skill-system-creator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Creator

Skill 创建工具

This skill provides guidance for creating effective skills.

本Skill为创建高效Skill提供指导。

About Skills

关于Skill

Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.

Skill是模块化、独立的包，通过提供专业知识、工作流和工具来扩展Claude的能力。可以将其视为特定领域或任务的“入职指南”——它们能将Claude从通用型Agent转变为具备程序知识的专业型Agent，而这类知识是任何模型都无法完全拥有的。

What Skills Provide

Skill能提供什么

Specialized workflows - Multi-step procedures for specific domains
Tool integrations - Instructions for working with specific file formats or APIs
Domain expertise - Company-specific knowledge, schemas, business logic
Bundled resources - Scripts, references, and assets for complex and repetitive tasks

专业工作流 - 特定领域的多步骤流程
工具集成 - 处理特定文件格式或API的操作指南
领域专业知识 - 公司专属知识、架构、业务逻辑
捆绑资源 - 用于复杂重复任务的脚本、参考资料和资产

Core Principles

核心原则

Concise is Key

简洁是关键

The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.

Default assumption: Claude is already very smart. Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?"

Prefer concise examples over verbose explanations.

上下文窗口是公共资源。Skill需要与Claude所需的其他所有内容共享上下文窗口：系统提示、对话历史、其他Skill的元数据以及实际的用户请求。

默认假设：Claude已经非常智能。 只添加Claude原本不具备的上下文信息。对每一条信息都要提出质疑：“Claude真的需要这个解释吗？”以及“这段内容的token成本是否值得？”

优先使用简洁的示例，而非冗长的解释。

Set Appropriate Degrees of Freedom

设置适当的自由度

Match the level of specificity to the task's fragility and variability:

High freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.

Medium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.

Low freedom (specific scripts, few parameters): Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.

Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).

根据任务的脆弱性和可变性匹配具体程度：

高自由度（基于文本的指令）：当存在多种有效方法、决策依赖于上下文，或需要启发式方法指导时使用。

中自由度（带参数的伪代码或脚本）：当存在首选模式、允许一定变化，或配置会影响行为时使用。

低自由度（特定脚本，参数极少）：当操作脆弱且容易出错、一致性至关重要，或必须遵循特定顺序时使用。

可以把Claude想象成在探索路径：两侧是悬崖的狭窄桥梁需要明确的护栏（低自由度），而开阔的场地则允许多种路线（高自由度）。

Anatomy of a Skill

Skill的结构

Every skill consists of a required SKILL.md file and optional bundled resources:

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)

每个Skill都包含一个必填的SKILL.md文件和可选的捆绑资源：

skill-name/
├── SKILL.md (必填)
│   ├── YAML前置元数据 (必填)
│   │   ├── name: (必填)
│   │   └── description: (必填)
│   └── Markdown指令 (必填)
└── 捆绑资源 (可选)
    ├── scripts/          - 可执行代码（Python/Bash等）
    ├── references/       - 按需加载到上下文的文档
    └── assets/           - 输出中使用的文件（模板、图标、字体等）

SKILL.md (required)

SKILL.md（必填）

Every SKILL.md consists of:

Frontmatter (YAML): Contains
```
name
```
and
```
description
```
fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.
Body (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).

每个SKILL.md包含：

前置元数据（YAML）：包含
```
name
```
和
```
description
```
字段。这是Claude判断何时使用该Skill的唯一依据，因此清晰、全面地描述Skill的功能和适用场景至关重要。
主体内容（Markdown）：使用Skill及其捆绑资源的指令和指南。仅在Skill被触发后才会加载（如果需要的话）。

Bundled Resources (optional)

捆绑资源（可选）

Scripts (

scripts/

)

脚本（

scripts/

）

Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.

When to include: When the same code is being rewritten repeatedly or deterministic reliability is needed
Example:
```
scripts/rotate_pdf.py
```
for PDF rotation tasks
Benefits: Token efficient, deterministic, may be executed without loading into context
Note: Scripts may still need to be read by Claude for patching or environment-specific adjustments

用于需要确定性可靠性或重复编写的任务的可执行代码（Python/Bash等）。

何时包含：当相同的代码需要重复编写，或需要确定性可靠性时
示例：用于PDF旋转任务的
```
scripts/rotate_pdf.py
```
优势：Token效率高、结果确定，无需加载到上下文即可执行
注意：Claude可能仍需要读取脚本以进行补丁或针对特定环境调整

References (

references/

)

参考资料（

references/

）

Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.

