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.

Rules to avoid typical LLM coding mistakes v1.0.0

Use this resource to guide the code an agent writes or reviews to avoid its typical mistakes

New

  • 489 downloads
  • 162 likes
  • 134 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-coding-discipline-guidelines

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 applies four principles: state assumptions before coding, prefer the simplest solution, make targeted changes and define verifiable criteria. You get leaner code, limited changes and explicit assumptions.

Mostly picked by

Updated November 2, 2026

Card for the “Rules to avoid typical LLM coding mistakes” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: the four principles (think first, simplicity, surgical changes, goal-driven execution)
  • SKILL.md: verifiable success criteria

Good fit for

  • You let an agent write or refactor code
  • You review changes produced by an LLM

Not for

    Tags

    • best practices
    • llm
    • code review
    • simplicity

    About

    You say

    “Add an export button, keep the code simple and list your assumptions first.”

    Card for the “Rules to avoid typical LLM coding mistakes” skill

    Skill published by multica-ai 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 guide the code an agent writes or reviews to avoid its typical mistakes
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.5 KB

    Origin and licence

    Listed unmodified

    Author
    multica-ai
    Source
    github.com/multica-ai/andrej-karpathy-skills/tree/2c606141936f1eeef17fa3043a72095b4765b9c2/skills/karpathy-guidelines
    Licence
    MIT

    Notice

    « karpathy-guidelines » (multica-ai, 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.