Reading
A skill repository for AI tools like Codex, Claude Code, OpenClaw, etc., covering 15 categories including development engineering, DevOps, financial investment, product design, etc., and providing directly reusable scripts and automated workflows.
Section 01
A skill repository for AI tools like Codex, Claude Code, OpenClaw, etc., covering 15 categories including development engineering, DevOps, financial investment, product design, etc., and providing directly reusable scripts and automated workflows.
Section 02
The goal of this repository is to become the "skill hub" for Chinese AI developers, addressing the following core pain points:
Reduce repetitive work: Developers no longer need to rewrite prompts or scripts for each common task; they can directly reuse verified skills.
Multi-tool compatibility: Skills are designed to be compatible with multiple AI tools like Codex, Claude Code, OpenClaw, avoiding lock-in to a single platform.
Ready-to-use: Many skills not only include documentation but also come with scripts/, references/, assets/ directories, which can be copied and used directly.
Continuous operation: Unlike static resources collected once, the repository has established a complete automated pipeline supporting new skill discovery, upstream synchronization, quality verification, and view generation.
Section 03
The repository divides skills into 15 categories based on application scenarios, each with a clear positioning and target users:
Section 04
Covers development, testing, performance optimization, code review, database and architecture design. Representative skills include codebase-onboarding (quick codebase onboarding), gh-fix-ci (CI failure repair), etc.
Section 05
Focuses on release management, monitoring and alerting, incident response, CI/CD processes, and environment management. Helps operation teams automate repetitive work.
Section 06
For scenarios like content operation, attribution analysis, competitor analysis on social media platforms such as Xiaohongshu, suitable for marketing and operation personnel.
Section 07
Provides skills such as financial data collection, valuation analysis, risk control, backtesting frameworks, and investment research report writing, serving quantitative investment and financial analysis scenarios.
Section 08
Covers daily high-frequency tasks for white-collar workers such as Word, Excel, PPT, PDF processing, and meeting minutes organization.
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.
A self-hosted MCP server that provides cross-session persistent coordination, task management, event bus, and observability for AI agents. It supports 35 tools and can be integrated into clients like Claude Code and Cursor with zero code changes.