Agent Skill

Skill Creator

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.

AI Agent·热情与甜心·来自 skill_hub·skillhub.cn ↗
skillhub install @user_0210c829/qclaw-skill-creator-pro
10 Stars·9.4万 综合热度·18,685 字文档·源站更新 2026-11-22

README 文档

18,685 字

Skill Creator

This skill provides guidance for creating effective skills.

About Skills

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

Skill vs Prompt vs MCP

维度PromptSkillMCP
本质单次对话指令持久化能力单元标准化工具接入协议
生命周期用完就丢写一次永久复用编写一次全平台通用
触发方式手动输入AI自动识别调用AI调用函数
可带资源❌ 纯文字✅ 脚本+文档+资源✅ 工具定义
团队共享❌ 难✅ Git管理✅ 注册表
类比说一句话给一本操作手册装一个USB接口

核心区别: Skill 解决"怎么干"(知识+流程),MCP 解决"能不能连"(工具+接口),Prompt 解决"当下这一句"(即时指令)。

@'

2. Step 1 标题和新增 Research First 段落

$content = $content -replace '### Step 1: Understanding the Skill with Concrete Examples', @'

Skill Composition Pattern

复杂 Skill 可以引用其他 Skill 或 Subagent,形成多阶段工作流:

solution-workflow/
├── SKILL.md                    ← 主编排器(定义步骤和调用顺序)
├── references/
│   ├── requirement-analyst.md  ← 需求分析师 Subagent
│   ├── tech-researcher.md      ← 技术调研员 Subagent
│   └── reviewer.md             ← 审查员 Subagent
└── scripts/
    └── validate-output.py      ← 输出校验脚本

主编排器 SKILL.md 写法:

# 技术方案工作流

## 步骤 1:需求澄清
调用 requirement-analyst Subagent,等待输出 docs/requirements.md

## 步骤 2:并行调研
同时启动多个 tech-researcher Subagent(≤7 个并发),分别产出独立报告

## 步骤 3:方案编写
调用 solution-architect Subagent,输入需求文档 + 所有调研报告

## 步骤 4:审查与改写循环
- 调用 reviewer 审查方案
- 若 fail → 调用 rewriter 修改 → 回到步骤 4
- 最多循环 5 次

关键原则:Skill 是"流程编排说明书",告诉主 Agent 何时调用哪个 Subagent,而不负责具体实现。每个 Subagent 有独立上下文和工具权限。

1a. Research First (强烈推荐)

凭空想出来的 Skill 和质量差距 10 倍。在动笔之前,让 AI 搜索目标领域的最佳实践、常见问题和社区推荐的做法:

你:我想创建一个 Go 代码审查的 Skill。
请先搜索 Go 代码审查的最佳实践、常见问题和社区推荐的检查维度,
然后帮我设计一个完整的 Skill 结构。

这步能帮 AI 发现人类自己可能忽略的检查维度、行业规范和反模式。简单 Skill(<200行)可跳过,复杂领域 Skill(安全/架构/合规)必做。

1b. Understand with Concrete Examples

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)
│   │   └── compatibility: (optional, rarely needed)
│   └── 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 (required), plus optional fields like license, metadata, and compatibility. Only name and description are read by Claude to determine when the skill triggers, so be clear and comprehensive about what the skill is and when it should be used. The compatibility field is for noting environment requirements (target product, system packages, etc.) but most skills don't need it.
  • 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

# 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:

# 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.

⚠️ MANDATORY: Use init_skill.py — No Manual Creation

Creating a new skill MUST use scripts/initskill.py. Do NOT manually create skill directories or SKILL.md files with mkdir, writeto_file, or any other method.

# The ONLY correct way to create a new skill:
scripts/init_skill.py <skill-name> --path ~/.qclaw/skills
# Windows:
python scripts\init_skill.py <skill-name> --path %USERPROFILE%\.qclaw\skills
  • ✅ Correct: Run scripts/init_skill.py news-paper-test --path ~/.qclaw/skills → creates ~/.qclaw/skills/news-paper-test/
  • ❌ FORBIDDEN: Manually writing files to ~/.qclaw/skills/ or any other path
  • ❌ FORBIDDEN: Using mkdir + writetofile to create skill structure
  • ❌ FORBIDDEN: Writing to ~/.qclaw/workspace/... or resources/openclaw/config/skills/...