When to include: For documentation that Claude should reference while working
Examples:
```
references/finance.md
```
for financial schemas,
```
references/mnda.md
```
for company NDA template,
```
references/policies.md
```
for company policies,
```
references/api_docs.md
```
for API specifications
Use cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
Benefits: Keeps SKILL.md lean, loaded only when Claude determines it's needed
Best practice: If files are large (>10k words), include grep search patterns in SKILL.md
Avoid duplication: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.

用于指导Claude流程和思考的文档和参考资料，可按需加载到上下文。

何时包含：当Claude在工作时需要参考文档时
示例：用于财务架构的
```
references/finance.md
```
、用于公司NDA模板的
```
references/mnda.md
```
、用于公司政策的
```
references/policies.md
```
、用于API规范的
```
references/api_docs.md
```
使用场景：数据库架构、API文档、领域知识、公司政策、详细工作流指南
优势：保持SKILL.md简洁，仅在Claude确定需要时才加载
最佳实践：如果文件较大（>10000字），在SKILL.md中包含grep搜索模式
避免重复：信息应仅存在于SKILL.md或参考文件中，不要重复。除非是Skill的核心内容，否则优先将详细信息放在参考文件中——这样可以保持SKILL.md简洁，同时让信息可被发现而不占用上下文窗口。仅在SKILL.md中保留必要的流程指令和工作流指南；将详细的参考资料、架构和示例移至参考文件。

Assets (

assets/

)

资产（

assets/

）

Files not intended to be loaded into context, but rather used within the output Claude produces.

When to include: When the skill needs files that will be used in the final output
Examples:
```
assets/logo.png
```
for brand assets,
```
assets/slides.pptx
```
for PowerPoint templates,
```
assets/frontend-template/
```
for HTML/React boilerplate,
```
assets/font.ttf
```
for typography
Use cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
Benefits: Separates output resources from documentation, enables Claude to use files without loading them into context

不加载到上下文，而是用于Claude生成的输出中的文件。

何时包含：当Skill需要用于最终输出的文件时
示例：用于品牌资产的
```
assets/logo.png
```
、用于PowerPoint模板的
```
assets/slides.pptx
```
、用于HTML/React样板的
```
assets/frontend-template/
```
、用于排版的
```
assets/font.ttf
```
使用场景：模板、图片、图标、样板代码、字体、可复制或修改的示例文档
优势：将输出资源与文档分离，使Claude无需加载即可使用文件

What to Not Include in a Skill

Skill中不应包含的内容

A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:

README.md
INSTALLATION_GUIDE.md
QUICK_REFERENCE.md
CHANGELOG.md
etc.

The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.

Skill应仅包含直接支持其功能的必要文件。请勿创建无关的文档或辅助文件，包括：

README.md
INSTALLATION_GUIDE.md
QUICK_REFERENCE.md
CHANGELOG.md
等等

Skill应仅包含AI Agent完成当前工作所需的信息。不应包含关于Skill创建过程、设置和测试流程、面向用户的文档等辅助上下文。创建额外的文档文件只会增加混乱和干扰。

Progressive Disclosure Design Principle

渐进式披露设计原则

Skills use a three-level loading system to manage context efficiently:

Metadata (name + description) - Always in context (~100 words)
SKILL.md body - When skill triggers (<5k words)
Bundled resources - As needed by Claude (Unlimited because scripts can be executed without reading into context window)

Skill使用三级加载系统来高效管理上下文：

元数据（名称+描述） - 始终在上下文中（约100字）
SKILL.md主体 - 当Skill被触发时（<5000字）
捆绑资源 - 由Claude按需加载（无限制，因为脚本无需读取到上下文窗口即可执行）

Progressive Disclosure Patterns

渐进式披露模式

Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.

Key principle: When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.

Pattern 1: High-level guide with references

markdown

undefined

保持SKILL.md主体内容精简，控制在500行以内，以减少上下文膨胀。当接近此限制时，将内容拆分为单独的文件。在将内容拆分到其他文件时，务必从SKILL.md中引用它们，并明确描述何时读取，以确保Skill的使用者知道它们的存在和使用时机。

核心原则：当Skill支持多种变体、框架或选项时，仅在SKILL.md中保留核心工作流和选择指南。将变体特定的细节（模式、示例、配置）移至单独的参考文件中。

模式1：带参考资料的高级指南

markdown

undefined

PDF Processing

PDF处理

Quick start

快速开始

Extract text with pdfplumber: [code example]

使用pdfplumber提取文本： [代码示例]

Advanced features

高级功能

Form filling: See FORMS.md for complete guide
API reference: See REFERENCE.md for all methods
Examples: See EXAMPLES.md for common patterns


Claude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.

