#170 by GitHub stars
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
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/brainstorming/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/chinese-code-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/chinese-commit-conventions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/chinese-documentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/chinese-git-workflow/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/diagnosing-superpowers/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/dispatching-parallel-agents/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/executing-plans/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/finishing-a-development-branch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/mcp-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/receiving-code-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/requesting-code-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/subagent-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/systematic-debugging/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/test-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/using-git-worktrees/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/using-superpowers/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/verification-before-completion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/workflow-runner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/writing-plans/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 020339d1410e
No earlier version was observed for comparison.
skills/writing-skills/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
020339d1410e → 020339d1410e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 020339d1410e
No earlier version was observed for comparison.
Verified commit 020339d1410e51a9eca16d26f4eac4cfee166d8a
git clone --filter=blob:none --no-checkout https://github.com/jnMetaCode/superpowers-zh.git .hotskills/jnmetacode-superpowers-zh && git -C .hotskills/jnmetacode-superpowers-zh checkout --detach 020339d1410e51a9eca16d26f4eac4cfee166d8a
# Copy each selected skill directory from .hotskills/jnmetacode-superpowers-zh into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/jnMetaCode/superpowers-zh.git .hotskills/jnmetacode-superpowers-zh && git -C .hotskills/jnmetacode-superpowers-zh checkout --detach 020339d1410e51a9eca16d26f4eac4cfee166d8a
# Copy each selected skill directory from .hotskills/jnmetacode-superpowers-zh into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/jnMetaCode/superpowers-zh.git .hotskills/jnmetacode-superpowers-zh && git -C .hotskills/jnmetacode-superpowers-zh checkout --detach 020339d1410e51a9eca16d26f4eac4cfee166d8a
# Copy each selected skill directory from .hotskills/jnmetacode-superpowers-zh into .gemini/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/jnMetaCode/superpowers-zh.git .hotskills/jnmetacode-superpowers-zh && git -C .hotskills/jnmetacode-superpowers-zh checkout --detach 020339d1410e51a9eca16d26f4eac4cfee166d8a
# Copy each selected skill directory from .hotskills/jnmetacode-superpowers-zh into .opencode/skills/<skill-name>/Heat
6.8- Star growth, last 7 daysAhead of 79% of tracked repositories
- Star growth, last 24 hoursAhead of 83% of tracked repositories
- Rank movement, last 7 daysAhead of 64% of tracked repositories
- Commits, last 30 daysAhead of 86% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- brainstorming
skills/brainstorming - chinese-code-review
skills/chinese-code-review - chinese-commit-conventions
skills/chinese-commit-conventions - chinese-documentation
skills/chinese-documentation - chinese-git-workflow
skills/chinese-git-workflow - diagnosing-superpowers
skills/diagnosing-superpowers - dispatching-parallel-agents
skills/dispatching-parallel-agents - executing-plans
skills/executing-plans - finishing-a-development-branch
skills/finishing-a-development-branch - mcp-builder
skills/mcp-builder - receiving-code-review
skills/receiving-code-review - requesting-code-review
skills/requesting-code-review - subagent-driven-development
skills/subagent-driven-development - systematic-debugging
skills/systematic-debugging - test-driven-development
skills/test-driven-development - using-git-worktrees
skills/using-git-worktrees - using-superpowers
skills/using-superpowers - verification-before-completion
skills/verification-before-completion - workflow-runner
skills/workflow-runner - writing-plans
skills/writing-plans - writing-skills
skills/writing-skills
How it works
brainstorming
When your agent uses it
在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能、修改行为,或筹划任何新东西,无论是软件还是软件之外(一场分享、一门生意、一次装修)。
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
2,892 tokensWhen the skill is activated
Reference documents
3,773 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 首先:你到底知道多少?
- 你的第一条消息
- 对话
- 复述给对方
- 判断工作规模
- 书面设计
- 危险信号
- 视觉伴侣
Scripts executed separately
scripts/helper.jsscripts/server.cjsscripts/start-server.shscripts/stop-server.sh
Files
../../.claude-plugin/marketplace.jsonasset696 bytes../../.claude-plugin/plugin.jsonasset592 bytes../../hooks/hooks.jsonasset334 bytesSKILL.mdcore11,099 bytesbuilder-check-prompt.mddoc911 bytesscripts/frame-template.htmlasset8,094 bytesscripts/helper.jsruns5,615 bytesscripts/server.cjsruns25,699 bytesscripts/start-server.shruns6,908 bytesscripts/stop-server.shruns3,263 bytesvisual-companion.mddoc12,908 bytes
Read SKILL.md
# 头脑风暴
你非常擅长构建。你会去构建你认为你的人类伙伴想要的东西,而这个"认为"通常比你感觉到的要单薄。这个技能的用途,是在动手构建任何东西之前,弄清他们真正想要什么、以及为什么。
人们常常还没想清楚自己想要什么。好的问题能帮他们把它想透。当你理解了背后的原因,那上百个他们从没提过的决定,你就会按他们自己会做的方式去做。
## 首先:你到底知道多少?
回复之前,先问自己:关于他们想要什么、为什么想要,我知道些什么?
