-tracing

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 locates the existing boundaries (prompts, structured generation, tracing scenarios) and separates prompt identity, model policy and tracing. You get calls that can be observed independently and checked before delivery.

Mostly picked by

Updated November 2, 2026

Card for the “Application LLM calls: prompts, models, tracing” 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: boundary mapping, prompt identity and versioning
  • SKILL.md: model policy, structured generation and verification

Good fit for

  • An LLM call is spread across several services
  • You want to track errors or costs per generation scenario

Not for

    Tags

    • LLM
    • prompts
    • structured generation
    • tracing

    About

    You say

    “Separate the summary prompt from the model policy and add its tracing.”

    Card for the “Application LLM calls: prompts, models, tracing” skill

    Skill published by lobehub 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 structure application LLM calls, with prompts, models and tracing
    3. Review and adjust the result

    Content preview

    Files

    • agents/openai.yaml0.3 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md4.3 KB

    Origin and licence

    Listed unmodified

    Author
    lobehub
    Source
    github.com/lobehub/lobehub/tree/4fe9e4227b730872669e12f9230d7672476af2f8/.agents/skills/llm-generation
    Licence
    Apache-2.0

    Notice

    « llm-generation » (lobehub, 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.