Reading
A structured skill set for AI coding assistants, encapsulating mature software engineering practices into reusable Agent skills, covering the full development process from requirement analysis to code review.
Section 01
A structured skill set for AI coding assistants, encapsulating mature software engineering practices into reusable Agent skills, covering the full development process from requirement analysis to code review.
Section 02
With the rapid development of large language models in code generation, AI Coding Agents are becoming important tools for developers. However, ensuring that AI maintains systematicity, predictability, and high-quality output in complex software development tasks remains an urgent problem to solve. The sw-superpower project came into being; it is a structured skill set for AI coding assistants, aiming to encapsulate mature software engineering practices into reusable Agent skills.
This project is a Chinese localization adaptation of the obra/superpowers framework, fully retaining the essence of its methodology while adapting content for Chinese developers. The core concepts can be summarized as "Process-Driven" and "Rules First"—each skill defines clear trigger conditions and execution processes, and places unbreakable rules in the first priority.
Section 03
sw-superpower includes 13 interrelated skill modules, covering the full software development lifecycle:
Section 04
Section 05
Section 06
Section 07
Section 08
The design of sw-superpower follows a series of strict principles to ensure the reliability and practicality of the skills:
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.
This article introduces an open-source project for building modern large language models from scratch. The project evolves from a GPT-2-style basic architecture to a Llama 2/3-style production-level implementation, covering complete tutorial implementations of key technologies such as RMSNorm, RoPE, SwiGLU, GQA, and MoE.