- **要紧的信息都在请求里了**("把图标改成矢车菊蓝")。这是一个快速、明确的任务。直接做,并说明你做了什么。
- **缺了某些不简单的东西。** 开始对话。
## 你的第一条消息View the complete source on GitHubchinese-code-review
When your agent uses it
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
2,592 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 审查反馈的表达方式
- 中英混排代码注释规范
- Commit Message 中英双语格式
- 常见反模式与对策
- 审查流程建议
- 检查清单
Files
SKILL.mdcore9,308 bytes
Read SKILL.md
# 中文代码审查规范
## 概述
国内团队做 Code Review 常遇到两个极端:要么过度客气导致关键问题被放过,要么照搬西方直白风格让同事下不来台。本技能帮你找到平衡点——**既不回避问题,又让人愿意接受反馈**。
**核心原则:** 用"建议"代替"命令",用"提问"代替"否定",但绝不因为面子而放过 bug。
## 审查反馈的表达方式
### 用建议代替命令
| 避免(命令式) | 推荐(建议式) |
|---------------|---------------|View the complete source on GitHubchinese-commit-conventions
When your agent uses it
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
2,722 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Conventional Commits 中文适配
- 2. 中文 commit message 模板
- 3. Subject 行规范
- 4. Body 编写规范
- 5. Breaking Changes 标注
- 6. Issue 关联
- 7. Changelog 自动生成配置
- 8. commitlint 中文配置
- 9. husky + lint-staged 集成
- 10. 团队规范检查清单
Files
SKILL.mdcore9,502 bytesSKILL.mdcore9,502 bytesSKILL.mdcore9,502 bytesSKILL.mdcore9,502 bytesSKILL.mdcore9,502 bytesSKILL.mdcore9,502 bytesSKILL.mdcore9,502 bytes
Read SKILL.md
# 中文 Git 提交规范
## 1. Conventional Commits 中文适配
基于 Conventional Commits 1.0.0 规范,针对中文团队的实际使用习惯进行适配。
### 类型(type)定义
| 类型 | 说明 | 示例场景 |
| ---------- | ---------------------------- | -------------------------- |
| `feat` | 新功能 | 添加用户注册模块 |
| `fix` | 修复缺陷 | 修复登录页白屏问题 |
| `docs` | 文档变更 | 更新 API 接口文档 |
| `style` | 代码格式(不影响逻辑) | 调整缩进、补充分号 |View the complete source on GitHubchinese-documentation
When your agent uses it
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
3,175 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 中文排版规范
- 中英混排最佳实践
- API 文档中英对照格式
- README.md 中文模板
- 常见问题与避坑指南
- 写作检查清单
Files
SKILL.mdcore10,903 bytesSKILL.mdcore10,903 bytesSKILL.mdcore10,903 bytes
Read SKILL.md
# 中文技术文档写作规范
## 概述
中文技术文档最常见的问题不是内容不够,而是**读起来别扭**——中英文挤在一起没有空格、全角半角混用、一股机翻味。本技能提供一套完整的中文技术文档写作规范,让你的文档**专业、好读、不出戏**。
**核心原则:** 排版服务于阅读体验,规范服务于一致性,内容服务于读者。
**参考标准:** [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines)
## 中文排版规范
### 空格
View the complete source on GitHubchinese-git-workflow
When your agent uses it
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
3,755 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 国内 Git 平台适配
- 工作流选择
- 分支命名规范
- 中文 Commit Message 规范
- CI/CD 平台适配
- PR/MR 描述模板
- 常用 Git 配置
- 检查清单
Files
SKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytesSKILL.mdcore13,510 bytes
Read SKILL.md
# 国内 Git 工作流规范
## 概述
国内团队用 Git 经常踩的坑:GitHub 访问不稳定、CI/CD 方案照搬国外水土不服、commit message 中英混杂没有规范。本技能提供一套**完整适配国内平台和团队习惯的 Git 工作流**。
**核心原则:** 工作流服务于团队效率,不是为了流程而流程。选适合团队规模的,别硬套大厂方案。
## 国内 Git 平台适配
### 平台对比
| 特性 | Gitee | Coding.net | 极狐 GitLab | CNB | GitHub |
|------|-------|------------|-------------|-----|--------|View the complete source on GitHubdiagnosing-superpowers
When your agent uses it
当一次 superpowers 会话出了问题、你的人类伙伴想知道原因时使用——重复劳动、无视计划、磕磕绊绊、结果质量差、某个技能没触发、"太慢了"、"为什么这么贵"、"它到底在干什么"——或者想给 superpowers 维护者整理一份 bug 报告;适用于当前会话,或按 id / 路径指定的过往会话,任何工具均可
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,007 tokensWhen the skill is activated
Reference documents
9,464 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 工作流
- 速查
- 硬性规则
- 危险信号
Files
SKILL.mdcore7,195 bytesprompts/analyst-common.mddoc1,645 bytesprompts/cost-and-time.mddoc1,589 bytesprompts/plan-adherence.mddoc1,690 bytesprompts/quality-evidence.mddoc1,543 bytesprompts/repeated-work.mddoc1,448 bytesprompts/request-conflicts.mddoc974 bytesprompts/scrub-audit.mddoc1,326 bytesprompts/scrub.mddoc1,429 bytesprompts/similar-session.mddoc1,699 bytesprompts/skill-timeline.mddoc1,645 bytesprompts/stumbles.mddoc1,382 bytesreferences/context-safety.mddoc979 bytesreferences/github-issues.mddoc1,889 bytesreferences/redaction-policy.mddoc2,156 bytesreferences/session-discovery.mddoc1,641 bytestemplates/bundle-README.mddoc3,618 bytestemplates/case.mddoc2,991 bytestemplates/issue.mddoc1,822 bytestemplates/report.mddoc2,409 bytes
