karpathy-guidelines · diff
git:20260802.1479e32 to git:20261008.3d24d40
12 added, 56 removed. Audit A to A.
---
name: karpathy-guidelines
- description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
- license: MIT
+ description: Pointer to the upstream skill for behavioural guidelines that reduce common LLM coding mistakes, installed from upstream.
domain: foundational
---
- # Karpathy Guidelines
-
- Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
-
- **Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
-
- ## 1. Think Before Coding
-
- **Don't assume. Don't hide confusion. Surface tradeoffs.**
-
- Before implementing:
- - State your assumptions explicitly. If uncertain, ask.
- - If multiple interpretations exist, present them - don't pick silently.
- - If a simpler approach exists, say so. Push back when warranted.
- - If something is unclear, stop. Name what's confusing. Ask.
-
- ## 2. Simplicity First
-
- **Minimum code that solves the problem. Nothing speculative.**
-
- - No features beyond what was asked.
- - No abstractions for single-use code.
- - No "flexibility" or "configurability" that wasn't requested.
- - No error handling for impossible scenarios.
- - If you write 200 lines and it could be 50, rewrite it.
-
- Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
-
- ## 3. Surgical Changes
-
- **Touch only what you must. Clean up only your own mess.**
-
- When editing existing code:
- - Don't "improve" adjacent code, comments, or formatting.
- - Don't refactor things that aren't broken.
- - Match existing style, even if you'd do it differently.
- - If you notice unrelated dead code, mention it - don't delete it.
-
- When your changes create orphans:
- - Remove imports/variables/functions that YOUR changes made unused.
- - Don't remove pre-existing dead code unless asked.
+ # Karpathy guidelines (pointer)
- The test: Every changed line should trace directly to the user's request.
+ Coco does not ship this skill because the upstream has no licence file, so this file only points to the original.
- ## 4. Goal-Driven Execution
+ ## Install from upstream
- **Define success criteria. Loop until verified.**
+ Review the upstream repository before you run its installer; Coco does not vet or pin it.
- Transform tasks into verifiable goals:
- - "Add validation" → "Write tests for invalid inputs, then make them pass"
- - "Fix the bug" → "Write a test that reproduces it, then make it pass"
- - "Refactor X" → "Ensure tests pass before and after"
+ The lines below are Claude Code slash commands, not shell commands.
- For multi-step tasks, state a brief plan:
- ```
- 1. [Step] → verify: [check]
- 2. [Step] → verify: [check]
- 3. [Step] → verify: [check]
+ ```text
+ /plugin marketplace add forrestchang/andrej-karpathy-skills
+ /plugin install andrej-karpathy-skills@karpathy-skills
```
- Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+ Source: https://github.com/multica-ai/andrej-karpathy-skills/blob/2c606141936f1eeef17fa3043a72095b4765b9c2/skills/karpathy-guidelines/SKILL.md
+
+ Coco will not reproduce the upstream text. If you are the author and want this link removed or changed, see docs/personas/TAKEDOWN.md.