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.

Choosing the LLM model per task v1.0.0

Use this resource to choose the most suitable LLM model for each task based on cost and complexity

New

  • 426 downloads
  • 108 likes
  • 110 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-model-routing

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 sorts each task by complexity and budget, then assigns it to a lighter or a more powerful model. You get an assignment grid and a routing strategy: static, cascading or adaptive.

Mostly picked by

Updated November 2, 2026

Card for the “Choosing the LLM model per task” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: decision tree, tier table and three routing strategies
  • CHANGELOG.md: version history
  • .claude-plugin/plugin.json: plugin metadata

Good fit for

  • You need to choose which model each step of an agent calls
  • Your AI API bill keeps growing and you want to cut it without losing quality

Not for

    Tags

    • routing
    • LLM models
    • AI costs
    • agents

    About

    You say

    “Which model should summarise customer reviews and draft a financial analysis report?”

    Card for the “Choosing the LLM model per task” skill

    Skill published by curiositech 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 choose the most suitable LLM model for each task based on cost and complexity
    3. Review and adjust the result

    Content preview

    Files

    • .claude-plugin/plugin.json0.6 KB
    • CHANGELOG.md0.5 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md6.7 KB

    Origin and licence

    Listed unmodified

    Author
    curiositech
    Source
    github.com/curiositech/some_claude_skills/tree/f49825290077e5fb46bb3e867dfa8a5b0161152b/.claude/skills/llm-router
    Licence
    MIT

    Notice

    « llm-router » (curiositech, 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.