Read SKILL.md
# 诊断 Superpowers
## 概述
和你的人类伙伴一起明确一次会话到底哪里出了问题,读取磁盘上的会话记录(transcript),
用证据报告发生了什么。你负责报告,不负责诊断 superpowers。superpowers 要不要改,
由分诊这份打包材料或这条 issue 的人决定。
**核心原则:** 每条发现都要引用 `path:line`。没有引用,就不算发现。每个数字都来自
会话记录或你亲自跑过的命令,绝不凭记忆。
## 工作流
每一步建一个待办。第 5–7 步只在各自注明的条件下执行。View the complete source on GitHubdispatching-parallel-agents
When your agent uses it
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
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
1,716 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 何时使用
- 模式
- 智能体提示词结构
- 常见错误
- 不适用的场景
- 实际案例
- 验证
Files
SKILL.mdcore6,044 bytes
Read SKILL.md
# 并行分派智能体
## 概述
你将任务委派给具有隔离上下文的专用智能体。通过精心设计它们的指令和上下文,确保它们专注并成功完成任务。它们不应继承你的会话上下文或历史记录——你要精确构造它们所需的一切。这样也能为你自己保留用于协调工作的上下文。
当你遇到多个不相关的失败(不同的测试文件、不同的子系统、不同的 bug),逐一排查会浪费时间。每个排查都是独立的,可以并行进行。
**核心原则:** 每个独立问题域分派一个智能体,让它们并发工作。
## 何时使用
```dot
digraph when_to_use {View the complete source on GitHubexecuting-plans
When your agent uses it
当你要在当前会话里亲自担任实现者执行一份实现计划时使用——你的人类伙伴选择了内联执行,或者没有可用的子智能体工具
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
5,663 tokensWhen the skill is activated
Reference documents
1,723 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时使用
- 流程
- 准备
- 任务循环
- 最终审查
- 收尾
- 常见的合理化借口
- 示例工作流
Scripts executed separately
scripts/task-donescripts/task-start../subagent-driven-development/scripts/review-package../subagent-driven-development/scripts/sdd-workspace
Files
SKILL.mdcore20,937 bytesscripts/task-doneruns1,692 bytesscripts/task-startruns963 bytes../requesting-code-review/code-reviewer.mddoc6,196 bytes../subagent-driven-development/scripts/review-packageruns2,029 bytes../subagent-driven-development/scripts/sdd-workspaceruns3,684 bytes
Read SKILL.md
# 执行计划
在本会话里亲自执行计划,一个任务接一个任务:不为每个任务派实现子智能体,也不为每个任务派审查者。只在最后对整个分支做一次全新上下文的审查。
**为什么内联:** 子智能体驱动开发为每个任务付一个全新实现者和一个全新审查者的钱,每一个都要从零重读代码库。内联执行只付一个上下文(你自己的)外加最后一个审查者。它放弃的是每个任务一份全新上下文、每个任务第二双眼睛。本技能用别的办法保住那两样东西换来的好处:简报就是规格,账本就是你的记忆,TDD 是每个任务的关卡,最终审查者就是第二双眼睛。
**核心原则:** 计划已经把该想的都想过了。严格照它执行,每一步都用一个你亲眼看着失败、又亲眼看着通过的测试来证明,并留下一份在你自己遗忘之后依然存在的记录。
**旁白:** 工具调用之间最多说一句简短的旁白——账本和工具结果本身就是记录。
**持续执行:** 不要在任务之间停下来向你的人类伙伴确认。他们选内联执行是为了少花钱,不是为了每做完一个任务就回答一次"我该继续吗?"。不间断地执行计划里的所有任务。
**做裁决,不要停摆。** 冲突、歧义、计划缺陷——你自己定。规格是有约束力的权威,计划是它的论证,两者都答不上来的部分由你的判断来定。每个决定都以 `Ruling: <你决定了什么> — <为什么> — <如果错了代价是什么>` 记进账本,然后继续。没有记进账本的裁决就偏离计划,等于一个暗中做出的决定。
View the complete source on GitHubfinishing-a-development-branch
When your agent uses it
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
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
2,412 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 步骤 1:验证测试
- 步骤 2:检测环境
- 步骤 3:确定基础分支
- 步骤 4:展示选项
- 步骤 5:执行选择
- 步骤 6:清理工作区
- 快速参考
- 常见的合理化借口
Files
SKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytesSKILL.mdcore8,238 bytes
Read SKILL.md
# 收尾一个开发分支
## 概述
**核心原则:** 验证测试 → 检测环境 → 展示选项 → 执行选择 → 清理。
**开始时宣告:** "我正在使用 finishing-a-development-branch 技能来收尾这份工作。"
## 步骤 1:验证测试
运行项目的完整测试套件(`npm test` / `cargo test` / `pytest` / `go test ./...`)。
**如果测试失败**,报告失败并停下——菜单是在测试全绿之后才出现的:
View the complete source on GitHubmcp-builder
When your agent uses it
在构建 MCP 服务器或 MCP 工具时使用 —— 系统化的生产级 MCP 构建方法论,覆盖工具设计、错误处理、传输层选择与测试,让 AI 助手连接外部能力
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
2,234 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 协议核心概念
- 2. 项目结构规范
- 3. Tool 设计原则
- 4. 输入验证和错误处理
- 5. 资源管理和生命周期
- 6. 测试策略
- 7. 安全考虑
- 8. 部署和分发
- 9. 调试技巧
- 10. 构建检查清单
Files
SKILL.mdcore7,986 bytesSKILL.mdcore7,986 bytesSKILL.mdcore7,986 bytes
Read SKILL.md
# MCP 服务器构建
系统化设计、实现、测试和部署 Model Context Protocol 服务器的方法论。
## 1. 协议核心概念
MCP 定义三种原语:
- **Tools(工具)**:AI 助手主动调用的函数,有副作用。如搜索、创建、删除操作。
- **Resources(资源)**:AI 助手只读访问的数据源,用 URI 标识。如 `users://{id}/profile`。
- **Prompts(提示词模板)**:预定义交互模板,引导用户触发工作流。
**选择原则:** 执行操作 → Tool | 读取数据 → Resource | 引导交互 → Prompt
View the complete source on GitHubreceiving-code-review
When your agent uses it
