jnMetaCode/superpowers-zh

🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活

What it solves

AI coding tools often lack structured workflows, leading to disorganized development, poor code quality, or lack of context. This project provides a standardized set of "skills"—methodologies like Test-Driven Development (TDD), systematic debugging, and structured brainstorming—that guide AI agents to work more reliably and professionally.

How it works

It acts as a localized, Chinese-enhanced fork of the popular superpowers framework. It installs a collection of 21 skills (15 translated from the original, 4 China-specific, and 2 restored legacy skills) into the configuration directories of 26 different AI coding tools (such as Cursor, Claude Code, Windsurf, and Aider). By placing these skill definitions into the project's local configuration, it forces the AI to follow specific protocols—such as asking clarifying questions before writing code or performing verification before marking a task as complete.

Who it’s for

It is designed for Chinese-speaking developers who use AI-powered coding assistants and want to improve the quality, consistency, and cultural relevance of the code generated by their tools. It is particularly useful for teams that need to adhere to specific Git workflows, documentation standards, or code review practices.

Highlights

  • Broad Compatibility: Supports 26 different AI coding tools, including IDEs, CLI agents, and plugins.
  • Standardized Workflows: Includes professional methodologies like TDD, systematic debugging, and parallel agent dispatching.
  • China-Specific Enhancements: Adds localized skills for Chinese code review standards, Git workflows, commit message conventions, and technical documentation.
  • Easy Installation: Provides a simple npx command to automatically detect the project's tools and install the necessary skill files.
  • Memory Management: Includes integration with engram to help AI tools maintain context across sessions.

Related

  • Project
    feiskyer/claude-code-settings

    A set of Claude Code plugins (skills & sub‑agents) that add brainstorming, deep research, GitHub issue/PR automation, image generation, translation, and more, with ready‑made config files for many LLM providers.

  • Project
    alchaincyf/huashu-skills

    huashu‑skills is a curated index of 57 Claude‑compatible *Agent Skills* (design, data, video, persona, etc.). 22 lightweight skills live in this repo; the rest are separate repos. Install with a one‑line `git clone` (or copy a sub‑folder), restart the agent, and the skill becomes usable. An included updater checks for newer versions. The collection provides ready‑made, plug‑in functionality for AI agents without writing code.

  • Project
    Yuan1z0825/nature-skills

    A library of 22 packaged AI-agent workflows ("skills") for academic research — paper reading, Nature-style writing, figure generation, reviewer responses, literature search, and patent drafting — installable into Claude Code, Codex, Chatbox, and other agents.

  • Project
    HughYau/qiushi-skill

    Qiushi‑Skill is a plug‑in library that adds nine philosophically‑derived reasoning methods (e.g., contradiction analysis, investigation‑first, mass‑line) to AI agents such as Claude Code, Cursor, and Codex. Installed via `npx qiushi-skill` or the Claude Code marketplace, it injects a lightweight kernel that enforces the principle “seek truth from facts” and routes tasks to the appropriate skill. Each skill provides trigger rules, step‑by‑step actions, output templates, hard constraints, and hand‑off specs, plus reference texts and optional sub‑agents for investigation or self‑criticism. The project aims to make agents more evidence‑driven, self‑critical, and strategically focused.