skill-creator

Anthropic ｜ Agent 與工作流 ｜ 原文 ｜ Apache-2.0

建立有效 skill 的指南，講結構、漸進式揭露和打包流程

---
name: skill-creator
description: 建立有效 skill 的指南。當使用者想建立新 skill（或更新現有 skill），為 Claude 的能力加上專門知識、工作流程或工具整合時，應該使用這個 skill。
license: Complete terms in LICENSE.txt
---

# Skill Creator

這個 skill 提供建立有效 skill 的指引。

## 關於 Skill

Skill 是模組化、自給自足的套件，透過提供專門知識、工作流程和工具來擴充 Claude 的能力。
可以把它們想成特定領域或任務的「新人上手指南」，它們把 Claude 從通用型 agent
變成具備程序性知識的專門 agent，而這種知識是任何模型都無法完整擁有的。

### Skill 能提供什麼

1. 專門的工作流程：針對特定領域的多步驟程序
2. 工具整合：說明如何處理特定檔案格式或 API
3. 領域專業知識：公司專屬的知識、schema、商業邏輯
4. 附帶資源：用於複雜、重複任務的 script、參考資料和素材

## 核心原則

### 簡潔是關鍵

Context window 是公共財。Skill 要跟 Claude 需要的所有其他東西共用 context window：system prompt、對話歷史、其他 Skill 的 metadata，還有使用者實際的請求。

**預設假設：Claude 已經很聰明。** 只加入 Claude 還沒有的 context。對每一則資訊都要質疑："Claude 真的需要這段說明嗎？" 還有 "這一段值得花這些 token 嗎？"

簡潔的範例優於冗長的說明。

### 設定適當的自由度

讓具體程度配合任務的脆弱度和變化程度：

**高自由度（文字說明）**：用在有多種做法都可行、決策取決於 context，或由經驗法則引導做法的時候。

**中自由度（偽代碼或帶參數的 script）**：用在有偏好的模式、允許某些變化，或設定會影響行為的時候。

**低自由度（特定 script、少量參數）**：用在操作脆弱又容易出錯、一致性很關鍵，或必須照特定順序執行的時候。

把 Claude 想成在探索一條路：兩側是懸崖的窄橋需要明確的護欄（低自由度），空曠的原野則允許走很多路線（高自由度）。

### Skill 的結構

每個 skill 都有一個必要的 SKILL.md 檔，以及選用的附帶資源：

```
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.)
```

#### SKILL.md（必要）

每個 SKILL.md 包含：

- **Frontmatter**（YAML）：包含 `name` 和 `description` 欄位。Claude 只會讀這兩個欄位來判斷什麼時候使用這個 skill，所以要把這個 skill 是什麼、什麼時候該用，描述得清楚又完整，這點非常重要。
- **本文**（Markdown）：使用這個 skill 的說明與指引。只有在 skill 觸發「之後」才會載入（如果有載入的話）。

#### 附帶資源（選用）

##### Script（`scripts/`）

需要確定性可靠度、或經常被重寫的任務所用的可執行程式碼（Python/Bash 等）。

- **什麼時候該放**：同一段程式碼一再被重寫，或需要確定性的可靠度時
- **範例**：處理 PDF 旋轉任務的 `scripts/rotate_pdf.py`
- **好處**：省 token、結果確定，而且可以不載入 context 就直接執行
- **注意**：Claude 可能還是需要讀 script，以便修補或做環境專屬的調整

##### 參考資料（`references/`）

需要時才載入 context 的文件和參考資料，用來輔助 Claude 的流程和思考。

- **什麼時候該放**：Claude 工作時應該參考的文件
- **範例**：財務 schema 用 `references/finance.md`、公司 NDA 範本用 `references/mnda.md`、公司政策用 `references/policies.md`、API 規格用 `references/api_docs.md`
- **使用情境**：資料庫 schema、API 文件、領域知識、公司政策、詳細的工作流程指南
- **好處**：讓 SKILL.md 保持精簡，只在 Claude 判斷需要時才載入
- **最佳實務**：如果檔案很大（>10k 字），在 SKILL.md 裡附上 grep 搜尋模式
- **避免重複**：資訊應該放在 SKILL.md 或參考檔其中之一，不要兩邊都放。除非真的是 skill 的核心，否則詳細資訊優先放參考檔，這樣 SKILL.md 保持精簡，資訊也找得到，又不會佔用 context window。SKILL.md 只留必要的程序指示和工作流程指引，詳細的參考資料、schema 和範例移到參考檔。