收到代码审查反馈后、实施建议之前使用,尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证,而非敷衍附和或盲目执行
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,891 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 响应模式
- 禁止的回应
- 处理不明确的反馈
- 按来源区别处理
- YAGNI 检查——针对"专业化"功能建议
- 实施顺序
- 何时反驳
- 确认正确的反馈
- 优雅地纠正自己的反驳
- 常见错误
- 真实案例
- GitHub 评论回复
Files
SKILL.mdcore6,216 bytes
Read SKILL.md
# 接收代码审查
## 概述
代码审查需要的是技术评估,不是情绪表演。
**核心原则:** 先验证再实施。先提问再假设。技术正确性优先于社交舒适度。
## 响应模式
```
收到代码审查反馈时:
1. 阅读:完整阅读反馈,不急于反应View the complete source on GitHubrequesting-code-review
When your agent uses it
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
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
852 tokensWhen the skill is activated
Reference documents
1,723 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时请求审查
- 如何请求
- 示例
- 常见的合理化借口
- 红线
Files
SKILL.mdcore2,938 bytesSKILL.mdcore2,938 bytescode-reviewer.mddoc6,196 bytes
Read SKILL.md
# 请求代码审查
派遣代码审查子代理,在问题扩散之前发现它们。审查者获得的是精心组织的评估上下文——绝不是你的会话历史。
**核心原则:** 早审查,勤审查。
## 何时请求审查
**必须审查:**
- 子代理驱动开发中每个任务完成后
- 完成重要功能后
- 合并到 main 之前
**可选但有价值:**View the complete source on GitHubsubagent-driven-development
When your agent uses it
当在当前会话中执行包含独立任务的实现计划时使用
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
9,207 tokensWhen the skill is activated
Reference documents
7,231 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时使用
- 流程
- 准备
- 模型选择
- 任务循环
- 最终审查
- 收尾
- 常见的合理化借口
- 示例工作流
Scripts executed separately
scripts/review-packagescripts/sdd-workspacescripts/task-brief
Files
../requesting-code-review/code-reviewer.mddoc6,196 bytesSKILL.mdcore32,976 bytesimplementer-prompt.mddoc6,175 bytesre-review-prompt.mddoc4,999 bytesscripts/review-packageruns2,029 bytesscripts/sdd-workspaceruns3,684 bytesscripts/task-briefruns1,580 bytestask-reviewer-prompt.mddoc9,106 bytes
Read SKILL.md
# 子智能体驱动开发
通过为每个任务分派一个全新的实现子智能体来执行计划:每个任务完成后做一次任务审查(规格合规性 + 代码质量),全部任务结束后再做一次覆盖整个分支的宽范围审查。
**为什么用子智能体:** 你把任务委派给具有隔离上下文的专用智能体。通过精心设计它们的指令和上下文,确保它们专注并成功完成任务。它们绝不应继承你会话的上下文或历史记录——你要精确构造它们所需的一切。这样也能为你自己保留用于协调工作的上下文。
**核心原则:** 每个任务一个全新子智能体 + 任务审查(规格 + 质量)+ 结尾宽范围审查 = 高质量、快速迭代
**旁白:** 工具调用之间最多说一句简短的旁白——进度账本和工具结果本身就是记录。
**持续执行:** 不要在任务之间停下来向你的人类伙伴确认。不间断地执行计划里的所有任务。唯一该停下的理由是:你无法解决的 BLOCKED 状态、确实妨碍推进的歧义,或所有任务已完成。"我该继续吗?"之类的询问和进度小结都在浪费他们的时间——他们让你执行计划,那就执行。
**做裁决,不要停摆。** 一个正在跑的计划不等人。冲突、歧义、计划缺陷、你本来想申请突破的上限——你自己定。规格是有约束力的权威,计划是它的论证,两者都答不上来的部分由你的判断来定。每个决定都以 `Ruling: <你决定了什么> — <为什么> — <如果错了代价是什么>` 记进账本,然后继续。一个错误的裁决,代价是你人类伙伴看得见、也撤得掉的返工;一个停在问题上的会话,代价是他们的一整天,而且什么也换不来。
View the complete source on GitHubsystematic-debugging
When your agent uses it
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
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
2,768 tokensWhen the skill is activated
Reference documents
6,388 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 铁律
- 何时使用
- 四个阶段
- 红线——停下来,按流程走
- 搭档发出的信号——说明你的方法不对
- 常见借口
- 速查表
- 当流程显示"找不到根因"
- 辅助技术
Scripts executed separately
condition-based-waiting-example.tsfind-polluter.sh
Files
CREATION-LOG.mddoc4,257 bytesSKILL.mdcore9,462 bytesSKILL.mdcore9,462 bytescondition-based-waiting-example.tsruns5,054 bytescondition-based-waiting.mddoc3,598 bytesdefense-in-depth.mddoc3,704 bytesfind-polluter.shruns1,986 bytesroot-cause-tracing.mddoc5,433 bytestest-academic.mddoc653 bytestest-pressure-1.mddoc1,900 bytestest-pressure-2.mddoc2,283 bytestest-pressure-3.mddoc2,692 bytes
Read SKILL.md
# 系统化调试
## 概述
**核心原则:** 在尝试修复之前,务必先找到根本原因。只修症状就是失败。
**敷衍走流程等于违背调试的精神。**
## 铁律
```
不做根因调查,不许提修复方案
```
View the complete source on GitHubtest-driven-development
When your agent uses it
在实现任何功能或修复 bug 时使用,在编写实现代码之前
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
2,814 tokensWhen the skill is activated
Reference documents
2,357 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 何时使用
- 铁律
- 红-绿-重构
- 好的测试
- 常见借口
- 危险信号 - 停下来,从头开始
- 示例:Bug 修复
- 验证清单
- 遇到困难时
- 调试集成
- 最终规则
Files
SKILL.mdcore10,095 bytesSKILL.mdcore10,095 bytesSKILL.mdcore10,095 bytesSKILL.mdcore10,095 bytesSKILL.mdcore10,095 byteswriting-good-tests.mddoc8,670 bytes
