Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问clear审计通过

skill-creator技能创建器

Agent Skill

skill-creator 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

470

周安装

19

GitHub Stars

8

下载量

147
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skill-creator(技能创建器)
来源仓库:https://github.com/vamseeachanta/workspace-hub
仓库路径:skills/skill-creator
安装命令:
npx skills add https://github.com/vamseeachanta/workspace-hub --skill skill-creator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/vamseeachanta/workspace-hub --skill skill-creator

简介

用于查找、检索和筛选相关信息,适合根据关键词、任务场景或来源线索快速定位候选结果。

  • 可结合来源仓库、安装命令和原始 README 继续核验具体用法。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 安装命令:npx skills add https://github.com/vamseeachanta/workspace-hub --skill skill-creator
  • 适用于 Codex、Claude、Cursor、Gemini CLI 等宿主环境。

SKILL.md

Skill Creator Skill

Overview

This skill guides the creation of new Claude Code skills. Skills are specialized instruction sets that enhance Claude's capabilities for specific domains, tasks, or workflows.

Quick Start

  1. Define scope - Answer: What problem? Who uses it? What outputs?
  2. Create structure - .claude/skills/skill-name/SKILL.md
  3. Write frontmatter - Name, description, version, category
  4. Add content - Overview, Instructions, Examples, Best Practices
  5. Test - Verify skill triggers correctly
# Create skill directory
mkdir -p .claude/skills/my-new-skill

# Create SKILL.md with template
cat > .claude/skills/my-new-skill/SKILL.md << 'EOF'
---
name: my-new-skill
description: Action-oriented description. Use for X, Y, and Z.
version: 1.0.0
category: [builders|tools|content-design|communication|meta]
---

# My New Skill

## Overview
[1-2 sentences explaining purpose]

## Instructions
[Step-by-step guidance]

## Examples
[Concrete examples]
EOF

When to Use

  • Building custom skills for specific domains
  • Creating reusable workflow templates
  • Standardizing organizational processes
  • Extending Claude Code capabilities
  • Documenting specialized knowledge

Skill Anatomy

File Structure

.claude/skills/
└── skill-name/
    ├── SKILL.md           # Required: Main skill definition
    └── resources/         # Optional: Supporting files
        ├── templates/
        ├── examples/
        └── data/

SKILL.md Structure

---
name: skill-name
description: One-line description of what this skill does and when to use it.
version: 1.0.0
category: builders
last_updated: 2026-01-02
related_skills:
  - related-skill-1
  - related-skill-2
---

# Skill Title

## Overview
Brief explanation of the skill's purpose and capabilities.

## Quick Start
Fastest path to value.

## When to Use
- Scenario 1
- Scenario 2
- Scenario 3

## Instructions
Detailed instructions for how to apply the skill.

## Examples
Concrete examples of the skill in action.

## Best Practices
Guidelines for effective use.

## Error Handling
Common issues and solutions.

## Metrics
How to measure success.

## Related Skills
Links to complementary skills.

## Version History
- **1.0.0** (YYYY-MM-DD): Initial release

Skill Design Principles

1. Clear Triggering

The description field is crucial--it determines when the skill activates:

Good descriptions:

description: Create professional presentations with python-pptx. Use for slide decks, pitch presentations, and visual reports.

Bad descriptions:

description: A skill for presentations.  # Too vague
description: This skill helps you...     # Starts with filler

Tips for descriptions:

  • Start with an action verb
  • Include specific use cases
  • Mention key technologies/tools
  • Keep under 200 characters

2. Progressive Disclosure

Structure content from general to specific:

## Overview
High-level purpose (always loaded)

## Quick Start
Fastest path to value

## Detailed Instructions
Comprehensive guidance

## Advanced Usage
Edge cases and optimization

## Reference
Complete API/options reference

3. Actionable Content

Every section should guide action:

## Bad: Conceptual only
CSS is a styling language for web pages.

## Good: Actionable
To style a button with hover effects:
\`\`\`css
.button {
    background: #007bff;
    transition: background 0.2s;
}
.button:hover {
    background: #0056b3;
}
\`\`\`

Creating a New Skill

Step 1: Define the Skill Scope

Answer these questions:

  1. What specific problem does this skill solve?
  2. Who is the target user?
  3. What inputs does it expect?
  4. What outputs does it produce?
  5. What tools/technologies does it use?