##### 素材（`assets/`）

不打算載入 context，而是用在 Claude 產出成果裡的檔案。

- **什麼時候該放**：skill 需要在最終成果中使用某些檔案時
- **範例**：品牌素材用 `assets/logo.png`、PowerPoint 範本用 `assets/slides.pptx`、HTML/React 樣板用 `assets/frontend-template/`、字型用 `assets/font.ttf`
- **使用情境**：範本、圖片、圖示、樣板程式碼、字型、會被複製或修改的範例文件
- **好處**：把輸出資源和文件分開，讓 Claude 不用載入 context 就能使用這些檔案

#### Skill 裡不該放什麼

Skill 只該包含直接支援其功能的必要檔案。「不要」建立多餘的文件或輔助檔案，包括：

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

Skill 只該放 AI agent 完成手上工作所需的資訊。不該包含建立它的過程、安裝與測試程序、給使用者看的文件這類輔助脈絡。多建文件只會增加雜亂和混淆。

### 漸進式揭露的設計原則

Skill 用三層載入機制來有效管理 context：

1. **Metadata（name + description）**：永遠在 context 裡（約 100 字）
2. **SKILL.md 本文**：skill 觸發時才載入（<5k 字）
3. **附帶資源**：Claude 需要時才載入（無上限，因為 script 可以不讀進 context window 就執行）

#### 漸進式揭露的模式

SKILL.md 本文只放重點，並控制在 500 行以內，減少 context 膨脹。接近這個上限時就把內容拆成獨立檔案。拆出去之後，一定要在 SKILL.md 裡參照它們，並清楚說明什麼時候該讀，這樣讀 skill 的人才知道它們存在、什麼時候該用。

**關鍵原則：** 當 skill 支援多種變體、框架或選項時，SKILL.md 只留核心工作流程和選擇指引。變體專屬的細節（模式、範例、設定）移到獨立的參考檔。

**模式 1：高階指南加參考檔**

```markdown
# PDF Processing

## Quick start

Extract text with pdfplumber:
[code example]

## Advanced features

- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns
```

Claude 只在需要時才載入 FORMS.md、REFERENCE.md 或 EXAMPLES.md。

**模式 2：依領域組織**

對於有多個領域的 Skill，依領域組織內容，避免載入不相關的 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)
```

使用者問到銷售指標時，Claude 只會讀 sales.md。

同樣地，對於支援多個框架或變體的 skill，依變體組織：

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

使用者選擇 AWS 時，Claude 只會讀 aws.md。

**模式 3：條件式細節**

先呈現基本內容，再連結到進階內容：

```markdown
# DOCX Processing

## Creating documents

Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).

## Editing documents

For simple edits, modify the XML directly.

