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.

Context engineering for agents and LLM pipelines v1.0.0

Use this resource to design or debug an agent system by optimizing its context and tokens

New

  • 338 downloads
  • 177 likes
  • 132 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-context-engineering-guide

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 reviews context design, spots degradation, applies compression and memory strategies, then evaluates performance. It relies on a four-bucket strategy for context. You get reasoned recommendations for your LLM system.

Mostly picked by

Updated November 2, 2026

Card for the “Context engineering for agents and LLM pipelines” skill

Details

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

Similar resources

View all

What you get

  • references/degradation.md: context degradation patterns
  • references/compression.md: compression strategies
  • references/multi-agent.md: multi-agent coordination

Good fit for

  • An agent forgets instructions in long conversations
  • You want to cut the token cost of an LLM pipeline

Not for

    Tags

    • context
    • tokens
    • agents
    • memory
    • llm

    About

    You say

    “My agent loses its instructions after twenty turns: diagnose its context.”

    Card for the “Context engineering for agents and LLM pipelines” skill

    Skill published by siviter-xyz 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 design or debug an agent system by optimizing its context and tokens
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/compression.md1.5 KB
    • references/degradation.md1.8 KB
    • references/evaluation.md1.5 KB
    • references/fundamentals.md2 KB
    • references/memory.md1.4 KB
    • references/multi-agent.md1.4 KB
    • references/optimization.md1.9 KB
    • references/tool-design.md1.2 KB
    • SKILL.md3.4 KB

    Origin and licence

    Listed unmodified

    Author
    siviter-xyz
    Source
    github.com/siviter-xyz/dot-agent/tree/33762551d4dfa2e757fa1b43417c7dab528a215f/skills/context-engineering
    Licence
    MIT

    Notice

    « context-engineering » (siviter-xyz, 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.