using-ltk

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Using ltk Skills

使用ltk Skills

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.
极为重要:
如果你认为哪怕只有1%的可能性某个技能可能适用于你正在做的事情,你也绝对必须调用该技能。
如果某一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。你不能找借口跳过这一步。

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.
In other environments: Check your platform's documentation for how skills are loaded.
在Claude Code中: 使用
Skill
工具。当你调用一个技能时,其内容会被加载并呈现给你——请严格按照内容执行。切勿对技能文件使用Read工具。
在其他环境中: 查看你所使用平台的文档,了解技能的加载方式。

Using Skills

使用技能

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.
在任何回复或操作之前调用相关或被请求的技能。 哪怕只有1%的可能性技能适用,你也应该调用技能进行确认。如果调用的技能最终不适合当前场景,你可以不用它。

Flow

流程

  1. User message received
  2. Might any skill apply? (even 1% chance)
  3. YES -> Invoke Skill tool, announce "Using [skill] for [purpose]"
  4. If skill has checklist -> Create TodoWrite todo per item
  5. Follow skill exactly
  6. Then respond (including clarifications)
  1. 收到用户消息
  2. 是否有任何技能可能适用?(哪怕只有1%的可能性)
  3. 是 -> 调用Skill工具,告知“正在使用[技能名称]完成[目的]”
  4. 如果技能包含检查清单 -> 针对每个条目创建TodoWrite待办事项
  5. 严格遵循技能要求
  6. 然后再进行回复(包括澄清问题)

Red Flags

警示信号

These thoughts mean STOP - you're rationalizing:
ThoughtReality
"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——你正在找借口跳过规则:
想法实际情况
“这只是个简单问题”问题也是任务。请检查是否有适用技能。
“我需要先获取更多上下文”技能检查要先于澄清问题。
“我先探索一下代码库”技能会告诉你如何探索。先检查技能。
“我可以快速查看git/文件”文件缺乏对话上下文。请检查是否有适用技能。
“我先收集一下信息”技能会告诉你如何收集信息。
“这个不需要正式技能”如果存在相关技能,就必须使用。
“我记得这个技能”技能会更新。请查看当前版本。
“这不算是任务”任何行动都是任务。请检查是否有适用技能。
“用这个技能大材小用了”简单的事情也可能变得复杂。请使用技能。
“我先做这一件小事”在做任何事情之前先检查技能。
“这样做效率很高”无纪律的行动会浪费时间。技能可以避免这种情况。
“我知道那是什么意思”了解概念不等于会使用技能。请调用它。

Skill Priority

技能优先级

When multiple skills could apply, use this order:
  1. Process skills first (brainstorming, debugging) - these determine HOW to approach the task
  2. Implementation skills second (language-specific, framework-specific) - these guide execution
"Let's build X" -> brainstorming/planning first, then implementation skills. "Fix this bug" -> systematic-debugging first, then domain-specific skills.
当多个技能可能适用时,请按照以下顺序选择:
  1. 优先使用流程类技能(头脑风暴、调试)——这些技能决定了你处理任务的方式
  2. 其次使用实现类技能(特定语言、特定框架)——这些技能指导具体执行
例如:“我们来构建X” -> 先使用头脑风暴/规划类技能,再使用实现类技能。 “修复这个bug” -> 先使用系统化调试技能,再使用特定领域技能。

Skill Types

技能类型

Rigid (TDD, debugging, verification): Follow exactly. Don't adapt away discipline.
Flexible (patterns, guides): Adapt principles to context.
The skill itself tells you which.
严格型(TDD、调试、验证):严格遵循要求。不要随意调整纪律要求。
灵活型(模式、指南):根据上下文调整原则。
技能本身会说明其类型。

Core ltk Skills

核心ltk Skills

These are the foundational skills you should know about:
SkillWhen to Use
verification-before-completion
Before ANY completion claim, commit, or PR
systematic-debugging
When encountering bugs, test failures, unexpected behavior
test-driven-development
When implementing any feature or bugfix
writing-plans
When planning implementation of features
executing-plans
When executing a written plan
以下是你应该了解的基础技能:
技能使用场景
verification-before-completion
在任何完成声明、提交或PR之前
systematic-debugging
遇到bug、测试失败或异常行为时
test-driven-development
实现任何功能或修复bug时
writing-plans
规划功能实现时
executing-plans
执行书面计划时

User Instructions

用户指令

Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.
指令告诉你要做什么,而不是怎么做。“添加X”或“修复Y”并不意味着可以跳过工作流程。