Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
Works with
Emphasizes surfacing assumptions and tradeoffs upfront rather than making silent decisions or hiding confusion
Advocates for minimum viable code with no speculative features, abstractions, or error handling beyond what was requested
Requires surgical, focused edits that touch only what's necessary and match existing code style without improving adjacen
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionkarpathy-guidelinesExecute the skills CLI command in your project's root directory to begin installation:
Fetches karpathy-guidelines from forrestchang/andrej-karpathy-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate karpathy-guidelines. Access via /karpathy-guidelines in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
35
total installs
35
this week
7.7K
GitHub stars
0
upvotes
Run in your terminal
35
installs
35
this week
7.7K
stars
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.
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
anthropics/claude-code
github/awesome-copilot
mblode/agent-skills
leonxlnx/taste-skill
sickn33/antigravity-awesome-skills
erichowens/some_claude_skills
karpathy-guidelines has been reliable in day-to-day use. Documentation quality is above average for community skills.
I recommend karpathy-guidelines for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
karpathy-guidelines reduced setup friction for our internal harness; good balance of opinion and flexibility.
Keeps context tight: karpathy-guidelines is the kind of skill you can hand to a new teammate without a long onboarding doc.
Solid pick for teams standardizing on skills: karpathy-guidelines is focused, and the summary matches what you get after install.
karpathy-guidelines fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Useful defaults in karpathy-guidelines — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Registry listing for karpathy-guidelines matched our evaluation — installs cleanly and behaves as described in the markdown.
karpathy-guidelines fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Solid pick for teams standardizing on skills: karpathy-guidelines is focused, and the summary matches what you get after install.
showing 1-10 of 33