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.

Debug inference for local or hosted models v1.0.0

Use this resource to diagnose an inference client that fails through a provider, a local model or a hosted API

New

  • 328 downloads
  • 105 likes
  • 161 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install inference-endpoint-debugging

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 checks the provider attachment, the endpoint's network policy, credential substitution and topology. It treats inference as ordinary network traffic and leaves your application's request unchanged.

Mostly picked by

Updated November 2, 2026

Card for the “Debug inference for local or hosted models” 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: five-step diagnosis flow
  • SKILL.md: common errors and a checklist for local models

Good fit for

  • Your app can no longer reach Ollama from the sandbox
  • A credentials error appears after you migrate an endpoint

Not for

    Tags

    • inference
    • ollama
    • network
    • diagnosis

    About

    You say

    “My client can't reach Ollama from the sandbox: find out why.”

    Card for the “Debug inference for local or hosted models” skill

    Skill published by nvidia 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 diagnose an inference client that fails through a provider, a local model or a hosted API
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.2 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.5 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/openshell/tree/2fb8d78af336a06455785e6d969a4c061e598adf/skills/debug-inference
    Licence
    Apache-2.0

    Notice

    « debug-inference » (nvidia, 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.