Read SKILL.md
# 测试驱动开发(TDD)
## 概述
先写测试。看它失败。写最少的代码让它通过。
**核心原则:** 如果你没有看到测试失败,你就不知道它是否测试了正确的东西。
**违反规则的字面意思就是违反规则的精神。**
## 何时使用
**始终使用:**
- 新功能View the complete source on GitHubusing-git-worktrees
When your agent uses it
当需要开始与当前工作区隔离的功能开发,或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,919 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 步骤 0:检测现有隔离
- 步骤 1:创建隔离工作区
- 步骤 2:项目设置
- 步骤 3:验证基线干净
- 快速参考
- 常见的合理化借口
Files
SKILL.mdcore6,789 bytesSKILL.mdcore6,789 bytesSKILL.mdcore6,789 bytesSKILL.mdcore6,789 bytesSKILL.mdcore6,789 bytesSKILL.mdcore6,789 bytesSKILL.mdcore6,789 bytesSKILL.mdcore6,789 bytes
Read SKILL.md
# 使用 Git 工作树
## 概述
确保工作发生在隔离的工作区中。优先使用你的平台的原生 worktree 工具。仅在没有原生工具可用时,再回退到手动 git worktree。
**核心原则:** 先检测现有隔离。然后用原生工具。再回退到 git。绝不与 harness 对抗。
**开始时宣布:** "我正在使用 using-git-worktrees 技能来建立一个隔离的工作区。"
## 步骤 0:检测现有隔离
**创建任何东西之前,先检查你是否已经在一个隔离的工作区里。**
View the complete source on GitHubusing-superpowers
When your agent uses it
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
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,354 tokensWhen the skill is activated
Reference documents
7,527 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 规则
- 技能优先级
- 红线
- 平台适配
- 中国特色技能路由
- 用户指令
Files
SKILL.mdcore5,095 bytesreferences/antigravity-tools.mddoc1,595 bytesreferences/claude-code-tools.mddoc1,514 bytesreferences/codex-tools.mddoc5,932 bytesreferences/copilot-tools.mddoc3,936 bytesreferences/gemini-tools.mddoc4,609 bytesreferences/hermes-tools.mddoc2,314 bytesreferences/muse-tools.mddoc2,021 bytesreferences/pi-tools.mddoc2,035 bytesreferences/qoder-tools.mddoc3,138 bytes
Read SKILL.md
<SUBAGENT-STOP>
如果你是作为子智能体被分派来执行特定任务的,忽略此技能。
</SUBAGENT-STOP>
<EXTREMELY-IMPORTANT>
如果你认为哪怕只有 1% 的可能性某个技能适用于你正在做的事情,你绝对必须调用该技能。
如果一个技能适用于你的任务,你没有选择。你必须使用它。
这不可协商。你不能通过合理化来逃避。
</EXTREMELY-IMPORTANT>
## 规则
View the complete source on GitHubverification-before-completion
When your agent uses it
在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,106 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 铁律
- 门控函数
- 常见失败模式
- 红线——停下来
- 防止合理化
- 关键模式
- 何时使用
Files
SKILL.mdcore3,624 bytes
Read SKILL.md
# 完成前验证
## 概述
**核心原则:** 始终用证据支撑结论。
**对这条规则敷衍了事,就等于违背了它的精神。**
## 铁律
```
没有新鲜的验证证据,不许宣称完成
```
View the complete source on GitHubworkflow-runner
When your agent uses it
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key,使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,728 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用场景
- 执行流程(5 步)
- 重要规则
- 没有 YAML 文件时的快捷模式
- 故障处理
Files
SKILL.mdcore6,193 bytes
Read SKILL.md
# 工作流执行器:在 AI 工具内运行多角色编排
直接在当前会话中执行 agency-orchestrator 的 YAML 工作流,无需配置 API key。当前 LLM 就是执行引擎——依次扮演每个角色完成任务。
## 适用场景
- 用户提供了一个 `.yaml` 工作流文件(如 `运行 workflows/story-creation.yaml`)
- 用户要求多个角色协作完成任务(如"用产品经理和架构师一起评审这个 PRD")
- 用户安装了 `agency-agents-zh` 并希望直接在 AI 工具内编排多角色
## 执行流程(5 步)
按以下顺序执行,不要跳步:
View the complete source on GitHubwriting-plans
When your agent uses it
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
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
2,560 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 范围检查
- 文件结构
- 任务粒度定界
- 步骤粒度
- 计划文档头部
- 任务结构
- 一个步骤包含什么
- 自检
- 执行交接
Files
SKILL.mdcore9,853 bytesSKILL.mdcore9,853 bytesSKILL.mdcore9,853 bytes
Read SKILL.md
# 编写计划
## 概述
为一位没见过这个代码库、也没见过这份规格的工程师编写实现计划。假设他们一旦知道确切的接口和确切的测试,就能用项目所用的语言写出地道的代码;也假设在计划留出选择余地的地方,他们会做出合理的选择。他们无从知道的,是你已经决定了什么:哪些文件、哪些名字和签名、规格里的哪些取值、哪些测试证明每个任务。把这些记下来。将整个计划拆成小步骤任务。DRY。YAGNI。TDD。频繁 commit。
**开始时宣布:** "我正在使用 writing-plans 技能创建实现计划。"
**上下文:** 此技能应在专用 worktree 中运行(由 brainstorming 技能创建)。
**计划保存位置:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
- (用户对计划位置的偏好优先于此默认值)
## 范围检查View the complete source on GitHubwriting-skills
When your agent uses it
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
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
7,145 tokensWhen the skill is activated
Reference documents
21,433 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 什么是技能?