**For tracked changes**: See [REDLINING.md](REDLINING.md)
**For OOXML details**: See [OOXML.md](OOXML.md)
```

Claude 只在使用者需要那些功能時，才會讀 REDLINING.md 或 OOXML.md。

**重要準則：**

- **避免多層巢狀的參照**：參照要從 SKILL.md 起算只深一層。所有參考檔都應該直接從 SKILL.md 連結。
- **替較長的參考檔加目錄**：超過 100 行的檔案，在開頭放目錄，讓 Claude 預覽時能看到完整範圍。

## Skill 建立流程

建立 skill 包含這些步驟：

1. 用具體範例理解這個 skill
2. 規劃可重複使用的 skill 內容（script、參考資料、素材）
3. 初始化 skill（執行 init_skill.py）
4. 編輯 skill（實作資源並撰寫 SKILL.md）
5. 打包 skill（執行 package_skill.py）
6. 依實際使用狀況迭代

照順序做這些步驟，只有在有明確理由說明不適用時才能跳過。

### 步驟 1：用具體範例理解 Skill

只有在 skill 的使用模式已經很清楚時才跳過這一步。即使是處理現有的 skill，這一步仍然有價值。

要建立有效的 skill，得清楚理解這個 skill 會怎麼被使用的具體範例。這種理解可以來自使用者直接給的範例，或是產生出來、並經使用者回饋驗證過的範例。

舉例來說，建立 image-editor skill 時，相關的問題包括：

- "image-editor skill 要支援什麼功能？編輯、旋轉，還有別的嗎？"
- "可以舉幾個這個 skill 會怎麼被使用的例子嗎？"
- "我想得到使用者可能會說『幫我去除這張圖的紅眼』或『旋轉這張圖』。你還想到其他使用方式嗎？"
- "使用者說什麼話應該觸發這個 skill？"

為了避免讓使用者應接不暇，不要在一則訊息裡問太多問題。先從最重要的問題開始，需要時再追問，效果會比較好。

當你清楚這個 skill 該支援什麼功能時，就結束這一步。

### 步驟 2：規劃可重複使用的 Skill 內容

要把具體範例變成有效的 skill，對每個範例這樣分析：

1. 想想怎麼從零開始執行這個範例
2. 找出重複執行這些工作流程時，哪些 script、參考資料和素材會有幫助

範例：建立 `pdf-editor` skill 來處理 "幫我旋轉這個 PDF" 這類請求時，分析結果是：

1. 旋轉 PDF 每次都得重寫同樣的程式碼
2. 在 skill 裡存一個 `scripts/rotate_pdf.py` script 會很有幫助

範例：設計 `frontend-webapp-builder` skill 來處理 "幫我做一個 todo app" 或 "幫我做一個追蹤步數的儀表板" 這類請求時，分析結果是：

1. 寫前端 webapp 每次都需要同樣的 HTML/React 樣板
2. 在 skill 裡存一個含樣板 HTML/React 專案檔的 `assets/hello-world/` 範本會很有幫助

範例：建立 `big-query` skill 來處理 "今天有多少使用者登入？" 這類請求時，分析結果是：

1. 查詢 BigQuery 每次都得重新摸索資料表 schema 和關聯
2. 在 skill 裡存一份記錄資料表 schema 的 `references/schema.md` 檔會很有幫助

要決定 skill 的內容，就分析每個具體範例，整理出要放進去的可重複使用資源清單：script、參考資料和素材。

### 步驟 3：初始化 Skill

到這一步，就是要真的建立 skill 了。

只有在要開發的 skill 已經存在、只需要迭代或打包時，才跳過這一步。這種情況就直接進入下一步。

從零開始建立新 skill 時，一律要執行 `init_skill.py` script。這個 script 會方便地產生新的範本 skill 目錄，自動包含 skill 需要的一切，讓建立 skill 的流程更有效率也更可靠。

用法：

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

這個 script 會：

- 在指定路徑建立 skill 目錄
- 產生帶有正確 frontmatter 和 TODO 佔位符的 SKILL.md 範本
- 建立範例資源目錄：`scripts/`、`references/` 和 `assets/`
- 在每個目錄加入可以自訂或刪除的範例檔

初始化之後，依需要自訂或移除產生的 SKILL.md 和範例檔。

### 步驟 4：編輯 Skill

編輯（新產生的或現有的）skill 時，記得這個 skill 是為了另一個 Claude 實例而建立的。放進對 Claude 有幫助、而且不顯而易見的資訊。想想哪些程序性知識、領域專屬細節或可重複使用的素材，能幫另一個 Claude 實例更有效地執行這些任務。

#### 學習已驗證的設計模式

依 skill 的需求參考這些指南：

- **多步驟流程**：順序式工作流程和條件邏輯，見 references/workflows.md
- **特定輸出格式或品質標準**：範本和範例模式，見 references/output-patterns.md

這些檔案包含有效 skill 設計的既定最佳實務。

#### 從可重複使用的 Skill 內容開始

開始實作時，先從前面找出來的可重複使用資源下手：`scripts/`、`references/` 和 `assets/` 檔案。注意這一步可能需要使用者提供輸入。例如實作 `brand-guidelines` skill 時，使用者可能需要提供品牌素材或範本放進 `assets/`，或提供文件放進 `references/`。

加入的 script 一定要實際跑過測試，確保沒有 bug、輸出符合預期。如果有很多類似的 script，只需要測試具代表性的樣本，就能確信它們都能運作，同時兼顧完成時間。

所有 skill 用不到的範例檔案和目錄都應該刪除。初始化 script 會在 `scripts/`、`references/` 和 `assets/` 裡建立範例檔來示範結構，但大部分 skill 不會全都用到。

#### 更新 SKILL.md

**撰寫準則：** 一律使用祈使句／不定詞形式。

##### Frontmatter

撰寫含 `name` 和 `description` 的 YAML frontmatter：

- `name`：skill 名稱
- `description`：這是 skill 主要的觸發機制，幫助 Claude 理解什麼時候該用這個 skill。
  - 要同時寫出這個 Skill 做什麼，以及什麼時候該用的具體觸發條件／情境。
  - 所有「什麼時候用」的資訊都放在這裡，不要放本文。本文只在觸發之後才載入，所以本文裡的「When to Use This Skill」段落對 Claude 沒有幫助。
  - `docx` skill 的 description 範例："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"

YAML frontmatter 不要放任何其他欄位。

##### 本文

撰寫使用這個 skill 及其附帶資源的說明。

### 步驟 5：打包 Skill

skill 開發完成後，必須打包成可散布的 .skill 檔，再分享給使用者。打包流程會先自動驗證 skill，確保符合所有要求：

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

可選的輸出目錄指定：

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

打包 script 會：

1. 自動**驗證** skill，檢查：

   - YAML frontmatter 格式和必要欄位
   - Skill 命名慣例和目錄結構
   - Description 的完整度和品質
   - 檔案組織和資源參照

2. 驗證通過就**打包**，建立以 skill 命名的 .skill 檔（例如 `my-skill.skill`），包含所有檔案並維持散布所需的正確目錄結構。.skill 檔就是副檔名為 .skill 的 zip 檔。

如果驗證失敗，script 會回報錯誤並結束，不會建立套件。修好驗證錯誤後，再執行一次打包指令。

### 步驟 6：迭代

測試 skill 之後，使用者可能會要求改進。這通常發生在剛用完 skill、對 skill 表現還記憶猶新的時候。

**迭代工作流程：**

1. 在真實任務上使用這個 skill
2. 注意哪裡卡住或沒效率
3. 找出 SKILL.md 或附帶資源該怎麼更新
4. 實作修改並再次測試

---
name: skill-creator
description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
license: Complete terms in LICENSE.txt
---

# Skill Creator

This skill provides guidance for creating effective skills.

## About Skills

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.

### What Skills Provide

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

## Core Principles

### Concise is Key

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.

### Set Appropriate Degrees of Freedom

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).

### Anatomy of a Skill

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.)
```

