Reading
A four-skill package for AI coding agents like Claude Design, covering design token extraction, design pattern libraries, excellent case references, and animated landing page workflows, helping AI agents output professional-level frontend code.
Section 01
A four-skill package for AI coding agents like Claude Design, covering design token extraction, design pattern libraries, excellent case references, and animated landing page workflows, helping AI agents output professional-level frontend code.
Section 02
The core goal of Design System Stack is to improve the design quality of AI-generated frontend code. It does not teach AI basic syntax for writing code, but rather imparts the mindset of design systems—how to start from Design Tokens, build a consistent visual language, and finally output Awwwards-level animated landing pages.
This skill package includes four complementary skill modules:
Section 03
When refactoring or migrating projects, a common requirement is: "Keep the new website's visual style consistent with the old one". The traditional approach is manual measurement and recording of color values, font sizes, spacing, etc., which is time-consuming and prone to omissions.
extract-design-system enables AI agents to automatically extract a complete design token system from any website:
Section 04
Section 05
Extracted design tokens are output in structured formats (e.g., JSON, YAML, or CSS custom properties), which can be directly imported into design tools (Figma, Sketch) or code libraries (Tailwind configuration, CSS variables).
Section 06
Section 07
The valuable experience of senior frontend engineers often lies not in knowing how to use CSS, but in knowing "when to use which pattern". design-system-patterns encodes this experience into reusable knowledge for AI.
Section 08
Layout Patterns:
Component Patterns:
Visual Patterns:
Interaction Patterns:
Keep going with more reads from the same topic.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
Folkering OS is the world's first AI-native bare-metal operating system, entirely written in Rust no_std without relying on Linux, POSIX, or libc. It can generate commands from scratch, compile them into WASM, and run them in 10 seconds, achieving true self-evolution.
This project explores how to use Large Language Models (LLMs) to detect logical vulnerabilities in Ethereum smart contracts, especially business logic flaws that are difficult for traditional static analysis tools to capture, such as economic manipulation and execution order errors.
Cross-generational hardware testing based on NVIDIA A10G and H100 GPUs, comparing and analyzing the throughput, latency, and concurrent scalability of three mainstream LLM inference frameworks. SGLang achieves a 3.4x performance advantage over vLLM on H100, while Ollama faces architectural bottlenecks in high-concurrency scenarios.