skill-discovery

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

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

<EXTREMELY-IMPORTANT> 如果你认为某项技能哪怕只有1%的概率适用于你当前正在做的事，你绝对必须调用该技能。

如果某项技能适用于你的任务，你没有选择余地，必须使用它。

这一点没有商量余地，不是可选项，你没有任何理由逃避这一要求。 </EXTREMELY-IMPORTANT>

How to Access Skills

如何访问技能

In Claude Code: Use the

Skill

tool or read skill files directly. When you invoke a skill, its content is loaded and presented to you - follow it directly.

In other environments: Check your platform's documentation for how skills are loaded.

在Claude Code中： 使用

Skill

工具或直接读取技能文件。当你调用技能时，它的内容会被加载并展示给你——直接遵循内容要求执行即可。

在其他环境中： 查看你所在平台的文档了解技能加载方式。

Using Framework Skills

使用框架技能

The Rule

规则

Invoke relevant or requested skills BEFORE any response or action. Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.

dot

digraph skill_flow {
    "User message received" [shape=doublecircle];
    "Might any skill apply?" [shape=diamond];
    "Invoke Skill tool" [shape=box];
    "Announce: 'Using [skill] to [purpose]'" [shape=box];
    "Has checklist?" [shape=diamond];
    "Create TodoWrite todo per item" [shape=box];
    "Follow skill exactly" [shape=box];
    "Respond (including clarifications)" [shape=doublecircle];

    "User message received" -> "Might any skill apply?";
    "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
    "Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
    "Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
    "Has checklist?" -> "Follow skill exactly" [label="no"];
    "Create TodoWrite todo per item" -> "Follow skill exactly";
}

在给出任何回复或执行任何操作前，先调用相关或被要求使用的技能。 哪怕只有1%的概率某技能可能适用，你也应该调用该技能进行确认。如果调用后发现该技能不匹配当前场景，你可以不用它。

dot

digraph skill_flow {
    "User message received" [shape=doublecircle];
    "Might any skill apply?" [shape=diamond];
    "Invoke Skill tool" [shape=box];
    "Announce: 'Using [skill] to [purpose]'" [shape=box];
    "Has checklist?" [shape=diamond];
    "Create TodoWrite todo per item" [shape=box];
    "Follow skill exactly" [shape=box];
    "Respond (including clarifications)" [shape=doublecircle];

    "User message received" -> "Might any skill apply?";
    "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
    "Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
    "Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
    "Has checklist?" -> "Follow skill exactly" [label="no"];
    "Create TodoWrite todo per item" -> "Follow skill exactly";
}

Red Flags

风险警示

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.

以下这些想法意味着你需要立刻停止——你正在给自己找借口：

想法	实际情况
"这只是个简单的问题"	问题也是任务，需要检查是否有适用技能。
"我需要先获取更多上下文"	技能检查要早于问询澄清步骤。
"我先探索一下代码库"	技能会告诉你应该如何探索，先检查技能。
"我可以快速查看git/文件"	文件缺少对话上下文，先检查是否有适用技能。
"我先收集一下信息"	技能会告诉你应该如何收集信息。
"这个不需要正式的技能"	如果有对应技能，就使用它。
"我记得这个技能的内容"	技能会迭代更新，读取当前版本。
"这个不算任务"	只要有动作就属于任务，检查是否有适用技能。
"用这个技能大材小用了"	简单的事也可能变复杂，使用技能。
"我先把这一件小事做了"	做任何事之前都要先检查技能。
"这样做感觉效率很高"	无章法的操作会浪费时间，技能可以避免这种情况。
"我知道这个是什么意思"	了解概念不等于会使用技能，调用它。

Skill Priority

技能优先级

When multiple skills could 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" -> brainstorming first, then implementation skills. "Fix this bug" -> debugging first, then domain-specific skills.

当有多个技能都可能适用时，按照以下顺序选择：

优先使用流程类技能（头脑风暴、debugging）——这类技能决定了处理任务的方式
其次使用实现类技能（frontend-design、mcp-builder）——这类技能指导执行过程

"我们来构建X" -> 先调用头脑风暴技能，再使用实现类技能。 "修复这个bug" -> 先调用debugging技能，再使用领域专属技能。

Skill Types

技能类型

Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline.

Flexible (patterns): Adapt principles to context.

The skill itself tells you which.

刚性技能（TDD、debugging）：严格遵循要求，不要背离规范。

柔性技能（patterns）：根据场景适配原则。

技能本身会说明自己属于哪一类。

User Instructions

用户指令

Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.

指令只说明做什么，不说明怎么做。"添加X"或者"修复Y"不代表可以跳过工作流。

Memory Protocol (MANDATORY)

记忆协议（强制要求）

Before starting: Read

.claude/context/memory/learnings.md

After completing:

New pattern ->
```
.claude/context/memory/learnings.md
```
Issue found ->
```
.claude/context/memory/issues.md
```
Decision made ->
```
.claude/context/memory/decisions.md
```

ASSUME INTERRUPTION: If it's not in memory, it didn't happen.

开始之前： 读取

.claude/context/memory/learnings.md

完成之后：

发现新模式 -> 写入
```
.claude/context/memory/learnings.md
```
发现问题 -> 写入
```
.claude/context/memory/issues.md
```
做出决策 -> 写入
```
.claude/context/memory/decisions.md
```

假设随时会被中断：没有记录在记忆中的内容，就等于没有发生过。