using-oac

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

<EXTREMELY-IMPORTANT> If you think there is even a 1% chance an OAC 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OAC技能有哪怕1%的可能性适用于你正在处理的事务，你绝对必须调用该技能。

如果某项技能适用于你的任务，你别无选择，必须使用它。

这没有商量余地，也不是可选操作。你不能找理由逃避这一点。 </EXTREMELY-IMPORTANT>

How to Access Skills

如何访问技能

In Claude Code: Use the

Skill

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

在Claude Code中： 使用

Skill

工具。调用技能时，其内容会被加载并呈现给你——请直接遵循这些内容。切勿对技能文件使用Read工具。

Using OAC Skills

使用OAC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];
    "About to build/create something?" [shape=doublecircle];
    "Already brainstormed?" [shape=diamond];
    "Invoke oac:approach skill" [shape=box];
    "Might any OAC skill apply?" [shape=diamond];
    "Invoke Skill tool" [shape=box];
    "Announce: 'OAC skill loaded: [friendly-skill-name] — [purpose]'" [shape=box];
    "Has checklist?" [shape=diamond];
    "Create TodoWrite todo per item" [shape=box];
    "Follow skill exactly" [shape=box];
    "Respond (including clarifications)" [shape=doublecircle];

    "About to build/create something?" -> "Already brainstormed?";
    "Already brainstormed?" -> "Invoke oac:approach skill" [label="no"];
    "Already brainstormed?" -> "Might any OAC skill apply?" [label="yes"];
    "Invoke oac:approach skill" -> "Might any OAC skill apply?";

    "User message received" -> "Might any OAC skill apply?";
    "Might any OAC skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
    "Might any OAC skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
    "Invoke Skill tool" -> "Announce: 'OAC skill loaded: [friendly-skill-name] — [purpose]'";
    "Announce: 'OAC skill loaded: [friendly-skill-name] — [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";
}

在做出任何回应或操作之前，调用相关或被请求的技能。 哪怕技能只有1%的适用可能性，你也应该调用它进行确认。如果调用的技能最终被证明不适合当前场景，你可以不用它。

dot

digraph skill_flow {
    "User message received" [shape=doublecircle];
    "About to build/create something?" [shape=doublecircle];
    "Already brainstormed?" [shape=diamond];
    "Invoke oac:approach skill" [shape=box];
    "Might any OAC skill apply?" [shape=diamond];
    "Invoke Skill tool" [shape=box];
    "Announce: 'OAC skill loaded: [friendly-skill-name] — [purpose]'" [shape=box];
    "Has checklist?" [shape=diamond];
    "Create TodoWrite todo per item" [shape=box];
    "Follow skill exactly" [shape=box];
    "Respond (including clarifications)" [shape=doublecircle];

    "About to build/create something?" -> "Already brainstormed?";
    "Already brainstormed?" -> "Invoke oac:approach skill" [label="no"];
    "Already brainstormed?" -> "Might any OAC skill apply?" [label="yes"];
    "Invoke oac:approach skill" -> "Might any OAC skill apply?";

    "User message received" -> "Might any OAC skill apply?";
    "Might any OAC skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
    "Might any OAC skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
    "Invoke Skill tool" -> "Announce: 'OAC skill loaded: [friendly-skill-name] — [purpose]'";
    "Announce: 'OAC skill loaded: [friendly-skill-name] — [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";
}

Available OAC Skills

可用的OAC技能

Skill	When to invoke
`oac:using-oac`	This skill — loaded at session start
`oac:approach`	BEFORE any creative work, building features, adding functionality
`oac:context-discovery`	BEFORE implementing anything — find standards and patterns
`oac:task-breakdown`	When breaking complex features into subtasks
`oac:code-execution`	When implementing code subtasks
`oac:test-generation`	When creating tests
`oac:code-review`	When reviewing code changes
`oac:external-research`	When working with external libraries/packages
`oac:parallel-execution`	When running multiple agents in parallel
`oac:debugger`	BEFORE proposing any fix for a bug or test failure
`oac:verification-before-completion`	BEFORE claiming any work is complete or tests pass

