Karpathy Guidelines
Keep agent-written code minimal, explicit, and verifiable whenever you implement, review, or refactor.
Install
npx skills add https://github.com/forrestchang/andrej-karpathy-skills --skill karpathy-guidelinesWhat is this skill?
- Think before coding: state assumptions, ask when unclear, surface tradeoffs
- Simplicity first: no speculative features or single-use abstractions
- Surgical changes: touch only required lines; avoid drive-by refactors
- Verifiable success criteria instead of vague “done” claims
- Biased toward caution over speed on non-trivial work
Adoption & trust: 13.8k installs on skills.sh; 171k GitHub stars; 3/3 security scanners passed (skills.sh audits).
Recommended Skills
Improve Codebase Architecturemattpocock/skills
Zoom Outmattpocock/skills
Caveman Reviewjuliusbrussee/caveman
Requesting Code Reviewobra/superpowers
Receiving Code Reviewobra/superpowers
Request Refactor Planmattpocock/skills
Journey fit
Primary fit
Code review is the canonical shelf because the skill explicitly targets writing, reviewing, and refactoring—but the habits apply across the journey. Review subphase matches surfacing assumptions and surgical edits before merge, even though the same rules apply while building features.
Common Questions / FAQ
Is Karpathy Guidelines safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Karpathy Guidelines
# 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. The test: Every changed line should trace directly to the user's request. ## 4. Goal-Driven Execution **Define success criteria. Loop until verified.** 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" 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.