using-superpowers

jnMetaCode/superpowers-zh · Agent Skill

This skill ensures the AI agent always searches for and uses relevant tools first before responding or taking actions.

Jump to install ↓

Overview

PublisherjnMetaCodeCommunity
RepositoryjnMetaCode/superpowers-zh ↗
Skill folderusing-superpowers
Stars8,021
Bundled files1
LicenseMIT
Last updatedSeptember 6, 2026
LinksSkill source ↗ · Repository ↗

Mozgi check

What we found in the skill files. Details come with a subscription.

Security
low risk · no obvious risks found — the full report shows the details
Compatibility
instructions only — works with most agents
Similar skills
51 similar skills found
Also with subscription

Installation

A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.

Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.

Install the “using-superpowers” skill from mozgi.io (https://mozgi.io/skills/using-superpowers-jnmetacode/) for me.

1. Download the archive: https://mozgi.io/skills/using-superpowers-jnmetacode/download
   If it fails, take the skill folder from the source: https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/using-superpowers
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “using-superpowers” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/using-superpowers/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

Review the source files

1 file Download Zip

Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.

SKILL.md contents

Original author text · read-only

<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

在任何响应或操作之前调用相关或被请求的技能——包括澄清性问题、探索代码库、或查看文件之前。如果调用后发现技能不适合当前情况，你不需要使用它。

在进入 EnterPlanMode 之前： 如果你还没有头脑风暴过，先调用头脑风暴技能。

然后宣布"使用 [技能] 来 [目的]"，并严格遵循该技能。如果它有检查清单，为每个条目创建一个待办。

技能优先级

当多个技能都适用时，流程技能优先——它们决定处理方式，然后由实现技能（前端设计等）负责执行。头脑风暴和系统化调试是 Superpowers 中最常见的流程技能，但这条规则适用于任何流程技能。

  • "让我们构建 X" → 先用 brainstorming，再用实现技能。
  • "修复这个 bug" → 先用 systematic-debugging，再用领域技能。

红线

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。 |

平台适配

如果你的运行环境在下面列出，请阅读对应的参考文件获取特殊说明：

  • Codex：references/codex-tools.md
  • Pi：references/pi-tools.md
  • Antigravity：references/antigravity-tools.md
  • Copilot CLI：references/copilot-tools.md
  • Hermes Agent：references/hermes-tools.md
  • Qoder：references/qoder-tools.md

Gemini CLI 用户通过 GEMINI.md 自动获得 references/gemini-tools.md 的工具映射。

中国特色技能路由

> 🇨🇳 本节是 superpowers-zh 的增量内容，上游 obra/superpowers 没有。

> 用于说明本 fork 原创的 chinese-* 系列 skill 何时使用。其余各节均为逐节翻译。

这 4 个 chinese-* 是参考资料，不是工作流 —— 话术模板、排版约定、平台配置差异。

它们只在用户显式调用时才加载，不要根据上下文自动触发：上下文里多一份排版参考

不会让你写得更好，只会挤掉真正需要的内容。

| 用户显式说 | 加载技能 | 里面是什么 |

|------|---------|---------|

| /chinese-code-review | chinese-code-review | 中文 review 话术模板、分级标注、国内团队常见反模式应对 |

| /chinese-git-workflow | chinese-git-workflow | Gitee / Coding.net / 极狐 GitLab / CNB 的 SSH、凭据、CI 接入差异 |

| /chinese-documentation | chinese-documentation | 中英文空格、全半角标点、术语保留、中文文案排版指北约定 |

| /chinese-commit-conventions | chinese-commit-conventions | Conventional Commits 中文适配、commitlint / husky 中文模板 |

用户没点名就不要主动拉进来。反过来，用户点名了就照它执行，不要因为"看起来只是格式问题"

而跳过。

它们与翻译技能叠加使用，不互斥：用户要求做中文 review 时，是

requesting-code-review（流程）加上 chinese-code-review（风格），不是二选一。

> 这个「只在显式调用时加载」是刻意决定，不是漏写（见 commit 392ff75）。改动它需要

> eval 证据 —— 参见 PR #123 与本仓 CLAUDE.md「Skill 改动需要 eval」。

用户指令

用户指令（CLAUDE.md、AGENTS.md、GEMINI.md 等、直接请求）优先于技能，技能又优先于默认行为。只有当你的人类伙伴明确告诉你跳过时，才能跳过技能工作流或指令。

Frequently asked questions

What does the using-superpowers skill do?

This skill ensures the AI agent always searches for and uses relevant tools first before responding or taking actions.

How do I install using-superpowers?

Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.

Which AI models work with using-superpowers?

Skills are plain Markdown instructions (the Agent Skills format), so using-superpowers works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.

Is using-superpowers free?

The skill is published openly by jnMetaCode under the MIT license. The skill itself costs nothing — you only pay your AI provider for the tokens you use.

Is it safe to install skills?

A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.

How is a skill different from an MCP server or a plugin?

An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.

Related skills

All skills →
browser-automation Automates web page control, including complex scenarios, login checks, tab management, and error handling. openclaw390k skill-creator Creates, edits, and validates SKILL.md files for AI agents, structuring them and preparing them for use. openclaw389k subagent-driven-development A development methodology where an agent delegates tasks to specialized sub-agents with isolated context, ensuring high code quality, automated result verification, and continuous plan execution without human intervention. obra303k using-superpowers This skill helps the agent find and use other skills, requiring their invocation before any response or action. obra283k dispatching-parallel-agents Distributes independent tasks among multiple agents for parallel execution, optimizing time and resources. obra283k writing-skills Creates and edits AI agent skills using a Test-Driven Development approach for documentation. obra283k