- TDD 映射到技能
- 何时创建技能
- 技能类型
- 目录结构
- SKILL.md 结构
- 技能发现优化(SDO)
- 流程图使用
- 代码示例
- 文件组织
- 铁律(与 TDD 相同)
- 测试所有技能类型
- 跳过测试的常见合理化借口
- 让形式匹配失败类型
- 让技能经受住合理化的考验
- 技能的红-绿-重构
- 反模式
- 停下:进入下一个技能之前
- 技能创建清单(TDD 适配版)
- 发现工作流
Scripts executed separately
render-graphs.js
Files
../using-superpowers/references/codex-tools.mddoc5,932 bytes../using-superpowers/references/gemini-tools.mddoc4,609 bytesSKILL.mdcore25,561 bytesSKILL.mdcore25,561 bytesSKILL.mdcore25,561 bytesSKILL.mdcore25,561 bytesSKILL.mdcore25,561 bytesSKILL.mdcore25,561 bytesanthropic-best-practices.mddoc42,446 bytesexamples/CLAUDE_MD_TESTING.mddoc5,423 bytesgraphviz-conventions.dotasset5,970 bytespersuasion-principles.mddoc5,387 bytesrender-graphs.jsruns5,633 bytestesting-skills-with-subagents.mddoc12,389 bytes
Read SKILL.md
# 编写技能
## 概述
**编写技能就是将测试驱动开发应用于流程文档。**
**个人技能存放在你所用运行环境的技能目录中**(Claude Code 上是 `~/.claude/skills/`)——其他运行环境的路径见 [codex-tools.md](../using-superpowers/references/codex-tools.md) 或 [gemini-tools.md](../using-superpowers/references/gemini-tools.md)。Codex、Copilot CLI 和 Gemini CLI 也都认 `~/.agents/skills/`,作为跨运行环境的别名。
你编写测试用例(带子智能体的压力场景),观察它们失败(基线行为),编写技能(文档),观察测试通过(智能体遵守规则),然后重构(堵住漏洞)。
**核心原则:** 如果你没有观察到智能体在没有该技能时失败,你就不知道这个技能是否教了正确的东西。
**必需背景:** 在使用此技能前,你必须理解 test-driven-development。该技能定义了基本的红-绿-重构循环。本技能将 TDD 适配到文档编写中。
View the complete source on GitHubSkills included
- brainstorming
- chinese-code-review
- chinese-commit-conventions
- chinese-documentation
- chinese-git-workflow
- diagnosing-superpowers
- dispatching-parallel-agents
- executing-plans
- finishing-a-development-branch
- mcp-builder
- receiving-code-review
- requesting-code-review
- subagent-driven-development
- systematic-debugging
- test-driven-development
- using-git-worktrees
- using-superpowers
- verification-before-completion
- workflow-runner
- writing-plans
- writing-skills
Repository facts
- License
- MIT
- Created
- Mar 20, 2026
- Last pushed
- Oct 26, 2026
- Forks
- 786
- Open issues
- 6
- Project activity
- Active
Rank over the last 12 weeks
Now #170 · best #148 · down 10 in 30 days
- #167 from Oct 28 to Oct 29
- #168 on Oct 30
- #169 on Oct 31
- #170 from Nov 1 to Nov 2
- #171 on Nov 3
- #170 since Nov 4
53 earlier periods
- #144 on Aug 2
- #146 from Aug 7 to Aug 8
- #144 on Aug 9
- #148 from Aug 10 to Aug 12
- #150 on Aug 13
- #152 on Aug 14
- #150 from Aug 15 to Aug 17
- #151 from Aug 18 to Aug 19
- #150 from Aug 20 to Aug 21
- #148 on Aug 22
- #152 from Aug 23 to Aug 25
- #151 from Aug 26 to Aug 29
- #150 on Aug 30
- #151 from Aug 31 to Sep 1
- #149 on Sep 2
- #151 on Sep 3
- #149 on Sep 4
- #151 on Sep 5
- #150 on Sep 6
- #152 from Sep 7 to Sep 9
- #153 on Sep 10
- #152 on Sep 11
- #155 on Sep 12
- #154 on Sep 13
- #155 from Sep 14 to Sep 15
- #154 on Sep 16
- #155 on Sep 17
- #156 on Sep 18
- #155 on Sep 19
- #157 from Sep 20 to Sep 21
- #156 on Sep 22
- #157 on Sep 23
- #156 from Sep 24 to Sep 25
- #157 from Sep 26 to Sep 27
- #158 from Sep 28 to Sep 29
- #157 on Sep 30
- #159 from Oct 1 to Oct 2
- #157 on Oct 3
- #156 on Oct 4
- #158 from Oct 5 to Oct 6
- #160 on Oct 7
- #159 on Oct 8
- #160 on Oct 9
- #159 on Oct 10
- #160 from Oct 11 to Oct 12
- #161 from Oct 13 to Oct 14
- #160 on Oct 15
- #158 on Oct 16
- #161 on Oct 17
- #162 from Oct 18 to Oct 19
- #163 on Oct 20
- #164 from Oct 21 to Oct 24
- #166 on Oct 25
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 53 notes
skills/chinese-commit-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-commit-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-commit-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-commit-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-commit-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-commit-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-documentation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-documentation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 6 dangerous shell commandsin 3 files: brainstorming/scripts/stop-server.sh:22 brainstorming/scripts/start-server.sh:148 subagent-driven-development/SKILL.md:272
- 72 network referencesin 13 files: chinese-git-workflow/SKILL.md:35 chinese-documentation/SKILL.md:19 .claude-plugin/marketplace.json:4 and 10 more
- No hidden or obfuscated text
- No instruction overrides
- 14 executable scriptsin 12 files: skills/subagent-driven-development/scripts/review-package:1 skills/subagent-driven-development/scripts/sdd-workspace:1 brainstorming/scripts/helper.js:1 and 9 more
- 8 references to secretsin 4 files: chinese-git-workflow/SKILL.md:39 brainstorming/scripts/server.cjs:133 systematic-debugging/SKILL.md:103 and 1 more
- No requests to vote in Hot
Show all 100 signals by file
.claude-plugin/marketplace.json
- Network accessline 4
"owner": { "name": "jnMetaCode", "url": "https://github.com/jnMetaCode" - Network accessline 5
"name": "jnMetaCode", "url": "https://github.com/jnMetaCode" }, - Network accessline 6
"url": "https://github.com/jnMetaCode" - Network accessline 14
"author": { "name": "jnMetaCode", "url": "https://github.com/jnMetaCode" - Network accessline 15
"name": "jnMetaCode", "url": "https://github.com/jnMetaCode" } - Network accessline 16
"url": "https://github.com/jnMetaCode"
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "jnMetaCode", "url": "https://github.com/jnMetaCode" - Network accessline 6
"name": "jnMetaCode", "url": "https://github.com/jnMetaCode" }, - Network accessline 7
"url": "https://github.com/jnMetaCode" - Network accessline 8
}, "homepage": "https://github.com/jnMetaCode/superpowers-zh", "repository": "https://github.com/jnMetaCode/superpowers-zh", - Network accessline 9
"homepage": "https://github.com/jnMetaCode/superpowers-zh", - Network accessline 10
"repository": "https://github.com/jnMetaCode/superpowers-zh",
skills/brainstorming/scripts/helper.js
- Executable scriptline 1
Executable file
skills/brainstorming/scripts/server.cjs
- Executable scriptline 1
Executable file - Network accessline 104
const STATE_DIR = path.join(SESSION_DIR, 'state'); const SUPERPOWERS_VERSION = readSuperpowersVersion(); const SUPERPOWERS_BRAND_IMAGE_URL = 'https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png'; - Network accessline 105
const SUPERPOWERS_VERSION = readSuperpowersVersion(); const SUPERPOWERS_BRAND_IMAGE_URL = 'https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png'; const TELEMETRY_DISABLE_ENV_VARS = [ - Network accessline 106
