using-superpowers

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

<SUBAGENT-STOP> 如果你是作为子智能体被分派来执行特定任务的，跳过此技能。 </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。这不是可选的。你不能通过合理化来逃避。 </EXTREMELY-IMPORTANT>

<SUBAGENT-STOP> If you are assigned as a sub-agent to perform a specific task, skip this skill. </SUBAGENT-STOP> <EXTREMELY-IMPORTANT> If you think there's even a 1% chance a skill applies to what you're doing, you absolutely must call that skill.

If a skill applies to your task, you have no choice. You must use it.

This is non-negotiable. It is not optional. You cannot rationalize your way out of it. </EXTREMELY-IMPORTANT>

指令优先级

Instruction Priority

Superpowers 技能覆盖默认系统提示行为，但用户指令始终具有最高优先级：

用户的明确指令（CLAUDE.md、GEMINI.md、AGENTS.md、直接请求）——最高优先级
Superpowers 技能 ——在冲突处覆盖默认系统行为
默认系统提示 ——最低优先级

如果 CLAUDE.md、GEMINI.md 或 AGENTS.md 说"不要使用 TDD"，而某个技能说"始终使用 TDD"，遵循用户的指令。用户拥有控制权。

Superpowers skills override default system prompt behavior, but user instructions always have the highest priority:

Explicit user instructions (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — Highest priority
Superpowers skills — Override default system behavior in case of conflict
Default system prompt — Lowest priority

If CLAUDE.md, GEMINI.md, or AGENTS.md says "Don't use TDD" and a skill says "Always use TDD", follow the user's instructions. The user is in control.

如何访问技能

How to Access Skills

在 Claude Code 中： 使用

Skill

工具。当你调用一个技能时，其内容会被加载并呈现给你——直接遵循即可。绝不要用 Read 工具读取技能文件。

在 Copilot CLI 中： 使用

skill

工具。技能从已安装的插件中自动发现。

skill

工具的工作方式与 Claude Code 的

Skill

工具相同。

在 Hermes Agent 中： 使用

skill_view

工具加载技能。Hermes 支持三级渐进式加载：

skills_list

浏览 →

skill_view(name)

加载完整内容 →

skill_view(name, path)

查看引用文件。

在 Gemini CLI 中： 技能通过

activate_skill

工具激活。Gemini 在会话开始时加载技能元数据，并按需激活完整内容。

在其他环境中： 查看你的平台文档了解技能的加载方式。

In Claude Code: Use the

Skill

tool. When you call a skill, its content is loaded and presented to you — follow it directly. Never use the Read tool to read skill files.

In Copilot CLI: Use the

skill

tool. Skills are automatically discovered from installed plugins. The

skill

tool works the same way as Claude Code's

Skill

tool.

In Hermes Agent: Use the

skill_view

tool to load skills. Hermes supports three-level progressive loading:

skills_list

browse →

skill_view(name)

load full content →

skill_view(name, path)

view referenced files.

In Gemini CLI: Skills are activated via the

activate_skill

tool. Gemini loads skill metadata at session start and activates full content on demand.

In other environments: Check your platform documentation for how to load skills.

平台适配

Platform Adaptation

技能使用 Claude Code 的工具名称。非 CC 平台：查看

references/copilot-tools.md

（Copilot CLI）、

references/hermes-tools.md

（Hermes Agent）、

references/codex-tools.md

（Codex）、

references/qoder-tools.md

（Qoder）了解工具对应关系。Gemini CLI 用户通过 GEMINI.md 自动获得工具映射。

Skills use Claude Code's tool names. For non-CC platforms: Check

references/copilot-tools.md

(Copilot CLI),

references/hermes-tools.md

(Hermes Agent),

references/codex-tools.md

(Codex),

references/qoder-tools.md

(Qoder) for tool mappings. Gemini CLI users get tool mappings automatically via GEMINI.md.

