Search
LearnPrompt/andrej-karpathy-skills
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Apply Andrej Karpathy AI methodology and principles from his 2023-2026 insights. Use this skill when the user wants to apply Karpathy-style… | LearnPrompt/ | 110 | — | ~1.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 2 | Apply Karpathy-style agentic engineering to any coding or building task. | LearnPrompt/ | 110 | — | ~1.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 3 | Sets up an autonomous research loop where an agent runs experiments on git branches, logs results and proposes the next iteration while you approve each hypothesis change. | LearnPrompt/ | 110 | — | ~1.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 4 | Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners. | LearnPrompt/ | 110 | — | ~1.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 5 | Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement. | LearnPrompt/ | 110 | — | ~1.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 6 | Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. | LearnPrompt/ | 110 | — | ~1.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 7 | Build and maintain an LLM-powered personal knowledge base or wiki. | LearnPrompt/ | 110 | — | ~1.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 8 | Run a structured reflection on how AI is reshaping your skills, career, and leverage. | LearnPrompt/ | 110 | — | ~1.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 9 | Apply Karpathy-style minimalism and anti-dependency principles to code and system design. | LearnPrompt/ | 110 | — | ~1.6k | Automated safety check: Pass | MIT | 3 mo ago |
| 10 | Upgrade LLM outputs from plain text to structured, rendered formats like HTML, Marp slides, or interactive dashboards. | LearnPrompt/ | 110 | — | ~1.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 11 | Build practice environments and evaluation gyms where agents can try, fail, and learn from feedback. | LearnPrompt/ | 110 | — | ~2.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 12 | Apply rigorous supply chain security hygiene to software projects — audit dependencies, detect risks, minimize attack surface. | LearnPrompt/ | 110 | — | ~1.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 13 | Write explicit strategy into system prompts as a learning mechanism — making LLM behavior more predictable and teachable through prompt-as-textbook approach. | LearnPrompt/ | 110 | — | ~1.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 14 | Apply the Karpathy understanding-first principle — verify what AI built, own your understanding, map the jagged capability landscape of LLMs. | LearnPrompt/ | 110 | — | ~1.6k | Automated safety check: Pass | MIT | 3 mo ago |
| 15 | Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration). | LearnPrompt/ | 110 | — | ~1.4k | Automated safety check: Pass | MIT | 3 mo ago |