const SUPERPOWERS_BRAND_IMAGE_URL = 'https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png'; - Access to secretsline 133
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Network accessline 251
return '<div class="brand"><a href="https://github.com/obra/superpowers">' + logo + '<span class="brand-copy">' + text + '</span></a></div>';
skills/brainstorming/scripts/start-server.sh
skills/brainstorming/scripts/stop-server.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 22
rm -f "${STATE_DIR}/server-info" - Dangerous shell operationline 79
rm -f "$PID_FILE" "$SERVER_ID_FILE" - Dangerous shell operationline 109
rm -f "$PID_FILE" "$SERVER_ID_FILE" "${STATE_DIR}/server.log" - Dangerous shell operationline 114
rm -rf "$SESSION_DIR"
skills/brainstorming/visual-companion.md
- Network accessline 40
# 返回:{"type":"server-started","port":52341, # "url":"http://localhost:52341/?key=ab12…", - Network accessline 41
# "url":"http://localhost:52341/?key=ab12…", - Network accessline 48
**URL 里带有会话密钥(`?key=…`)。** 服务器会拒绝任何不带它的请求, 所以永远要把 `url` 字段里的**完整** URL 交给用户—— 绝不去掉查询字符串,也绝不给出一个光秃秃的 `http://host:port`。这个 - Network accessline 49
所以永远要把 `url` 字段里的**完整** URL 交给用户—— 绝不去掉查询字符串,也绝不给出一个光秃秃的 `http://host:port`。这个 密钥守着 HTTP 和 WebSocket 访问,让误开的浏览器标签页或网络上的其他机器 - Network accessline 50
绝不去掉查询字符串,也绝不给出一个光秃秃的 `http://host:port`。这个
skills/chinese-code-review/SKILL.md
- Network accessline 63
参考:https://cheatsheetseries.owasp.org/cheatsheets/SQL_Injection_Prevention_Cheat_Sheet.html
skills/chinese-commit-conventions/SKILL.md
skills/chinese-documentation/SKILL.md
- Network accessline 19
**参考标准:** [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines) - Network accessline 68
# 好 请参考 [官方文档](https://example.com) 获取更多信息。 - Network accessline 69
请参考 [官方文档](https://example.com) 获取更多信息。 - Network accessline 71
# 坏 请参考[官方文档](https://example.com)获取更多信息。 - Network accessline 72
请参考[官方文档](https://example.com)获取更多信息。 - Network accessline 267
[]() - Network accessline 268
[]() - Network accessline 317
\```bash # 克隆项目 git clone https://gitee.com/your-org/your-project.git - Network accessline 319
git clone https://gitee.com/your-org/your-project.git - Network accessline 333
- [依赖项目一](https://example.com) — 简要说明 - Network accessline 334
- [依赖项目二](https://example.com) — 简要说明
skills/chinese-git-workflow/SKILL.md
- Network accessline 35
# 设置 Gitee 远程仓库 git remote add origin https://gitee.com/<org>/<repo>.git - Network accessline 36
git remote add origin https://gitee.com/<org>/<repo>.git - Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 43
[Credential-related source omitted] - Network accessline 46
# 同时推送到 Gitee 和 GitHub(镜像同步) git remote set-url --add --push origin https://gitee.com/<org>/<repo>.git - Network accessline 47
git remote set-url --add --push origin https://gitee.com/<org>/<repo>.git - Network accessline 48
git remote set-url --add --push origin https://github.com/<org>/<repo>.git - Network accessline 54
# Coding 的仓库地址格式 git remote add origin https://e.coding.net/<team>/<project>/<repo>.git - Network accessline 55
git remote add origin https://e.coding.net/<team>/<project>/<repo>.git - Network accessline 64
# 极狐 GitLab 私有化部署常见地址格式 git remote add origin https://jihulab.com/<group>/<repo>.git - Network accessline 65
git remote add origin https://jihulab.com/<group>/<repo>.git - Network accessline 67
# 或者企业内部部署 git remote add origin https://gitlab.yourcompany.com/<group>/<repo>.git - Network accessline 68
git remote add origin https://gitlab.yourcompany.com/<group>/<repo>.git - Network accessline 74
# CNB 仓库地址(仅支持 HTTPS,不提供 SSH 协议) git remote add origin https://cnb.cool/<org>/<repo>.git - Network accessline 75
git remote add origin https://cnb.cool/<org>/<repo>.git - Network accessline 347
NODE_IMAGE: node:20-alpine # 使用国内镜像加速 NPM_REGISTRY: https://registry.npmmirror.com - Network accessline 349
NPM_REGISTRY: https://registry.npmmirror.com - Network accessline 505
# 代理设置(如果需要同时使用 GitHub) git config --global http.https://github.com.proxy socks5://127.0.0.1:7890 - Network accessline 506
git config --global http.https://github.com.proxy socks5://127.0.0.1:7890 - Network accessline 508
# NPM 使用国内镜像 npm config set registry https://registry.npmmirror.com - Network accessline 509
npm config set registry https://registry.npmmirror.com - Access to secretsline 530
[Credential-related source omitted]
skills/diagnosing-superpowers/references/github-issues.md
- Network accessline 3
`gh` 已安装并已认证时就用 `gh`;它处理认证、限流和 JSON。退而求其次用 curl 调公开 API, - Network accessline 18
curl -s -H "Accept: application/vnd.github+json" \ - Network accessline 19
"https://api.github.com/search/issues?q=repo:jnMetaCode/superpowers-zh+is:issue+<url-encoded terms>&per_page=10" \ - Network accessline 23
没有 curl 时,交给对方 `https://github.com/jnMetaCode/superpowers-zh/issues?q=<terms>`。 - Network accessline 42
https://github.com/jnMetaCode/superpowers-zh/issues/new?template=diagnosis_report.md&title=<url-encoded title>&body=<url-encoded body>
skills/executing-plans/scripts/task-done
- Executable scriptline 1
#!/usr/bin/env bash
skills/executing-plans/scripts/task-start
- Executable scriptline 1
#!/usr/bin/env bash
skills/mcp-builder/SKILL.md
- Access to secretsline 194
[Credential-related source omitted]
skills/subagent-driven-development/SKILL.md
- Dangerous shell operationline 272
当覆盖整个分支的最终审查干净、且它的修复已合并时,删除**本计划**的工作区(`rm -rf <工作区>`)——现在 git 历史就是记录了。同级目录属于别的计划,别去动它们。
skills/subagent-driven-development/scripts/review-package
skills/subagent-driven-development/scripts/sdd-workspace
skills/subagent-driven-development/scripts/task-brief
- Executable scriptline 1
#!/usr/bin/env bash
skills/systematic-debugging/SKILL.md
skills/systematic-debugging/condition-based-waiting-example.ts
- Executable scriptline 1
Executable file
skills/systematic-debugging/find-polluter.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/using-superpowers/references/qoder-tools.md
- Network accessline 19
> **适用范围:Qoder CLI。** 下表逐条核对自 [Qoder 官方文档 · 子代理](https://docs.qoder.com/zh/cli/subagent)(核对于 2026-08)。 - Network accessline 33
[#119](https://github.com/jnMetaCode/superpowers-zh/issues/119) 报告:在 **Qoder IDE** 里跑 `subagent-driven-development` 时,Qoder 说它只提供 `CodeReview` subagent、**没有** `general-purpose`,于是自行降级为「控制者直接实现 + CodeReview agent 做审查」。