技能	调用时机
`oac:using-oac`	本技能——会话开始时加载
`oac:approach`	在进行任何创意工作、构建功能、添加功能之前
`oac:context-discovery`	在实施任何内容之前——查找标准和模式
`oac:task-breakdown`	将复杂功能拆分为子任务时
`oac:code-execution`	实施代码子任务时
`oac:test-generation`	创建测试时
`oac:code-review`	审查代码变更时
`oac:external-research`	使用外部库/包时
`oac:parallel-execution`	并行运行多个Agent时
`oac:debugger`	针对错误或测试失败提出任何修复方案之前
`oac:verification-before-completion`	声称任何工作已完成或测试通过之前

Skill Priority

技能优先级

When multiple skills could apply, use this order:

Process skills first (approach, debugger) — these determine HOW to approach the task
Implementation skills second (context-discovery, task-breakdown, code-execution) — these guide execution

"Let's build X" → approach first, then context-discovery, then implementation skills. "Fix this bug" → debugger first, then verification-before-completion.

当多个技能都适用时，请按照以下顺序使用：

优先使用流程类技能（approach、debugger）——这些技能决定了处理任务的方式
其次使用实施类技能（context-discovery、task-breakdown、code-execution）——这些技能指导执行过程

"Let's build X" → approach first, then context-discovery, then implementation skills. "Fix this bug" → debugger first, then verification-before-completion.

Red Flags

警示信号

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.

出现以下想法时请立即停止——你正在找借口：

想法	实际情况
"This is just a simple question"	问题也是任务，请检查是否有适用技能。
"I need more context first"	技能检查要先于澄清问题。
"Let me explore the codebase first"	技能会告诉你如何探索，请先检查。
"I can check git/files quickly"	文件缺乏对话上下文，请检查是否有适用技能。
"Let me gather information first"	技能会告诉你如何收集信息，请先检查。
"This doesn't need a formal skill"	如果存在适用技能，就使用它。
"I remember this skill"	技能会演进，请查看当前版本。
"This doesn't count as a task"	行动就是任务，请检查是否有适用技能。
"The skill is overkill"	简单的事情可能变得复杂，请使用它。
"I'll just do this one thing first"	在做任何事情之前都要先检查。
"This feels productive"	无纪律的行动会浪费时间，技能可以避免这种情况。
"I know what that means"	了解概念≠使用技能，请调用它。

Skill Types

技能类型

Rigid (debugger, verification-before-completion): Follow exactly. Don't adapt away discipline.

Flexible (approach, context-discovery): Adapt principles to context.

The skill itself tells you which.

严格型（debugger、verification-before-completion）：严格遵循，不要偏离规范。

灵活型（approach、context-discovery）：根据上下文调整原则。

技能本身会说明它属于哪一类。

Skill Friendly Names

技能友好名称

When announcing a skill, use the friendly name below (not the internal skill ID):

Skill ID	Friendly Name
`oac-approach`	OAC Approach
`context-discovery`	OAC Context Discovery
`task-breakdown`	OAC Task Breakdown
`code-execution`	OAC Code Execution
`test-generation`	OAC Test Generation
`code-review`	OAC Code Review
`external-research`	OAC External Research
`parallel-execution`	OAC Parallel Execution
`debugger`	OAC Debugger
`verification-before-completion`	OAC Verification
`context-setup`	OAC Context Setup

Example announcement:

OAC skill loaded: OAC Approach — planning before implementation

宣布技能时，请使用下面的友好名称（而非内部技能ID）：

技能ID	友好名称
`oac-approach`	OAC 方法
`context-discovery`	OAC 上下文探索
`task-breakdown`	OAC 任务拆分
`code-execution`	OAC 代码执行
`test-generation`	OAC 测试生成
`code-review`	OAC 代码审查
`external-research`	OAC 外部研究
`parallel-execution`	OAC 并行执行
`debugger`	OAC 调试工具
`verification-before-completion`	OAC 验证
`context-setup`	OAC 上下文设置

Example announcement:

OAC skill loaded: OAC Approach — planning before implementation

User Instructions

用户指令

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

指令说明的是要做什么，而不是怎么做。"Add X"或"Fix Y"并不意味着可以跳过工作流程。