AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Using Superpowers

skill-myswallow-superpowers-lite-using-superpowers · by MySwallow

在开始任何对话时使用——确立在回应前如何查找和使用 skills

No reviews yet
0 installs
9 views
0.0% view→install

Install

$ agentstack add skill-myswallow-superpowers-lite-using-superpowers

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-myswallow-superpowers-lite-using-superpowers)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Using Superpowers? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

如果你是被作为子代理派来执行特定任务的,跳过这个 skill。

使用 Skills

核心规则

在回应用户消息之前,检查是否有可用的 skill 适用。 如果是,在产生任何其他输出(包括澄清问题)之前, 通过 Skill 工具调用它。简短声明:"Using [skill] to [purpose]"。

digraph skill_flow {
    "收到用户消息" [shape=doublecircle];
    "即将 EnterPlanMode?" [shape=doublecircle];
    "已经 brainstorm 过?" [shape=diamond];
    "调用 brainstorming skill" [shape=box];
    "可能有 skill 适用?" [shape=diamond];
    "调用 Skill 工具" [shape=box];
    "声明:'Using [skill] to [purpose]'" [shape=box];
    "有检查清单?" [shape=diamond];
    "为每项创建 TodoWrite 待办" [shape=box];
    "严格遵循 skill" [shape=box];
    "回应(包括澄清问题)" [shape=doublecircle];

    "即将 EnterPlanMode?" -> "已经 brainstorm 过?";
    "已经 brainstorm 过?" -> "调用 brainstorming skill" [label="否"];
    "已经 brainstorm 过?" -> "可能有 skill 适用?" [label="是"];
    "调用 brainstorming skill" -> "可能有 skill 适用?";

    "收到用户消息" -> "可能有 skill 适用?";
    "可能有 skill 适用?" -> "调用 Skill 工具" [label="是,哪怕只有 1%"];
    "可能有 skill 适用?" -> "回应(包括澄清问题)" [label="绝对不"];
    "调用 Skill 工具" -> "声明:'Using [skill] to [purpose]'";
    "声明:'Using [skill] to [purpose]'" -> "有检查清单?";
    "有检查清单?" -> "为每项创建 TodoWrite 待办" [label="是"];
    "有检查清单?" -> "严格遵循 skill" [label="否"];
    "为每项创建 TodoWrite 待办" -> "严格遵循 skill";
}

如何访问 Skills

Skills 默认遵循 Claude Code 约定。各平台有自己的访问方式:

  • Claude Code: 使用 Skill 工具。调用时 skill 的内容会被加载——直接遵循即可。绝不要用 Read 工具读取 skill 文件。
  • GitHub Copilot CLI: 使用 skill 工具(语义与 Claude Code 的 Skill 工具相同)。
  • Gemini CLI: skills 通过 activate_skill 激活。Gemini 在会话开始时加载元数据,按需激活完整内容。
  • Codex CLI / 其他平台: 见本目录下的 references/ 查工具名等价对照。

通用兜底:自己读取 SKILL.md 内容并按其指导操作。

指令优先级(最高 → 最低)

  1. 用户指令 — CLAUDE.md、AGENTS.md、用户直接请求
  2. Skills — 当冲突时覆盖默认系统行为
  3. 默认系统 prompt

如果用户指令与 skill 冲突,遵循用户。用户说了算。

红色信号——如果你想到以下任一,停下来

  • "这只是一个简单问题" → 问题就是任务,检查是否有 skill
  • "我得先收集更多上下文" → 检查 skill 必须先于澄清问题
  • "让我先探索一下代码库" → skills 会告诉你怎么探索
  • "这事不需要正式 skill" → 如果存在 skill,就用它
  • "用 skill 太重了" → 简单的事情会变复杂
  • "我知道那是什么意思" → 知道概念 ≠ 使用 skill
  • "我先做完这一件事再说" → 在做任何事之前先检查

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.