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 prompt caching v1.0.0

Use this resource to reduce LLM call costs with caching

New

  • 510 downloads
  • 225 likes
  • 247 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-prompt-caching-strategies

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 picks the right caching layer: prompt prefix, full response or cache-augmented context. It avoids mistakes such as caching responses at high temperature or never invalidating the cache. You get a caching strategy suited to your calls.

Mostly picked by

Updated November 2, 2026

Card for the “LLM prompt caching” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: capabilities and caching models
  • sub-skills/: Anthropic prompt caching, response caching, CAG and anti-patterns

Good fit for

  • Your system prompts are long and repeated on every call
  • Your LLM API bill grows with the same reused context

Not for

    Tags

    • caching
    • prompt
    • cost
    • llm

    About

    You say

    “Add prompt caching to my 20,000-token system prompt and estimate the savings.”

    Card for the “LLM prompt caching” 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 reduce LLM call costs with caching
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE2.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.4 KB
    • sub-skills/anthropic-prompt-caching.md0.1 KB
    • sub-skills/cache-augmented-generation-cag.md0.1 KB
    • sub-skills/caching-everything.md0.5 KB
    • sub-skills/caching-with-high-temperature.md0 KB
    • sub-skills/no-cache-invalidation.md0 KB
    • sub-skills/response-caching.md0.1 KB

    Origin and licence

    Listed unmodified

    Author
    dokhacgiakhoa
    Source
    github.com/dokhacgiakhoa/agent-skills-4-vibe-coding-cli/tree/c4a059bbf7a8d6b2162071f0fbfe74053faa6d20/.agent/skills/prompt-caching
    Licence
    MIT

    Notice

    « prompt-caching » (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.