#### SKILL.md (required)

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).

#### Bundled Resources (optional)

##### Scripts (`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

##### References (`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.

##### Assets (`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

#### What to Not Include in a Skill

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.

### Progressive Disclosure Design Principle

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

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

#### Progressive Disclosure Patterns

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
# PDF Processing

## Quick start

Extract text with pdfplumber:
[code example]

## Advanced features

- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
- **Examples**: See [EXAMPLES.md](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
# DOCX Processing

## Creating documents

Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).

## Editing documents

For simple edits, modify the XML directly.

**For tracked changes**: See [REDLINING.md](REDLINING.md)
**For OOXML details**: See [OOXML.md](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.

## Skill Creation Process

Skill creation involves these steps:

1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Initialize the skill (run init_skill.py)
4. Edit the skill (implement resources and write SKILL.md)
5. Package the skill (run package_skill.py)
6. Iterate based on real usage

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

### Step 1: Understanding the Skill with Concrete Examples

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.

### Step 2: Planning the Reusable Skill Contents

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

1. Considering how to execute on the example from scratch
2. 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:

1. Rotating a PDF requires re-writing the same code each time
2. 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:

1. Writing a frontend webapp requires the same boilerplate HTML/React each time
2. 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:

1. Querying BigQuery requires re-discovering the table schemas and relationships each time
2. 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.

### Step 3: Initializing the 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.

### Step 4: Edit the 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.

#### Learn Proven Design Patterns

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.

#### Start with Reusable Skill Contents

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.

#### Update SKILL.md

**Writing Guidelines:** Always use imperative/infinitive form.

##### Frontmatter

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.

##### Body

Write instructions for using the skill and its bundled resources.

### Step 5: Packaging a 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:

1. **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

2. **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.

### Step 6: Iterate

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:**

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