Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
68 changes: 68 additions & 0 deletions .claude/skills/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
# LLM Agent Skills for End Users

This directory contains skills for GitHub Copilot and other LLM agents to help developers use Ignite UI Web Components effectively in their applications.

## What are Skills?

Skills are structured instructions that help AI agents understand and execute common tasks consistently. Each skill is a self-contained guide that provides step-by-step instructions, code examples, and best practices.

## Available Skills

| Skill | Description | Use When |
| ----------------------------------------------------------- | ---------------------------------------------------------------------------------- | ------------------------------------- |
| [igniteui-wc-choose-components](./igniteui-wc-choose-components/SKILL.md) | Identify the right components for a UI pattern and navigate to official docs/demos | Deciding which components to use |
| [igniteui-wc-integrate-with-framework](./igniteui-wc-integrate-with-framework/SKILL.md) | Integrate components into React, Angular, Vue, or vanilla JS applications | Setting up components in your project |
| [igniteui-wc-customize-component-theme](./igniteui-wc-customize-component-theme/SKILL.md) | Customize styling using CSS custom properties, parts, and theming system | Applying custom brand colors/styles |
| [igniteui-wc-generate-from-image-design](./igniteui-wc-generate-from-image-design/SKILL.md) | Implement a view from a screenshot or mockup using Ignite UI Web Components | Converting a design image into UI |
| [igniteui-wc-optimize-bundle-size](./igniteui-wc-optimize-bundle-size/SKILL.md) | Reduce bundle size by importing only needed components and lazy loading | Optimizing production performance |

## How to Use

When working with an AI agent like GitHub Copilot, reference skills by name or ask questions naturally:

### Natural Questions
- "How do I integrate igniteui-webcomponents with React?"
- "Help me customize the button colors to match my brand"
- "Build this screenshot with Ignite UI Web Components"
- "My bundle size is too large, how can I reduce it?"
- "Show me how to use these components in Vue"

### Direct Skill Reference
- "Follow the integrate-with-framework skill for my Angular app"
- "Use the customize-component-theme skill to help me style components"
- "Use the generate-from-image-design skill to implement this mockup"
- "Apply the optimize-bundle-size skill to reduce my bundle"

## Skill Structure

Each skill contains:

- **Example Usage**: Common questions or scenarios
- **When to Use**: Situations where the skill applies
- **Related Skills**: Other relevant skills to explore
- **Step-by-Step Instructions**: Detailed guidance with code examples
- **Framework-Specific Examples**: React, Angular, Vue, and vanilla JS patterns
- **Common Issues & Solutions**: Troubleshooting guidance
- **Best Practices**: Recommended approaches
- **Additional Resources**: Further reading and documentation

## Contributing

If you identify gaps in the skills or have suggestions for improvements:

1. [Open an issue](https://github.com/IgniteUI/igniteui-webcomponents/issues) describing the improvement
2. Submit a pull request with the proposed changes
3. Follow the skill format and structure of existing skills

For skills related to **contributing to the library itself** (creating components, reviewing PRs, etc.), see [`.github/skills/`](../.github/skills/).

## Additional Resources

- [Component Documentation](https://igniteui.github.io/igniteui-webcomponents)
- [Project README](../README.md)
- [Code Examples & Storybook](https://igniteui.github.io/igniteui-webcomponents)
- [GitHub Repository](https://github.com/IgniteUI/igniteui-webcomponents)

## License

These skills are provided under the same license as the Ignite UI Web Components library. See [LICENSE](../LICENSE) for details.
431 changes: 431 additions & 0 deletions .claude/skills/igniteui-wc-choose-components/SKILL.md

Large diffs are not rendered by default.

Original file line number Diff line number Diff line change
@@ -0,0 +1,82 @@
# Setting Up the Ignite UI CLI MCP Server

> **Part of the [`igniteui-wc-choose-components`](../SKILL.md) skill hub.**

## Contents

- [Setting Up the Ignite UI CLI MCP Server](#setting-up-the-ignite-ui-cli-mcp-server)
- [Contents](#contents)
- [VS Code](#vs-code)
- [Cursor](#cursor)
- [Claude Desktop](#claude-desktop)
- [WebStorm / JetBrains IDEs](#webstorm--jetbrains-ides)
- [Verifying the Setup](#verifying-the-setup)

The Ignite UI CLI MCP server enables AI assistants to discover Ignite UI components, access component documentation, and support related Ignite UI workflows. It must be configured in your editor before these tools become available.

## VS Code

Create or edit `.vscode/mcp.json` in your project:

```json
{
"servers": {
"igniteui-cli": {
"command": "npx",
"args": ["-y", "igniteui-cli", "mcp"]
}
}
}
```

This works whether `igniteui-cli` is installed locally in `node_modules` or needs to be pulled from the npm registry — `npx -y` handles both cases.

## Cursor

Create or edit `.cursor/mcp.json`:

```json
{
"mcpServers": {
"igniteui-cli": {
"command": "npx",
"args": ["-y", "igniteui-cli", "mcp"]
}
}
}
```

## Claude Desktop

Edit the Claude Desktop config file:

- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`

```json
{
"mcpServers": {
"igniteui-cli": {
"command": "npx",
"args": ["-y", "igniteui-cli", "mcp"]
}
}
}
```

## WebStorm / JetBrains IDEs

1. Go to **Settings → Tools → AI Assistant → MCP Servers**
2. Click **+ Add MCP Server**
3. Set Command to `npx` and Arguments to `-y igniteui-cli mcp`
4. Click OK and restart the AI Assistant

> The `-y` flag skips interactive prompts if `igniteui-cli` is not already installed locally.

## Verifying the Setup

After configuring the MCP server, ask your AI assistant:

> "List all available Ignite UI components"

If the MCP server is running, the `list_components` tool will return all available components for the detected framework.
Loading
Loading