Related Jira issue: ECS-9
| name | karpathy-writing-style |
|---|---|
| description | Emulate Andrej Karpathy's distinctive technical writing style for long-form AI/tech articles. Use when writing English technical essays, year-in-review posts, AI industry analysis, or opinion pieces that should feel insightful, accessible, and authentically "Karpathy-like" in voice and structure. |
This skill captures Karpathy's distinctive voice for technical long-form writing. Apply these patterns to produce articles that feel genuinely Karpathy-esque.
The most consequential AI development of the next few years isn't a new model—it's Skills. Here's the thesis:
- Skill will replace work—because unlike agents, Skills are controllable, auditable, and correctable.
- Millions of Skills will emerge in 2-3 years—far faster than the App Store took to reach 2 million apps.
- Unmanned companies will form—humans move from "in the loop" to "on the loop."
- Unmanned companies will outperform human-operated ones—Skills self-evolve through revenue outcomes, surpassing human-designed approaches.
Models are the power plants; Skills are the appliances. The appliance market is always 1000x larger.
| --- | |
| name: chinese-tweet-writing | |
| description: 中文推特/X写作优化。用于撰写或润色中文推文,包括产品分享、个人见解、行业观察等内容。当用户需要写中文推特、优化推文、或将长内容压缩成推文格式时使用。 | |
| --- | |
| # 中文推特写作规范 | |
| ## 核心原则 | |
| 1. **长度限制**:正文不超过140字(不含链接) |
GitHub: https://github.com/GBSOSS/nano-live2d
NanoLive2D - Open-source Live2D avatar customization pipeline. Describe clothing in text → AI generates texture → avatar wears it in 3-5 seconds (using Gemini 2.0/2.5). Plus real-time Q&A with natural expressions.
I built a tool that converts any MCP server into a Claude Skill, reducing context usage by 90%.
Using Claude with multiple MCP servers, I kept running into issues:
- Had ~15 MCP servers configured
- Tool definitions ate 30-40k tokens before any actual work
- Claude felt slower, responses got cut off