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.

Caching prompts and model responses v1.0.0

Use this resource to cut the cost and latency of language model calls with caching

New

  • 571 downloads
  • 162 likes
  • 162 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 cache level (prefix, response or semantic similarity), plans invalidation and measures hit rate. You get a caching strategy and tracking metrics.

Mostly picked by

Updated November 2, 2026

Card for the “Caching prompts and model responses” 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: agent role and caching principles
  • references/patterns.md: prefix and response cache patterns
  • references/sharp_edges.md: stale caches and their causes

Good fit for

  • A long system prompt is resent with every request
  • Your language model bill grows with repeated questions

Not for

    Tags

    • prompt caching
    • llm
    • cost
    • latency
    • invalidation

    About

    You say

    “Cache the prefix of my 20,000-token system prompt for a customer support assistant.”

    Card for the “Caching prompts and model responses” skill

    Skill published by omer-metin 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 cut the cost and latency of language model calls with caching
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/patterns.md7 KB
    • references/sharp_edges.md6.2 KB
    • references/validations.md1.6 KB
    • SKILL.md1.8 KB

    Origin and licence

    Listed unmodified

    Author
    omer-metin
    Source
    github.com/omer-metin/skills-for-antigravity/tree/e8dcf4e8737921a10088bd5c9eb65e81f74c051f/skills/prompt-caching
    Licence
    Apache-2.0

    Notice

    « prompt-caching » (omer-metin, 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.