#402402nd of 455 in Skills, plugins and prompts
claude-code-skills-zh
Chinese-language index of Claude Code skills, plus 21 original skills
- Stars
- 905
- License
- MIT
- Last commit
- Nov 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
A curated index of 443+ third-party Claude Code Skills, Agents and Plugins, grouped by scenario with Chinese descriptions. It has separate categories for Chinese platforms such as WeChat official accounts, Xiaohongshu and Feishu. It also ships 21 original skills (zh-code-reviewer, zh-readme, api-tester, refactor-advisor, perf-profiler), installable through the Claude Code plugin marketplace or by copying into ~/.claude/skills.
Who it is for: Chinese-speaking developers looking for ready-to-install Claude Code skills
Strengths
- Installs original skills via /plugin marketplace add, or by copying folders to ~/.claude/skills
- Descriptions in Chinese, with a separate category for Feishu, Xiaohongshu and similar platforms
- 21 original skills cover code review, README writing, API testing, refactoring and profiling
- Entries note compatibility with Claude Code, Codex, Gemini CLI and Cursor
Weaknesses
- Most of the 443+ entries link to third-party repos, not code maintained here
- Plugin install requires Claude Code 2.1 or newer
- Counts disagree within the README: 20 vs 21 original skills, 438+ vs 443+ curated
- Original skills target Chinese-language output, less useful for English-only teams
What it needs
- no GPU
- Needs Claude Code 2.1+
- Models: Claude Code, Codex, Gemini CLI, Cursor
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |