Repository
jnMetaCode/superpowers-zh agent skills
- skills
- 21
- GitHub stars
- 8.3k
GitHub description: “🦸 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”
- Stars
- 8,265 (771 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Mar 2026
- Homepage
- sp.aiolaola.com
- ai-coding
- chinese
- claude-code
- cursor
- mcp
- skills
- superpowers
- tdd
- agent-skills
- agentic-coding
- code-review
- kiro
- npm-package
- prompt-engineering
- trae
- gemini-cli
Install all skills
npx skills add jnMetaCode/superpowers-zhAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in jnMetaCode/superpowers-zh, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate. | jnMetaCode/ | 8.3k | — | ~1.8k | Automated safety check: Pass | MIT | 3 days ago |
| 2 | Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese. | jnMetaCode/ | 8.3k | 1 repo | ~982 | Automated safety check: Pass | MIT | 3 days ago |
| 3 | Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end. | jnMetaCode/ | 8.3k | — | ~2.5k | Automated safety check: Pass | MIT | 3 days ago |
| 4 | Runs agency-orchestrator YAML workflows inside the current agent session, with the session's own model playing each role in turn and no API key needed. | jnMetaCode/ | 8.3k | 1 repo | ~885 | Automated safety check: Pass | MIT | 3 days ago |
| 5 | Gives Chinese-language templates and priority labels for code review feedback, plus guidance on bilingual comments, commit messages and common team anti-patterns. | jnMetaCode/ | 8.3k | — | ~1.2k | Automated safety check: Pass | MIT | 3 days ago |
| 6 | Reference for Chinese-language git commits and changelogs: Conventional Commits adapted for Chinese teams, with templates, breaking-change notes and issue links for several platforms. | jnMetaCode/ | 8.3k | — | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 7 | Reference rules for typesetting Chinese technical documents: spacing around English and digits, punctuation, term handling, bilingual API docs and README layout. | jnMetaCode/ | 8.3k | — | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 8 | Methodology for designing, implementing and testing Model Context Protocol servers in TypeScript or Python, covering tool design, error handling and security, in Chinese. | jnMetaCode/ | 8.3k | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 9 | Guides how an agent handles code review feedback: verify each suggestion against the codebase, ask about unclear items first, and push back with technical reasons when needed. | jnMetaCode/ | 8.3k | — | ~707 | Automated safety check: Pass | MIT | 3 days ago |
| 10 | Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output. | jnMetaCode/ | 8.3k | — | ~443 | Automated safety check: Pass | MIT | 3 days ago |
| 11 | Reference for setting up Git on Gitee, Coding.net, JiHu GitLab and CNB, with branching models, branch naming and CI differences for teams in China. | jnMetaCode/ | 8.3k | — | ~2.4k | Automated safety check: Warn | MIT | 3 days ago |
| 12 | Investigates what went wrong in a superpowers session by reading its transcript, reports findings with path and line citations, and can draft a GitHub issue or redacted bundle. | jnMetaCode/ | 8.3k | — | ~858 | Automated safety check: Pass | MIT | 3 days ago |
| 13 | 在开始任何对话时使用——确立如何查找和使用技能，要求在任何响应（包括澄清性问题）之前调用 Skill 工具. An agent skill from jnMetaCode/superpowers-zh. | jnMetaCode/ | 8.3k | — | ~679 | Automated safety check: Pass | MIT | 3 days ago |
| 14 | 当在当前会话中执行包含独立任务的实现计划时使用 | jnMetaCode/ | 8.3k | — | ~3.8k | Automated safety check: Pass | MIT | 3 days ago |
| 15 | 当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用 | jnMetaCode/ | 8.3k | — | ~778 | Automated safety check: Pass | MIT | 3 days ago |
| 16 | 当实现完成、所有测试通过、需要决定如何集成这份工作时使用 | jnMetaCode/ | 8.3k | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 17 | 完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求 | jnMetaCode/ | 8.3k | — | ~416 | Automated safety check: Pass | MIT | 3 days ago |
| 18 | 遇到任何 bug、测试失败或异常行为时使用，在提出修复方案之前执行 | jnMetaCode/ | 8.3k | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 19 | 在实现任何功能或修复 bug 时使用，在编写实现代码之前 | jnMetaCode/ | 8.3k | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 20 | 当你有规格说明或需求用于多步骤任务时使用，在动手写代码之前 | jnMetaCode/ | 8.3k | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 21 | 当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用 | jnMetaCode/ | 8.3k | — | ~3.2k | Automated safety check: Pass | MIT | 3 days ago |
Questions, answered from the data.
What is the best skill in jnMetaCode/superpowers-zh?
Brainstorming Before Building from jnMetaCode/superpowers-zh ranks first of the 21 skills in jnMetaCode/superpowers-zh listed here, with the highest score: its repository has 8.3k GitHub stars, its SKILL.md loads about 1.8k tokens and it passes the automated safety check with no findings. Next come Git Worktree Isolation and Inline Plan Execution.
Are the skills in jnMetaCode/superpowers-zh official?
None yet. All 21 skills in jnMetaCode/superpowers-zh listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from jnMetaCode/superpowers-zh?
Run npx skills add jnMetaCode/superpowers-zh in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.