**Pattern 2: Domain-specific organization**

For Skills with multiple domains, organize content by domain to avoid loading irrelevant context:

bigquery-skill/ ├── SKILL.md (overview and navigation) └── reference/ ├── finance.md (revenue, billing metrics) ├── sales.md (opportunities, pipeline) ├── product.md (API usage, features) └── marketing.md (campaigns, attribution)


When a user asks about sales metrics, Claude only reads sales.md.

Similarly, for skills supporting multiple frameworks or variants, organize by variant:

cloud-deploy/ ├── SKILL.md (workflow + provider selection) └── references/ ├── aws.md (AWS deployment patterns) ├── gcp.md (GCP deployment patterns) └── azure.md (Azure deployment patterns)


When the user chooses AWS, Claude only reads aws.md.

**Pattern 3: Conditional details**

Show basic content, link to advanced content:

```markdown

表单填写：完整指南请参见FORMS.md
API参考：所有方法请参见REFERENCE.md
示例：常见模式请参见EXAMPLES.md


Claude仅在需要时才会加载FORMS.md、REFERENCE.md或EXAMPLES.md。

**模式2：按领域组织**

对于包含多个领域的Skill，按领域组织内容以避免加载无关上下文：

bigquery-skill/ ├── SKILL.md（概述和导航） └── reference/ ├── finance.md（收入、计费指标） ├── sales.md（销售机会、销售漏斗） ├── product.md（API使用、功能） └── marketing.md（营销活动、归因）


当用户询问销售指标时，Claude仅读取sales.md。

类似地，对于支持多个框架或变体的Skill，按变体组织：

cloud-deploy/ ├── SKILL.md（工作流+供应商选择） └── references/ ├── aws.md（AWS部署模式） ├── gcp.md（GCP部署模式） └── azure.md（Azure部署模式）


当用户选择AWS时，Claude仅读取aws.md。

**模式3：条件式细节**

显示基础内容，链接到高级内容：

```markdown

DOCX Processing

DOCX处理

Creating documents

创建文档

Use docx-js for new documents. See DOCX-JS.md.

使用docx-js创建新文档。请参见DOCX-JS.md。

Editing documents

编辑文档

For simple edits, modify the XML directly.

For tracked changes: See REDLINING.md For OOXML details: See OOXML.md


Claude reads REDLINING.md or OOXML.md only when the user needs those features.

**Important guidelines:**

- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.
- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing.

对于简单编辑，直接修改XML即可。

对于修订跟踪：请参见REDLINING.md 对于OOXML细节：请参见OOXML.md


Claude仅在用户需要这些功能时才会读取REDLINING.md或OOXML.md。

**重要指南**：

- **避免深层嵌套引用** - 保持引用与SKILL.md处于同一层级。所有参考文件应直接从SKILL.md链接。
- **结构化较长的参考文件** - 对于超过100行的文件，在顶部包含目录，以便Claude在预览时能看到完整范围。

Skill Creation Process

Skill创建流程

Skill creation follows a Spec → Test → Develop workflow:

Understand the skill with concrete examples

Create behavior spec (

SKILL.spec.yaml

via

skill-system-behavior:create-spec

)

Validate the spec (
```
skill-system-behavior:validate-spec
```
)
Define acceptance tests (structural + behavioral, from spec)
Initialize the skill (run init_skill.py)
Implement the skill (resources + SKILL.md — make tests pass)
Verify structural tests (
```
skill-system-behavior:verify-structural
```
)
Generate behavior contract (
```
skill-system-behavior:generate-contract
```
)
Package the skill (run package_skill.py)
Iterate based on real usage

Follow these steps in order, skipping only if there is a clear reason why they are not applicable.

