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.

Improve prompt cache hit rate v1.0.0

Use this resource to cut the cost and latency of repeated LLM calls with prompt caching

New

  • 455 downloads
  • 118 likes
  • 174 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-cache-hit-optimization

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 analyses prompt structure, separates stable from variable content and recommends an order that maximises reuse. You get a cost calculation and a verification method, without assuming unmeasured savings.

Mostly picked by

Updated November 2, 2026

Card for the “Improve prompt cache hit rate” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: stable prefix, user boundaries and provider requirements
  • SKILL.md: cost calculator, examples and verification workflow

Good fit for

  • Repeated requests share long instructions or reference documents
  • Your API bill must fall without changing models

Not for

    Tags

    • prompt caching
    • cost
    • latency
    • llm
    • optimisation

    About

    You say

    “Reorder my support assistant prompts so the cache covers the system instructions and the knowledge base.”

    Card for the “Improve prompt cache hit rate” skill

    Skill published by affaan-m 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 cut the cost and latency of repeated LLM calls with prompt caching
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md9.9 KB

    Origin and licence

    Listed unmodified

    Author
    affaan-m
    Source
    github.com/affaan-m/ecc/tree/25278e7d7b6cf6e6a4e7a6c8e10f14ff22f0eb5b/skills/prompt-caching-strategy
    Licence
    MIT

    Notice

    « prompt-caching-strategy » (affaan-m, 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.