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.

Choose LLM parameters by task v1.0.0

Use this resource to tune model parameters for the type of task

New

  • 367 downloads
  • 103 likes
  • 179 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-parameter-settings-by-task

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 suggests generation parameters suited to formal proof, code generation or creative tasks, with the reasoning behind each. You get a justified configuration for your model calls.

Mostly picked by

Updated November 2, 2026

Card for the “Choose LLM parameters by task” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: parameter tables by task type
  • SKILL.md: proof plan request template and anti-patterns

Good fit for

  • You tune a model for code generation
  • Creative answers are too repetitive or too vague

Not for

    Tags

    • llm
    • parameters
    • temperature
    • tuning

    About

    You say

    “Which LLM parameters should I use to generate code?”

    Card for the “Choose LLM parameters by task” skill

    Skill published by parcadei 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 tune model parameters for the type of task
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.9 KB

    Origin and licence

    Listed unmodified

    Author
    parcadei
    Source
    github.com/parcadei/continuous-claude-v3/tree/d07ff4b06b62f43771bc0c927d0211b734d6149e/.claude/skills/llm-tuning-patterns
    Licence
    MIT

    Notice

    « llm-tuning-patterns » (parcadei, 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.