Skill创建遵循规范→测试→开发的工作流：

通过具体示例理解Skill

创建行为规范（通过

skill-system-behavior:create-spec

生成

SKILL.spec.yaml

）

验证规范（
```
skill-system-behavior:validate-spec
```
）
定义验收测试（来自规范的结构+行为测试）
初始化Skill（运行init_skill.py）
实现Skill（资源+SKILL.md — 确保测试通过）
验证结构测试（
```
skill-system-behavior:verify-structural
```
）
生成行为契约（
```
skill-system-behavior:generate-contract
```
）
打包Skill（运行package_skill.py）
根据实际使用情况迭代

按顺序执行这些步骤，仅在有明确理由说明不适用时才跳过。

Why Spec-First?

为什么要先做规范？

Contract-first: forces clear operation boundaries before coding
Testable: acceptance criteria are executable, not aspirational
Prevents scope creep: spec defines what's in, everything else is out
Generated docs: behavior contracts (Mermaid DAGs) are derived from specs, not hand-written

契约优先：在编码前明确操作边界
可测试：验收标准是可执行的，而非理想化的
防止范围蔓延：规范定义了包含的内容，其他内容均不纳入
生成文档：行为契约（Mermaid DAG）从规范衍生，而非手动编写

Step 1: Understanding the Skill with Concrete Examples

步骤1：通过具体示例理解Skill

Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.

To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.

For example, when building an image-editor skill, relevant questions include:

"What functionality should the image-editor skill support? Editing, rotating, anything else?"
"Can you give some examples of how this skill would be used?"
"I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?"
"What would a user say that should trigger this skill?"

To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.

Conclude this step when there is a clear sense of the functionality the skill should support.

仅当Skill的使用模式已清晰理解时才跳过此步骤。即使处理现有Skill，此步骤仍然有价值。

要创建有效的Skill，需清晰理解Skill的具体使用示例。这种理解可以来自直接的用户示例，或经过用户反馈验证的生成示例。

例如，在构建图像编辑器Skill时，相关问题包括：

“图像编辑器Skill应支持哪些功能？编辑、旋转，还是其他？”
“你能举一些这个Skill的使用示例吗？”
“我能想象用户会要求‘去除这张图片的红眼’或‘旋转这张图片’。你认为用户还会以其他方式使用这个Skill吗？”
“用户说什么话应该触发这个Skill？”

为避免使用户不知所措，请勿在一条消息中提出过多问题。从最重要的问题开始，根据需要跟进以提高有效性。

当对Skill应支持的功能有清晰认识时，结束此步骤。

Step 2: Planning the Reusable Skill Contents

步骤2：规划可复用的Skill内容

To turn concrete examples into an effective skill, analyze each example by:

Considering how to execute on the example from scratch
Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly

Example: When building a

pdf-editor

skill to handle queries like "Help me rotate this PDF," the analysis shows:

Rotating a PDF requires re-writing the same code each time
A
```
scripts/rotate_pdf.py
```
script would be helpful to store in the skill

Example: When designing a

frontend-webapp-builder

skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:

Writing a frontend webapp requires the same boilerplate HTML/React each time
An
```
assets/hello-world/
```
template containing the boilerplate HTML/React project files would be helpful to store in the skill

Example: When building a

big-query

skill to handle queries like "How many users have logged in today?" the analysis shows:

Querying BigQuery requires re-discovering the table schemas and relationships each time
A
```
references/schema.md
```
file documenting the table schemas would be helpful to store in the skill

To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.

要将具体示例转化为有效的Skill，请按以下方式分析每个示例：

考虑如何从头开始执行示例
确定在重复执行这些工作流时，哪些脚本、参考资料和资产会有帮助

示例：当构建

pdf-editor

Skill来处理“帮我旋转这个PDF”之类的查询时，分析表明：

旋转PDF需要每次重写相同的代码
在Skill中存储
```
scripts/rotate_pdf.py
```
脚本会很有帮助

示例：当为“帮我构建一个待办事项应用”或“帮我构建一个跟踪步数的仪表板”之类的查询设计

frontend-webapp-builder

Skill时，分析表明：

编写前端Web应用每次都需要相同的HTML/React样板代码
在Skill中存储包含HTML/React项目样板文件的
```
assets/hello-world/
```
模板会很有帮助

示例：当构建

big-query

Skill来处理“今天有多少用户登录？”之类的查询时，分析表明：

查询BigQuery需要每次重新发现表架构和关系
在Skill中存储记录表架构的
```
references/schema.md
```
文件会很有帮助

要确定Skill的内容，请分析每个具体示例，创建要包含的可复用资源列表：脚本、参考资料和资产。

Step 3: Initializing the Skill

步骤3：初始化Skill

At this point, it is time to actually create the skill.

Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.

When creating a new skill from scratch, always run the

init_skill.py

script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.

Usage:

bash

scripts/init_skill.py <skill-name> --path <output-directory>

The script:

Creates the skill directory at the specified path
Generates a SKILL.md template with proper frontmatter and TODO placeholders
Creates example resource directories:
```
scripts/
```
,
```
references/
```
, and
```
assets/
```
Adds example files in each directory that can be customized or deleted

After initialization, customize or remove the generated SKILL.md and example files as needed.

此时，是时候实际创建Skill了。

仅当正在开发的Skill已存在，且需要迭代或打包时才跳过此步骤。在这种情况下，继续下一步。

从头创建新Skill时，请始终运行

init_skill.py

脚本。该脚本会方便地生成一个新的模板Skill目录，自动包含Skill所需的所有内容，使Skill创建过程更加高效和可靠。

用法：

bash

scripts/init_skill.py <skill-name> --path <output-directory>

该脚本：

在指定路径创建Skill目录
生成带有正确前置元数据和待办事项占位符的SKILL.md模板
创建示例资源目录：
```
scripts/
```
、
```
references/
```
和
```
assets/
```
在每个目录中添加可自定义或删除的示例文件

初始化后，根据需要自定义或删除生成的SKILL.md和示例文件。

Step 4: Edit the Skill

步骤4：编辑Skill

When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.

在编辑（新生成或现有）Skill时，请记住该Skill是为另一个Claude实例使用而创建的。包含对Claude有益且非显而易见的信息。考虑哪些程序知识、领域特定细节或可复用资产能帮助另一个Claude实例更有效地执行这些任务。

PostgreSQL DB targeting standard (mandatory when storage is PostgreSQL)

PostgreSQL数据库目标标准（当存储为PostgreSQL时为必填）

Resolve DB target by
```
SKILL_PGDATABASE
```
first.
Reject ambient
```
PGDATABASE
```
when
```
SKILL_PGDATABASE
```
is absent.
Otherwise auto-detect from project name as
```
<project>-memory
```
.
Avoid hardcoded DB names in runtime scripts.

首先通过
```
SKILL_PGDATABASE
```
解析数据库目标。
当
```
SKILL_PGDATABASE
```
不存在时，拒绝使用环境变量
```
PGDATABASE
```
。
否则根据项目名称自动检测为
```
<project>-memory
```
。
避免在运行时脚本中使用硬编码的数据库名称。

Learn Proven Design Patterns

学习经过验证的设计模式

Consult these helpful guides based on your skill's needs:

Multi-step processes: See references/workflows.md for sequential workflows and conditional logic
Specific output formats or quality standards: See references/output-patterns.md for template and example patterns

These files contain established best practices for effective skill design.

根据Skill的需求参考以下有用指南：

多步骤流程：请参见references/workflows.md了解顺序工作流和条件逻辑
特定输出格式或质量标准：请参见references/output-patterns.md了解模板和示例模式

这些文件包含有效Skill设计的既定最佳实践。

Start with Reusable Skill Contents

从可复用Skill内容开始

To begin implementation, start with the reusable resources identified above:

scripts/

references/

, and

assets/

files. Note that this step may require user input. For example, when implementing a

brand-guidelines

skill, the user may need to provide brand assets or templates to store in

assets/

, or documentation to store in

references/

Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.

Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in

scripts/

references/

, and

assets/

to demonstrate structure, but most skills won't need all of them.

要开始实现，请从上面确定的可复用资源开始：

scripts/

、

references/

和

assets/

文件。请注意，此步骤可能需要用户输入。例如，在实现

brand-guidelines

Skill时，用户可能需要提供品牌资产或模板以存储在

assets/

中，或提供文档以存储在

references/

中。

添加的脚本必须通过实际运行来测试，以确保没有错误且输出符合预期。如果有许多类似的脚本，只需测试代表性样本即可，在确保所有脚本正常工作的同时平衡完成时间。

任何Skill不需要的示例文件和目录都应删除。初始化脚本会在

scripts/

、

references/

和

assets/

中创建示例文件以展示结构，但大多数Skill不需要所有这些文件。

Update SKILL.md

更新SKILL.md

Writing Guidelines: Always use imperative/infinitive form.