skills/workflow-runner/SKILL.md
skills/writing-skills/SKILL.md
- Network accessline 99
**Frontmatter(YAML):** - 两个必需字段:`name` 和 `description`(完整支持字段参见 [agentskills.io/specification](https://agentskills.io/specification)) - Network accessline 100
- 两个必需字段:`name` 和 `description`(完整支持字段参见 [agentskills.io/specification](https://agentskills.io/specification)) - Network accessline 640
**绿色阶段 - 编写最小技能:** - [ ] 名称只使用字母、数字、连字符(无括号/特殊字符) - [ ] YAML frontmatter 包含必需的 `name` 和 `description` 字段(最多 1024 字符;参见 [spec](https://agentskills.io/specification)) - Network accessline 641
- [ ] 名称只使用字母、数字、连字符(无括号/特殊字符) - [ ] YAML frontmatter 包含必需的 `name` 和 `description` 字段(最多 1024 字符;参见 [spec](https://agentskills.io/specification)) - [ ] 描述以"Use when..."开头并包含具体的触发条件/症状 - Network accessline 642
- [ ] YAML frontmatter 包含必需的 `name` 和 `description` 字段(最多 1024 字符;参见 [spec](https://agentskills.io/specification))
skills/writing-skills/anthropic-best-practices.md
- Network accessline 13
[上下文窗口](https://platform.claude.com/docs/en/build-with-claude/context-windows)是公共资源。你的技能与 Claude 需要知道的所有其他内容共享上下文窗口,包括: - Network accessline 248
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=87782ff239b297d9a9e8e1b72ed72db9" alt="简单的 SKILL.md 文件,展示 YAML frontmatter 和 markdown 正文" - Network accessline 252
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=a5e0aa41e3d53985a7e3e43668a33ea3" alt="捆绑额外的参考文件如 reference.md 和 forms.md。" data-og- - Network accessline 918
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=4bbc45f2c2e0bee9f2f0d5da669bad00" alt="将可执行脚本与指令文件捆绑在一起" data-og-width="2048" widt
skills/writing-skills/render-graphs.js
- Executable scriptline 1
#!/usr/bin/env node
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Combined signals: 1 fact
- Reads SSH keys, and the same file sends data over the network or runs a command (line 46)chinese-git-workflow/SKILL.md:39High confidence
Declared and executed: 1 fact
- Contacts primeradiant.com, which SKILL.md, the README and the plugin manifest do not mentionbrainstorming/scripts/server.cjs:106High confidence
Signal confidence: 100 facts
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:4High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:5High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:6High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:14High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:15High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:16High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:5High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:6High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:7High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:8High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:9High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:10High confidence
- Executable script in code of a file that runsbrainstorming/scripts/helper.js:1High confidence
- Executable script in code of a file that runsbrainstorming/scripts/server.cjs:1High confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:104High confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:105High confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:106High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuebrainstorming/scripts/server.cjs:133Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuebrainstorming/scripts/server.cjs:134Low confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:251High confidence
- Executable script in code of a file that runsbrainstorming/scripts/start-server.sh:1High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/start-server.sh:148High confidence
- Executable script in code of a file that runsbrainstorming/scripts/stop-server.sh:1High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:22High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:79High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:109High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:114High confidence
- Network access in code of documentationbrainstorming/visual-companion.md:40Low confidence
- Network access in code of documentationbrainstorming/visual-companion.md:41Low confidence
- Network access in prose of documentationbrainstorming/visual-companion.md:48Low confidence
- Network access in prose of documentationbrainstorming/visual-companion.md:49Low confidence
- Network access in prose of documentationbrainstorming/visual-companion.md:50Low confidence
- Network access in code of the SKILL.mdchinese-code-review/SKILL.md:63High confidence
- Network access in code of the SKILL.mdchinese-commit-conventions/SKILL.md:173High confidence
- Network access in code of the SKILL.mdchinese-commit-conventions/SKILL.md:174High confidence
- Network access in prose of the SKILL.mdchinese-documentation/SKILL.md:19Low confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:68High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:69High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:71High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:72High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:267High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:268High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:317High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:319High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:333High confidence
- Network access in code of the SKILL.mdchinese-documentation/SKILL.md:334High confidence
- Network access in code of the SKILL.mdchinese-git-workflow/SKILL.md:35High confidence
- Network access in code of the SKILL.mdchinese-git-workflow/SKILL.md:36High confidence
- Access to secrets in code of the SKILL.md: reads a credential storechinese-git-workflow/SKILL.md:39High confidence
- Access to secrets in code of the SKILL.md: reads a credential storechinese-git-workflow/SKILL.md:43High confidence
and 50 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/brainstorming/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Manifest gemini-extension.json | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/brainstorming/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Native | Path .opencode/INSTALL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/jnmetacode-superpowers-zh/)