The script handles directory creation, path validation, and template generation. Manual creation bypasses these safeguards and leads to incorrect paths. No exceptions.

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.

Planning tip: After research (Step 1a) and example analysis, write a one-paragraph Scope Statement that defines what the skill covers — and what it deliberately leaves out. This prevents scope creep and keeps SKILL.md under 500 lines.

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.

MANDATORY: You MUST run init_skill.py to create the skill directory and template files. Do NOT manually create directories or write SKILL.md files yourself. The script ensures correct path, directory structure, and template format.

Usage:

scripts/init_skill.py <skill-name> --path ~/.qclaw/skills

On Windows:

python scripts\init_skill.py <skill-name> --path %USERPROFILE%\.qclaw\skills

CRITICAL: The --path MUST be set to ~/.qclaw/skills (Windows: %USERPROFILE%\.qclaw\skills). This ensures user-created skills persist across application updates. Example: scripts/init_skill.py say-hi --path ~/.qclaw/skills creates ~/.qclaw/skills/say-hi/.

NEVER create skills in the application's bundled skills directory (e.g., resources/openclaw/config/skills/ or any path containing openclaw/config/skills). That directory is reserved for built-in skills shipped with the application and is completely replaced during updates — any user-created skills placed there will be permanently lost.

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 (lowercase + hyphens, 1-64 chars))
  • description: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill.
  • 推荐模板: Use when [触发条件/关键词] to [目标行动] by [核心操作] while [重要限制]
  • Include both what the Skill does and specific triggers/contexts for when to use it.
  • 同时写"什么时候不用"(负面案例),告诉 AI 不该用的场景同样重要:
    description: >
      生成PPT演示文稿。Use when users mention PowerPoint, slides,
      or presentation. Do NOT use when user only needs a quick text summary.
  • 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"
  • allowed-tools (可选): 允许使用的工具白名单,如 Read, Bash(grep:*)。限制工具范围可防止 AI 用错工具。
  • context: fork (可选): 设为 fork 时在隔离子代理中运行,避免污染主会话上下文。
  • agent (可选): 指定子代理类型(仅 context:fork 时有效)。
  • metadata (可选): 元信息对象,可包含:
  • version: 版本号,如 "1.0.0"
  • domain: 领域标签,如 backend / frontend / data
  • triggers: 触发关键词列表
  • author: 作者信息

示例:

  metadata:
    version: "1.0.0"
    domain: backend
    triggers: [SpringBoot, REST API, JPA]

Do not include any other fields in YAML frontmatter.

Body

Write instructions for using the skill and its bundled resources.

⚠️ Mandatory: Gotchas Section

这是 ROI 最高的单项改进。 每个 Skill 的 SKILL.md 正文末尾必须包含一个 ## ⚠️ Gotchas 段落,专门写"AI 容易犯的错误和陷阱":

## ⚠️ Gotchas

- **不要用 rm -rf 删除任何目录** — 使用 trash 命令代替
- **数据库操作前必须先备份** — 执行 scripts/backup.sh
- **不要修改代码,只做审查** — 这是 review 不是 fix
- **大文件(>1000行)分段审查** — 一次性全读会超出上下文
- **遇到二进制文件直接跳过** — 不要尝试解析 .png/.pdf

为什么必写?AI 特别容易在边缘情况上翻车——默认行为不等于安全行为。一个 Gotcha 能救一条命。

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:

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

Optional output directory specification:

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
  1. 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

Quality Self-Check List

写完 Skill 后,对照这份清单自查:

  • [ ] description 是否明确了触发条件和能力边界?
  • [ ] SKILL.md 是否少于 500 行?
  • [ ] 是否每个 Skill 只解决一个问题(单一职责)?
  • [ ] 是否有代码示例或命令模板(而非纯文字描述)?
  • [ ] 是否有 Gotchas 部分预防常见错误?
  • [ ] 详细文档是否移到了 references/?
  • [ ] 需要确定性执行的操作是否写成了 scripts?
  • [ ] 是否在至少 3 个真实场景测试过(正常/边缘/不适用)?
  • [ ] 是否假设了工具已安装?(应明确写安装命令)
  • [ ] name 是否全小写+连字符?
  • [ ] description 是否包含负面案例(不该用的场景)?
  • [ ] 复杂 Skill 是否在动笔前做了调研(Step 1a)?

同分类其他技能

查看全部 ›