写作指南：始终使用祈使语气/不定式形式。

Frontmatter

前置元数据

Write the YAML frontmatter with

name

and

description

```
name
```
: The skill name
```
description
```
: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill.
- Include both what the Skill does and specific triggers/contexts for when to use it.
- Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to Claude.
- Example description for a
```
docx
```
  skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"

Do not include any other fields in YAML frontmatter.

编写包含

name

和

description

的YAML前置元数据：

```
name
```
：Skill名称
```
description
```
：这是Skill的主要触发机制，帮助Claude理解何时使用该Skill。
- 同时包含Skill的功能以及使用它的特定触发条件/上下文。
- 所有“何时使用”的信息都应放在这里 - 不要放在主体中。主体仅在触发后才加载，因此主体中的“何时使用本Skill”部分对Claude没有帮助。
- ```
docx
```
  Skill的描述示例：“全面的文档创建、编辑和分析，支持修订跟踪、批注、格式保留和文本提取。当Claude需要处理专业文档（.docx文件）时使用，包括：(1) 创建新文档，(2) 修改或编辑内容，(3) 处理修订跟踪，(4) 添加批注，或任何其他文档任务”

请勿在YAML前置元数据中包含任何其他字段。

Body

主体内容

Write instructions for using the skill and its bundled resources.

编写使用Skill及其捆绑资源的指令。

Step 5: Packaging a Skill

步骤5：打包Skill

Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:

bash

scripts/package_skill.py <path/to/skill-folder>

Optional output directory specification:

bash

scripts/package_skill.py <path/to/skill-folder> ./dist

The packaging script will:

Validate the skill automatically, checking:
- YAML frontmatter format and required fields
- Skill naming conventions and directory structure
- Description completeness and quality
- File organization and resource references
Package the skill if validation passes, creating a .skill file named after the skill (e.g.,
```
my-skill.skill
```
) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.

If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.

Skill开发完成后，必须将其打包为可分发的.skill文件与用户共享。打包过程会自动先验证Skill，确保其符合所有要求：

bash

scripts/package_skill.py <path/to/skill-folder>

可选的输出目录指定：

bash

scripts/package_skill.py <path/to/skill-folder> ./dist

打包脚本将：

验证自动验证Skill，检查：
- YAML前置元数据格式和必填字段
- Skill命名约定和目录结构
- 描述的完整性和质量
- 文件组织和资源引用
打包如果验证通过，则创建一个以Skill命名的.skill文件（例如
```
my-skill.skill
```
），包含所有文件并保持适当的目录结构以便分发。.skill文件是带有.skill扩展名的zip文件。

如果验证失败，脚本将报告错误并不创建包。修复所有验证错误后，再次运行打包命令。

Step 6: Iterate

步骤6：迭代

After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.

Iteration workflow:

Use the skill on real tasks
Notice struggles or inefficiencies
Identify how SKILL.md or bundled resources should be updated
Implement changes and test again