Step 2: Write the Frontmatter

---
name: lowercase-kebab-case
description: Action-oriented description with use cases. Use for X, Y, and Z.
version: 1.0.0
category: builders
last_updated: 2026-01-02
related_skills:
  - related-skill-1
---

Naming conventions:

  • Use lowercase with hyphens: api-testing, data-viz
  • Be descriptive but concise
  • Avoid generic names like helper or utils

Step 3: Structure the Content

Overview Section

## Overview

[1-2 sentences explaining what this skill enables]

**Key Capabilities:**
- Capability 1
- Capability 2
- Capability 3

Instructions Section

## Instructions

### [Task Category 1]

[Step-by-step instructions]

\`\`\`language
// Code example
\`\`\`

### [Task Category 2]

[More instructions with examples]

Examples Section

## Examples

### Example 1: [Scenario Name]

**Input:** [What user provides]

**Process:** [What skill does]

**Output:** [What user receives]

\`\`\`
// Complete working example
\`\`\`

Step 4: Add Supporting Materials

If needed, create resources:

skill-name/
├── SKILL.md
└── resources/
    ├── templates/
    │   └── starter.template
    ├── examples/
    │   └── complete-example.py
    └── config/
        └── defaults.yaml

Reference them in SKILL.md:

See [starter template](resources/templates/starter.template) for a quick start.

Skill Templates

Technical Skill Template

---
name: tech-skill-name
description: Technical capability description. Use for specific technical tasks.
version: 1.0.0
category: builders
---

# Technical Skill Name

## Overview

This skill provides [capability] using [technology/tool].

## Prerequisites

- Dependency 1
- Dependency 2

## Installation

\`\`\`bash
# Installation commands
\`\`\`

## Quick Start

\`\`\`language
// Minimal working example
\`\`\`

## Core Operations

### Operation 1

\`\`\`language
// Code
\`\`\`

### Operation 2

\`\`\`language
// Code
\`\`\`

## Configuration Options

| Option | Type | Default | Description |
|--------|------|---------|-------------|
| option1 | string | "default" | Description |

## Error Handling

### Common Errors

**Error: [Error Name]**
- Cause: [Why it happens]
- Solution: [How to fix]

## Best Practices

1. Practice 1
2. Practice 2
3. Practice 3

Process Skill Template

---
name: process-skill-name
description: Process/workflow description. Use for organizational tasks.
version: 1.0.0
category: communication
---

# Process Skill Name

## Overview

This skill guides [process type] for [outcome].

## When to Use

- Situation 1
- Situation 2
- Situation 3

## Process Steps

### Step 1: [Name]

[Instructions]

**Checklist:**
- [ ] Item 1
- [ ] Item 2

### Step 2: [Name]

[Instructions]

**Template:**
\`\`\`
[Template content]
\`\`\`

### Step 3: [Name]

[Instructions]

## Templates

### [Template Name]

\`\`\`
[Full template]
\`\`\`

## Examples

### [Scenario]

[Complete worked example]

## Tips

- Tip 1
- Tip 2
- Tip 3

Creative Skill Template

---
name: creative-skill-name
description: Creative capability description. Use for design/content creation.
version: 1.0.0
category: content-design
---

# Creative Skill Name

## Overview

This skill enables creation of [output type] with [characteristics].

## Design Principles

### Principle 1: [Name]
[Explanation]

### Principle 2: [Name]
[Explanation]

## Styles & Variations

### Style 1: [Name]
[Description and examples]

### Style 2: [Name]
[Description and examples]

## Creation Process

### Phase 1: [Name]
[Instructions]

### Phase 2: [Name]
[Instructions]

## Technical Implementation

\`\`\`language
// Code for creating the output
\`\`\`

## Quality Checklist

- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3

## Inspiration & Examples

[Gallery of examples with explanations]

Execution Checklist

Before creating a skill:

  • Scope clearly defined (problem, users, inputs, outputs)
  • Name follows kebab-case convention
  • Description is action-oriented with use cases

During creation:

  • Frontmatter complete (name, description, version, category)
  • Overview explains value in 2-3 sentences
  • Quick Start provides immediate value
  • Instructions are actionable, not conceptual
  • Examples are complete and runnable

After creation:

  • Skill triggers correctly when invoked
  • Code examples tested and working
  • Related skills referenced in new skill's frontmatter
  • Existing related skills updated — search for skills that overlap or compose with this one; add this skill to their related_skills: frontmatter (bidirectional linking is mandatory)
  • Version history added

Skill Quality Checklist

Content Quality

  • Description clearly states purpose and trigger conditions
  • Overview explains value proposition in 2-3 sentences
  • Instructions are actionable, not just conceptual
  • Examples are complete and runnable
  • Best practices are specific and justified

Structure Quality

  • Follows progressive disclosure (general -> specific)
  • Uses consistent heading hierarchy
  • Code blocks have language tags
  • Tables are properly formatted
  • Lists are parallel in structure

Usability

  • Can be used without reading entire document
  • Quick start enables immediate value
  • Error scenarios are addressed
  • Edge cases are documented
  • Related skills are referenced

Technical Accuracy

  • Code examples are tested and work
  • Dependencies are listed
  • Version requirements are specified
  • Installation steps are complete

Error Handling

Common Errors

Error: Skill not triggering

  • Cause: Description too vague or doesn't match user intent
  • Solution: Rewrite description with specific use cases and action verbs

Error: Skill content too large

  • Cause: Too much content in single SKILL.md
  • Solution: Move large examples to resources/ folder, keep SKILL.md under 500 lines

Error: Circular skill references

  • Cause: Skills reference each other in loops
  • Solution: Review related_skills, ensure DAG structure

Error: Outdated code examples

  • Cause: Dependencies or APIs changed
  • Solution: Test examples regularly, update version history

Skill Maintenance

Versioning

Track significant changes:

<!-- At end of SKILL.md -->

---
## Version History

- **1.2.0** (2025-01-15): Added new feature X
- **1.1.0** (2024-12-01): Updated examples for tool v2
- **1.0.0** (2024-10-15): Initial release

Deprecation

When retiring a skill:

---
name: old-skill-name
description: DEPRECATED - Use new-skill-name instead. [Original description]
deprecated: true
deprecated_date: 2026-01-02
replacement: new-skill-name
---

Metrics

Track skill effectiveness:

MetricTargetHow to Measure
Trigger accuracy>90%Skill activates when intended
Completion rate>85%Users complete skill workflow
Error rate<10%Failed executions / total
Update frequencyMonthlyLast update within 30 days
User satisfaction>4/5Feedback ratings

Integration with Claude Code

Skill Discovery

Skills are discovered from:

  1. .claude/skills/ in project directory
  2. ~/.claude/skills/ for user-level skills

Skill Loading

  • Metadata: Always loaded (name, description)
  • Body: Loaded when skill is triggered
  • Resources: Loaded on demand

Best Practices for Performance

  1. Keep SKILL.md focused (under 500 lines ideal)
  2. Move large examples to resources/
  3. Reference external documentation for comprehensive APIs
  4. Use code blocks sparingly--quality over quantity

Related Skills


Version History

  • 2.0.0 (2026-01-02): Upgraded to v2 template - added Quick Start, When to Use, Execution Checklist, Error Handling, Metrics sections; enhanced frontmatter with version, category, related_skills
  • 1.0.0 (2024-10-15): Initial release with skill anatomy, design principles, templates, quality checklist

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

27.48%
按下载量换算40

windsurf

21.33%
按下载量换算31

trae

17.17%
按下载量换算25

OpenCode

14.04%
按下载量换算21

Cursor

7.32%
按下载量换算11

Codex

3.91%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills