Create Claude Code custom skills with proper structure and metadata. Use when building new skills, setting up skill directories, or packaging skills for distribution.
Creates properly structured Claude Code custom skills with YAML frontmatter and correct file organization. Use when building new skills, setting up directories, or packaging skills for distribution.
/plugin marketplace add flpbalada/thinking-toolkit/plugin install skill-creator@thinking-toolkitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
A guide for creating Claude Code custom skills following Anthropic's official guidelines.
Every skill needs a directory with at minimum one Skill.md file:
my-skill/
└── Skill.md
For complex skills with additional resources:
my-skill/
├── Skill.md
├── REFERENCE.md # Detailed reference docs
└── scripts/
└── helper.py # Executable code (optional)
The Skill.md file must begin with YAML frontmatter:
---
name: my-skill-name
description:
Brief description of what this skill does and when Claude should use it.
Maximum 200 characters.
---
# Skill Title
Your skill content here...
| Field | Max Length | Purpose |
|---|---|---|
name | 64 chars | Human-friendly identifier |
description | 200 chars | Tells Claude when to invoke this skill |
| Field | Example | Purpose |
|---|---|---|
dependencies | python>=3.8, pandas>=1.5.0 | Required software packages |
Structure your skill using progressive disclosure:
Reference additional files in your Skill.md so Claude knows when to access them.
Skills can include executable scripts for advanced functionality:
Supported languages:
Important: Dependencies must be pre-installed. Additional packages cannot be installed at runtime.
Correct structure:
my-skill.zip
└── my-skill/
└── Skill.md
Incorrect structure:
my-skill.zip
└── Skill.md # Wrong! Missing parent folder
Before packaging:
name is ≤64 charactersdescription is ≤200 characters and clearly explains when to useAfter enabling:
Do:
Avoid:
---
name: my-guide
description:
Apply [topic] best practices and guidelines. Use when working on [context] or
need guidance about [subject].
---
# [Topic] Guide
Brief introduction to what this guide covers.
## When to Use
- [Use case 1]
- [Use case 2]
- [Use case 3]
## Core Principles
### Principle 1: [Name]
Explanation and examples.
### Principle 2: [Name]
Explanation and examples.
## Step-by-Step Process
1. **[Step name]** - Description
2. **[Step name]** - Description
3. **[Step name]** - Description
## Examples
### Good Example
\`\`\` [code or text example] \`\`\`
### Bad Example
\`\`\` [code or text example] \`\`\`
## Common Mistakes
- [Mistake 1] - How to avoid
- [Mistake 2] - How to avoid
---
name: generate-something
description:
Generate [type of code] following project conventions. Use when creating new
[components/modules/files] or need boilerplate for [context].
---
# [Type] Generator
Creates [type of code] with consistent structure and patterns.
## When to Use
- Creating new [component type]
- Need boilerplate for [context]
- Setting up [feature type]
## Generated Structure
\`\`\` [directory structure] \`\`\`
## Required Inputs
| Input | Description | Example |
| ----- | ------------- | ------------- |
| Name | [description] | `MyComponent` |
| Type | [description] | `form` |
## Output Format
### [File 1]
\`\`\`[language] // Template with placeholders [code template] \`\`\`
### [File 2]
\`\`\`[language] [code template] \`\`\`
## Conventions
- [Convention 1]
- [Convention 2]
- [Convention 3]
## Customization Options
- **[Option 1]**: [description]
- **[Option 2]**: [description]
---
name: analyze-something
description:
Analyze [subject] for [purpose]. Use when reviewing [context], investigating
[issues], or evaluating [criteria].
---
# [Subject] Analyzer
Systematic analysis of [subject] to identify [outcomes].
## When to Use
- Reviewing [context]
- Investigating [type of issues]
- Evaluating [criteria]
- Before [action/decision]
## Analysis Framework
### Phase 1: [Name]
- [ ] Check [item]
- [ ] Verify [item]
- [ ] Review [item]
### Phase 2: [Name]
- [ ] Examine [item]
- [ ] Test [item]
- [ ] Validate [item]
### Phase 3: [Name]
- [ ] Assess [item]
- [ ] Measure [item]
- [ ] Document [item]
## Evaluation Criteria
| Criteria | Weight | Description |
| ------------ | ------ | ------------- |
| [Criteria 1] | High | [Description] |
| [Criteria 2] | Medium | [Description] |
| [Criteria 3] | Low | [Description] |
## Output Template
\`\`\`markdown
## Analysis Summary
**Subject:** [what was analyzed] **Date:** [date]
### Findings
1. [Finding 1]
2. [Finding 2]
### Recommendations
- [Recommendation 1]
- [Recommendation 2]
### Risk Level
[Low/Medium/High] - [justification] \`\`\`
## Red Flags
- [Red flag 1] - indicates [problem]
- [Red flag 2] - indicates [problem]
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.