#6565th of 98 in Skills, plugins and rules
superpowers-zh
Chinese translation of the superpowers skills set for AI coding tools
- Stars
- 8.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- JavaScript
Missed the latest GitHub check; these facts may be older.
Overview
Installs 21 skills (brainstorming, TDD, systematic debugging, code review, parallel agents) into 26 AI coding tools, including Claude Code, Cursor, Codex CLI, Gemini CLI and Windsurf. 15 are translations of upstream superpowers, 4 are manually invoked China-specific skills, and 2 are kept from upstream history. Installed with `npx superpowers-zh`, which detects the tool in use.
Who it is for: Chinese-speaking devs adding skills to Claude Code, Cursor, Codex
Strengths
- One `npx superpowers-zh` command detects the tool and installs skills, project or global scope
- Covers 26 tools versus 6 in the English upstream
- Also ships as a Claude Code plugin marketplace entry with hooks and bootstrap files
- Adds Gitee, Coding, GitLab CN and CNB workflow skills; upstream sections are translated, not altered
Weaknesses
- Skills and docs are in Chinese; English readers should use the upstream project
- The four China-specific skills load only when invoked manually, e.g. `/chinese-code-review`
- Manual `cp -r skills` install skips hooks and bootstrap, so skills do not auto-trigger
- README is crowded with sponsor banners and promo links
What it needs
- no GPU
- Needs Node.js (npx), An AI coding tool such as Claude Code or Cursor
Also in Skills, plugins and rules
See all 98| Rank | Project | Score |
|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 2 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| 3 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 94 out of 100 |
| #4 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 93 out of 100 |
| #5 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |