使用超能力

其他 社区

技能解读

using-superpowers 是 superpowers 体系的「使用守则」:你必须把 skills 当成第一层指令源——只要有 1% 可能命中当前任务,必须 invoke。但用户的显式指令永远凌驾于 skill 之上。

优先级

1)用户显式指令(CLAUDE.md / GEMINI.md / AGENTS.md / 直接对话)= 最高;2)superpowers skills——在与默认 system prompt 冲突时覆盖默认;3)默认 system prompt = 最低。CLAUDE.md 说「不要 TDD」、skill 说「永远 TDD」时,听用户的——用户握控制权。

铁律

"IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT." 哪怕只有 1% 可能命中也必须先 invoke 检查;如果 invoke 后发现这个 skill 跟当前情境不对,再放弃。SUBAGENT-STOP:被派为 subagent 干具体任务时跳过本 skill——subagent 拿到的 prompt 已是「精剪好的任务卡」,不该再触发 skill 路由。

Skill 的访问方式

  • Claude Code:用 Skill tool;invoke 后 skill 内容被加载并展示给你,跟着做即可——永远不要用 Read 去打开 skill 文件
  • Copilot CLI:skill tool(从已装 plugin auto-discover,等价于 Claude Code 的 Skill)
  • Gemini CLI:activate_skill tool(session start 加载 metadata,需要时才激活完整内容)
  • 其他平台:查平台文档

平台适配

Skills 用的是 Claude Code 的 tool 名。非 CC 平台:references/copilot-tools.md(Copilot CLI)、references/codex-tools.md(Codex)有 tool 等价映射;Gemini CLI 通过 GEMINI.md 自动加载映射。

适合的场景

  • 第一次接 superpowers skills,理解「skill > default」的优先级
  • 多平台共用同一组 skill(Claude Code / Copilot / Gemini),要知道每家怎么 invoke
  • 调试「为什么 agent 不按 skill 来」——多半是没遵守这条铁律

不适合

  • 你是被派活的 subagent:按 SUBAGENT-STOP 跳过即可
  • 当前任务无任何 skill 适配:本守则会让你 invoke 一下确认无命中即可

配套

writing-skills(怎么写 skill 让其他 agent 容易命中)、skill-creator(写新 skill 的元 skill)、template-skill(骨架)、subagent-driven-development(subagent 与本守则的边界)。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
通用
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@obra · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • 命令执行
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

<SUBAGENT-STOP>
If you were dispatched as a subagent to execute a specific task, ignore this skill.
</SUBAGENT-STOP>

<EXTREMELY-IMPORTANT>
If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.

IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.

This is not negotiable. You cannot rationalize your way out of this.
</EXTREMELY-IMPORTANT>

## The Rule

**Invoke relevant or requested skills BEFORE any response or action** — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.

**Before entering plan mode:** if you haven't already brainstormed, invoke the brainstorming skill first.

Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.

## Skill Priority

When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them.

- "Let's build X" → superpowers:brainstorming first, then implementation skills.
- "Fix this bug" → superpowers:systematic-debugging first, then domain skills.

## Red Flags

These thoughts mean STOP—you're rationalizing:

| Thought | Reality |
|---------|---------|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
| "Let me gather information first" | Skills tell you HOW to gather information. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I'll just do this one thing first" | Check BEFORE doing anything. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |

## Platform Adaptation

If your harness appears here, read its reference file for special instructions:

- Codex: `references/codex-tools.md`
- Pi: `references/pi-tools.md`
- Antigravity: `references/antigravity-tools.md`
- Hermes Agent: `references/hermes-tools.md`

## User Instructions

User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。