superpowers-zh
github.com/jnMetaCode/superpowers-zh
Skill | Added | Review |
|---|---|---|
writing-skills skills/writing-skills/SKILL.md 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 | 56 56 Impact — No eval scenarios have been run Securityby  Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
writing-plans skills/writing-plans/SKILL.md 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 | 46 46 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
workflow-runner skills/workflow-runner/SKILL.md 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。 | 63 63 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Reviewed: Version: 12a4dc1 | |
verification-before-completion skills/verification-before-completion/SKILL.md 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 | 73 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
using-superpowers skills/using-superpowers/SKILL.md 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 | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
using-git-worktrees skills/using-git-worktrees/SKILL.md 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 | 63 63 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
test-driven-development skills/test-driven-development/SKILL.md 在实现任何功能或修复 bug 时使用，在编写实现代码之前 | 52 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
systematic-debugging skills/systematic-debugging/SKILL.md 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 | 64 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
subagent-driven-development skills/subagent-driven-development/SKILL.md 当在当前会话中执行包含独立任务的实现计划时使用 | 48 48 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
requesting-code-review skills/requesting-code-review/SKILL.md 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 | 52 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
receiving-code-review skills/receiving-code-review/SKILL.md 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 | 55 55 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Reviewed: Version: 12a4dc1 | |
mcp-builder skills/mcp-builder/SKILL.md MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力 | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
finishing-a-development-branch skills/finishing-a-development-branch/SKILL.md 当实现完成、所有测试通过、需要决定如何集成工作时使用——通过提供合并、PR 或清理等结构化选项来引导开发工作的收尾 | 71 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
executing-plans skills/executing-plans/SKILL.md 当你有一份书面实现计划需要在单独的会话中执行，并设有审查检查点时使用 | 60 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
dispatching-parallel-agents skills/dispatching-parallel-agents/SKILL.md 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 | 57 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
chinese-git-workflow skills/chinese-git-workflow/SKILL.md 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。 | 66 66 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Reviewed: Version: 12a4dc1 | |
chinese-documentation skills/chinese-documentation/SKILL.md 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。 | 70 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
chinese-commit-conventions skills/chinese-commit-conventions/SKILL.md 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。 | 67 67 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
chinese-code-review skills/chinese-code-review/SKILL.md 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。 | 71 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 | |
brainstorming skills/brainstorming/SKILL.md 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、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。 | 65 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 12a4dc1 |