使用技能

Using Skills

规则

Rules

在任何响应或操作之前调用相关或被请求的技能。 哪怕只有 1% 的可能性某个技能适用，你都应该调用该技能来检查。如果调用后发现技能不适合当前情况，你不需要使用它。

dot

digraph skill_flow {
    "收到用户消息" [shape=doublecircle];
    "即将进入 EnterPlanMode？" [shape=doublecircle];
    "已经头脑风暴过？" [shape=diamond];
    "调用头脑风暴技能" [shape=box];
    "可能有技能适用？" [shape=diamond];
    "调用 Skill 工具" [shape=box];
    "宣布：'使用 [技能] 来 [目的]'" [shape=box];
    "有检查清单？" [shape=diamond];
    "为每个条目创建 TodoWrite 待办" [shape=box];
    "严格遵循技能" [shape=box];
    "响应（包括澄清）" [shape=doublecircle];

    "即将进入 EnterPlanMode？" -> "已经头脑风暴过？";
    "已经头脑风暴过？" -> "调用头脑风暴技能" [label="否"];
    "已经头脑风暴过？" -> "可能有技能适用？" [label="是"];
    "调用头脑风暴技能" -> "可能有技能适用？";

    "收到用户消息" -> "可能有技能适用？";
    "可能有技能适用？" -> "调用 Skill 工具" [label="是，哪怕只有 1%"];
    "可能有技能适用？" -> "响应（包括澄清）" [label="确定不适用"];
    "调用 Skill 工具" -> "宣布：'使用 [技能] 来 [目的]'";
    "宣布：'使用 [技能] 来 [目的]'" -> "有检查清单？";
    "有检查清单？" -> "为每个条目创建 TodoWrite 待办" [label="是"];
    "有检查清单？" -> "严格遵循技能" [label="否"];
    "为每个条目创建 TodoWrite 待办" -> "严格遵循技能";
}

Call relevant or requested skills before any response or action. Even if there's only a 1% chance a skill applies, you should call the skill to check. If after calling you find the skill isn't suitable for the current situation, you don't need to use it.

dot

digraph skill_flow {
    "Received User Message" [shape=doublecircle];
    "About to EnterPlanMode?" [shape=doublecircle];
    "Already Brainstormed?" [shape=diamond];
    "Call Brainstorm Skill" [shape=box];
    "Possible Skill Applicable?" [shape=diamond];
    "Call Skill Tool" [shape=box];
    "Announce: 'Using [Skill] to [Purpose]'" [shape=box];
    "Has Checklist?" [shape=diamond];
    "Create TodoWrite Tasks for Each Item" [shape=box];
    "Strictly Follow Skill" [shape=box];
    "Respond (including clarification)" [shape=doublecircle];

    "About to EnterPlanMode?" -> "Already Brainstormed?";
    "Already Brainstormed?" -> "Call Brainstorm Skill" [label="No"];
    "Already Brainstormed?" -> "Possible Skill Applicable?" [label="Yes"];
    "Call Brainstorm Skill" -> "Possible Skill Applicable?";

    "Received User Message" -> "Possible Skill Applicable?";
    "Possible Skill Applicable?" -> "Call Skill Tool" [label="Yes, even 1% chance"];
    "Possible Skill Applicable?" -> "Respond (including clarification)" [label="Confirmed not applicable"];
    "Call Skill Tool" -> "Announce: 'Using [Skill] to [Purpose]'";
    "Announce: 'Using [Skill] to [Purpose]'" -> "Has Checklist?";
    "Has Checklist?" -> "Create TodoWrite Tasks for Each Item" [label="Yes"];
    "Has Checklist?" -> "Strictly Follow Skill" [label="No"];
    "Create TodoWrite Tasks for Each Item" -> "Strictly Follow Skill";
}

红线

Red Lines

这些想法意味着停下——你在合理化：

想法	现实
"这只是一个简单的问题"	问题就是任务。检查技能。
"我需要先了解更多上下文"	技能检查在澄清性问题之前。
"让我先探索一下代码库"	技能告诉你如何探索。先检查。
"我可以快速查一下 git/文件"	文件缺少对话上下文。检查技能。
"让我先收集信息"	技能告诉你如何收集信息。
"这不需要正式的技能"	如果技能存在，就使用它。
"我记得这个技能"	技能会迭代更新。阅读当前版本。
"这不算一个任务"	行动 = 任务。检查技能。
"技能太小题大做了"	简单的事会变复杂。使用它。
"让我先做这一件事"	在做任何事之前先检查。
"这样做感觉很高效"	无纪律的行动浪费时间。技能防止这一点。
"我知道那是什么意思"	知道概念 ≠ 使用技能。调用它。