skill

{
  "schema_version": "2.0",
  "id": "skill-system-creator",
  "version": "1.0.0",
  "capabilities": ["skill-create", "skill-validate", "skill-package", "artifact-gap-analysis", "artifact-generate", "artifact-brainstorm", "artifact-eval"],
  "effects": ["fs.read", "fs.write", "proc.exec"],
  "operations": {
    "init": {
      "description": "Initialize a new skill directory with SKILL.md template and resource folders.",
      "input": {
        "skill_name": { "type": "string", "required": true, "description": "Name for the new skill" },
        "output_dir": { "type": "string", "required": false, "description": "Directory to create skill in" }
      },
      "output": {
        "description": "Path to created skill directory",
        "fields": { "path": "string" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/init_skill.py", "{skill_name}", "--path", "{output_dir}"],
        "windows": ["python", "scripts/init_skill.py", "{skill_name}", "--path", "{output_dir}"]
      }
    },
    "package": {
      "description": "Validate and package a skill into a distributable .skill file.",
      "input": {
        "skill_path": { "type": "string", "required": true, "description": "Path to skill folder" }
      },
      "output": {
        "description": "Path to .skill package file",
        "fields": { "package_path": "string" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/package_skill.py", "{skill_path}"],
        "windows": ["python", "scripts/package_skill.py", "{skill_path}"]
      }
    },
    "suggest-artifacts": {
      "description": "Detect creator artifact gaps by reading behavior graph plus skills-index.json and returning ranked suggestions.",
      "input": {
        "repo_root": { "type": "string", "required": false, "description": "Repository root" }
      },
      "output": {
        "description": "Ranked artifact suggestions",
        "fields": { "suggestions": "array" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "suggest-artifacts"],
        "windows": ["python", "scripts/creator_tool.py", "suggest-artifacts"]
      }
    },
    "generate": {
      "description": "Generate creator artifacts with deterministic template + validation (currently supports --type script).",
      "input": {
        "artifact_type": { "type": "string", "required": true, "description": "Artifact type; script supported" },
        "name": { "type": "string", "required": true, "description": "Artifact file name" },
        "output_dir": { "type": "string", "required": true, "description": "Output directory" },
        "force": { "type": "boolean", "required": false, "description": "Overwrite when target exists" }
      },
      "output": {
        "description": "Generation and validation result",
        "fields": { "artifact": "object", "validation": "object", "structural_validation": "object" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "generate", "--type", "{artifact_type}", "--name", "{name}", "--output-dir", "{output_dir}"],
        "windows": ["python", "scripts/creator_tool.py", "generate", "--type", "{artifact_type}", "--name", "{name}", "--output-dir", "{output_dir}"]
      }
    },
    "brainstorm": {
      "description": "Combine memory learnings and graph/spec structure into ranked improvement suggestions.",
      "input": {
        "limit": { "type": "number", "required": false, "description": "Suggestion limit" },
        "memory_limit": { "type": "number", "required": false, "description": "Memory sample limit" }
      },
      "output": {
        "description": "Ranked brainstorm suggestions with rationale",
        "fields": { "suggestions": "array" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "brainstorm"],
        "windows": ["python", "scripts/creator_tool.py", "brainstorm"]
      }
    },
    "eval": {
      "description": "Route artifact evaluation through skill-system-gate and emit pass/fail with improvement suggestions.",
      "input": {
        "artifact_path": { "type": "string", "required": true, "description": "Artifact path" },
        "rules_template": { "type": "string", "required": false, "description": "Optional rules template" }
      },
      "output": {
        "description": "Gate evaluation report",
        "fields": { "passed": "boolean", "gate_summary": "object", "improvement_suggestions": "array" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "eval", "--artifact", "{artifact_path}"],
        "windows": ["python", "scripts/creator_tool.py", "eval", "--artifact", "{artifact_path}"]
      }
    }
  },
  "stdout_contract": {
    "last_line_json": true
  }
}

