From content-ideas
Use when writing, reviewing, or refactoring any code to enforce: surface assumptions before coding, minimum code that solves the problem, surgical edits that touch only what's required, and verifiable success criteria. Always-on behavioral overlay during implementation work. Triggers on "karpathy", "apply karpathy", "coding guardrails", or any coding task in projects where this skill is loaded.
How this skill is triggered — by the user, by Claude, or both
Slash command
/content-ideas:karpathy-guidelinesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
Minimum code that solves the problem. Nothing speculative.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
Touch only what you must. Clean up only your own mess.
When editing existing code:
When your changes create orphans:
The test: Every changed line should trace directly to the user's request.
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
Code Quality & Review
None — standalone behavioral overlay. No file inputs or outputs.
| Skill | Pattern | Condition | Handoff Artifact |
|---|---|---|---|
claude-code-director | Behavioral overlay | always-on during any implementation phase | — (modifies HOW coding runs, not what is produced) |
plaid (Build phase) | Behavioral overlay | always-on when executing docs/product-roadmap.md tasks | — |
code-review / ce-code-review | Domain cluster | sibling in the code quality domain; code-review assesses output, karpathy-guidelines governs process | — |
simplify | Domain cluster | sibling; simplify cleans up after implementation, karpathy-guidelines prevents overcomplication during it | — |
This skill has no interactive invocation. It is an always-on overlay: whenever any implementation work runs in a project that has loaded karpathy-guidelines, these four rules govern how Claude codes — not as a checklist to recite, but as internalized behavior.
npx claudepluginhub shekerkamma/content-ideas --plugin content-ideasGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Implements work from a spec or tickets using TDD at agreed seams, with regular typechecking and test runs, followed by code review.