These thoughts mean stop — you're rationalizing:

Thought	Reality
"This is just a simple question"	Questions are tasks. Check skills.
"I need more context first"	Skill checks come before clarifying questions.
"Let me explore the codebase first"	Skills tell you how to explore. Check first.
"I can quickly check git/files"	Files lack conversational context. Check skills.
"Let me gather information first"	Skills tell you how to gather information.
"This doesn't need a formal skill"	If the skill exists, use it.
"I remember this skill"	Skills iterate and update. Read the current version.
"This isn't a real task"	Actions = tasks. Check skills.
"The skill is overkill"	Simple things get complicated. Use it.
"Let me just do this one thing first"	Check before doing anything.
"This feels efficient"	Undisciplined action wastes time. Skills prevent this.
"I know what that means"	Knowing the concept ≠ using the skill. Call it.

技能优先级

Skill Priority

当多个技能可能适用时，使用此顺序：

流程技能优先（头脑风暴、调试）- 这些决定如何处理任务
实现技能其次（前端设计、mcp-builder）- 这些指导执行

"让我们构建 X" → 先头脑风暴，再使用实现技能。 "修复这个 bug" → 先调试，再使用领域特定技能。

When multiple skills may apply, use this order:

Process skills first (brainstorming, debugging) — These determine how to approach the task
Implementation skills second (frontend design, mcp-builder) — These guide execution

"Let's build X" → Brainstorm first, then use implementation skills. "Fix this bug" → Debug first, then use domain-specific skills.

中国特色技能路由

China-Specific Skill Routing

当检测到以下场景时，必须优先调用对应的中国特色技能：

场景	调用技能
代码审查且团队使用中文沟通	superpowers:chinese-code-review
使用 Gitee/Coding/极狐 GitLab	superpowers:chinese-git-workflow
编写中文技术文档或 README	superpowers:chinese-documentation
编写 git commit message（中文项目）	superpowers:chinese-commit-conventions
构建 MCP 服务器/工具	superpowers:mcp-builder

判断依据：

项目中有中文注释、中文 README、或 .gitee 目录 → 启用中文系列技能
commit 历史中有中文 → 使用中文提交规范
用户用中文交流 → 所有输出使用中文，优先考虑中国特色技能

中国特色技能与翻译技能叠加使用，不互斥。例如：做代码审查时，同时使用 requesting-code-review（流程）+ chinese-code-review（风格）。

When the following scenarios are detected, must prioritize calling the corresponding China-specific skills:

Scenario	Skill to Call
Code review and team communicates in Chinese	superpowers:chinese-code-review
Using Gitee/Coding/Jihu GitLab	superpowers:chinese-git-workflow
Writing Chinese technical documents or README	superpowers:chinese-documentation
Writing git commit messages (Chinese projects)	superpowers:chinese-commit-conventions
Building MCP servers/tools	superpowers:mcp-builder

Judgment Criteria:

Chinese comments, Chinese README, or .gitee directory in the project → Enable Chinese series skills
Chinese in commit history → Use Chinese commit conventions
User communicates in Chinese → All output in Chinese, prioritize China-specific skills

China-specific skills are used in combination with translation skills, not mutually exclusive. For example: When doing code review, use both requesting-code-review (process) + chinese-code-review (style).

技能类型

Skill Types

刚性的（TDD、调试）：严格遵循。不要偏离纪律。

灵活的（模式）：根据上下文调整原则。

技能本身会告诉你它属于哪种。

Rigid (TDD, debugging): Follow strictly. Do not deviate from discipline.

Flexible (patterns): Adapt principles to context.

The skill itself will tell you which type it is.

用户指令

User Instructions

指令说明做什么，而非怎么做。"添加 X"或"修复 Y"不意味着跳过工作流。

Instructions say what to do, not how to do it. "Add X" or "Fix Y" does not mean skipping workflows.