测试Skill后，用户可能会要求改进。这通常发生在使用Skill后不久，用户对Skill的表现有清晰的印象。

迭代工作流：

在实际任务中使用Skill
注意遇到的困难或低效之处
确定应如何更新SKILL.md或捆绑资源
实施更改并再次测试

skill

{
  "schema_version": "2.0",
  "id": "skill-system-creator",
  "version": "1.0.0",
  "capabilities": ["skill-create", "skill-validate", "skill-package", "artifact-gap-analysis", "artifact-generate", "artifact-brainstorm", "artifact-eval"],
  "effects": ["fs.read", "fs.write", "proc.exec"],
  "operations": {
    "init": {
      "description": "Initialize a new skill directory with SKILL.md template and resource folders.",
      "input": {
        "skill_name": { "type": "string", "required": true, "description": "Name for the new skill" },
        "output_dir": { "type": "string", "required": false, "description": "Directory to create skill in" }
      },
      "output": {
        "description": "Path to created skill directory",
        "fields": { "path": "string" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/init_skill.py", "{skill_name}", "--path", "{output_dir}"],
        "windows": ["python", "scripts/init_skill.py", "{skill_name}", "--path", "{output_dir}"]
      }
    },
    "package": {
      "description": "Validate and package a skill into a distributable .skill file.",
      "input": {
        "skill_path": { "type": "string", "required": true, "description": "Path to skill folder" }
      },
      "output": {
        "description": "Path to .skill package file",
        "fields": { "package_path": "string" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/package_skill.py", "{skill_path}"],
        "windows": ["python", "scripts/package_skill.py", "{skill_path}"]
      }
    },
    "suggest-artifacts": {
      "description": "Detect creator artifact gaps by reading behavior graph plus skills-index.json and returning ranked suggestions.",
      "input": {
        "repo_root": { "type": "string", "required": false, "description": "Repository root" }
      },
      "output": {
        "description": "Ranked artifact suggestions",
        "fields": { "suggestions": "array" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "suggest-artifacts"],
        "windows": ["python", "scripts/creator_tool.py", "suggest-artifacts"]
      }
    },
    "generate": {
      "description": "Generate creator artifacts with deterministic template + validation (currently supports --type script).",
      "input": {
        "artifact_type": { "type": "string", "required": true, "description": "Artifact type; script supported" },
        "name": { "type": "string", "required": true, "description": "Artifact file name" },
        "output_dir": { "type": "string", "required": true, "description": "Output directory" },
        "force": { "type": "boolean", "required": false, "description": "Overwrite when target exists" }
      },
      "output": {
        "description": "Generation and validation result",
        "fields": { "artifact": "object", "validation": "object", "structural_validation": "object" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "generate", "--type", "{artifact_type}", "--name", "{name}", "--output-dir", "{output_dir}"],
        "windows": ["python", "scripts/creator_tool.py", "generate", "--type", "{artifact_type}", "--name", "{name}", "--output-dir", "{output_dir}"]
      }
    },
    "brainstorm": {
      "description": "Combine memory learnings and graph/spec structure into ranked improvement suggestions.",
      "input": {
        "limit": { "type": "number", "required": false, "description": "Suggestion limit" },
        "memory_limit": { "type": "number", "required": false, "description": "Memory sample limit" }
      },
      "output": {
        "description": "Ranked brainstorm suggestions with rationale",
        "fields": { "suggestions": "array" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "brainstorm"],
        "windows": ["python", "scripts/creator_tool.py", "brainstorm"]
      }
    },
    "eval": {
      "description": "Route artifact evaluation through skill-system-gate and emit pass/fail with improvement suggestions.",
      "input": {
        "artifact_path": { "type": "string", "required": true, "description": "Artifact path" },
        "rules_template": { "type": "string", "required": false, "description": "Optional rules template" }
      },
      "output": {
        "description": "Gate evaluation report",
        "fields": { "passed": "boolean", "gate_summary": "object", "improvement_suggestions": "array" }
      },
      "entrypoints": {
        "unix": ["python3", "scripts/creator_tool.py", "eval", "--artifact", "{artifact_path}"],
        "windows": ["python", "scripts/creator_tool.py", "eval", "--artifact", "{artifact_path}"]
      }
    }
  },
  "stdout_contract": {
    "last_line_json": true
  }
}

skill-system-creator

Original

Translation

Skill Creator

Skill 创建工具

About Skills

关于Skill

What Skills Provide

Skill能提供什么

Core Principles

核心原则

Concise is Key

简洁是关键

Set Appropriate Degrees of Freedom

设置适当的自由度

Anatomy of a Skill

Skill的结构

SKILL.md (required)

SKILL.md（必填）

Bundled Resources (optional)

捆绑资源（可选）

Scripts (scripts/)

脚本（scripts/）

References (references/)

参考资料（references/）

Assets (assets/)

资产（assets/）

What to Not Include in a Skill

Skill中不应包含的内容

Progressive Disclosure Design Principle

渐进式披露设计原则

Progressive Disclosure Patterns

渐进式披露模式

PDF Processing

PDF处理

Quick start

快速开始

Advanced features

高级功能

DOCX Processing

DOCX处理

Creating documents

创建文档

Editing documents

编辑文档

Skill Creation Process

Skill创建流程

Why Spec-First?

为什么要先做规范？

Step 1: Understanding the Skill with Concrete Examples

步骤1：通过具体示例理解Skill

Step 2: Planning the Reusable Skill Contents

步骤2：规划可复用的Skill内容

Step 3: Initializing the Skill

步骤3：初始化Skill

Step 4: Edit the Skill

步骤4：编辑Skill

PostgreSQL DB targeting standard (mandatory when storage is PostgreSQL)

PostgreSQL数据库目标标准（当存储为PostgreSQL时为必填）

Learn Proven Design Patterns

学习经过验证的设计模式

Start with Reusable Skill Contents

从可复用Skill内容开始

Update SKILL.md

更新SKILL.md

Frontmatter

前置元数据

Body

主体内容

Step 5: Packaging a Skill

步骤5：打包Skill

Step 6: Iterate

步骤6：迭代

Scripts (
`scripts/`
)

脚本（
`scripts/`
）

References (
`references/`
)

参考资料（
`references/`
）

Assets (
`assets/`
)

资产（
`assets/`
）