### Build and Start Project

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/advanced-usage/available-tools/execute-command.md

Executes build and start commands in sequence for a project.

```xml
<execute_command>
<command>npm run build && npm start</command>
</execute_command>
```

--------------------------------

### Install LiteLLM with Proxy Support

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/providers/litellm.md

Install LiteLLM with the necessary dependencies for proxy support. This command ensures you have the 'proxy' extra installed.

```bash
pip install 'litellm[proxy]'
```

--------------------------------

### Codebase Search: Feature-Focused Query

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/advanced-usage/available-tools/codebase-search.md

Focus your queries on specific features or functionalities. This example searches for 'database connection pool setup'.

```xml
<codebase_search>
<query>database connection pool setup</query>
</codebase_search>
```

--------------------------------

### Start Local Development Server

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/README.md

Starts a local development server for live preview. Changes are reflected without server restart.

```bash
$ pnpm start
```

--------------------------------

### Start LiteLLM Proxy Server

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/providers/litellm.md

Start the LiteLLM proxy server using a configuration file or a single model for quick start. The server defaults to running at http://0.0.0.0:4000.

```bash
# Using configuration file (recommended)
litellm --config config.yaml

# Or quick start with a single model
export ANTHROPIC_API_KEY=your-anthropic-key
litellm --model anthropic/claude-model-id
```

--------------------------------

### STDIO Transport Configuration Example

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/mcp/using-mcp-in-roo.mdx

A configuration example for a local server using the STDIO transport, including optional fields like cwd and env.

```json
{
  "mcpServers": {
    "local-server": {
      "command": "node",
      "args": ["server.js"],
      "cwd": "/path/to/project/root", // Optional: Specify working directory
      "env": {
        "API_KEY": "your_api_key"
      },
      "alwaysAllow": ["tool1", "tool2"],
      "disabled": false
    }
  }
}
```

--------------------------------

### Install Nightly VSIX Builds with pnpm

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/update-notes/v3.43.0.mdx

Use this command to simplify the installation of nightly VSIX builds for Zoo Code.

```bash
pnpm install:vsix:nightly
```

--------------------------------

### SSE (Legacy) configuration example

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/mcp/using-mcp-in-roo.mdx

Example configuration for a remote MCP server using the legacy sse transport type.

```json
{
  "mcpServers": {
    "legacy-remote-server": {
      "type": "sse", // Explicitly define as SSE
      "url": "https://your-legacy-server-url.com/mcp-base", // Base URL
      "headers": {
        "Authorization": "Bearer your-legacy-token"
      },
      "alwaysAllow": ["oldToolX"],
      "disabled": false
    }
  }
}
```

--------------------------------

### Get System Status with No Arguments

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/advanced-usage/available-tools/use-mcp-tool.md

This example shows how to call a tool that requires no specific arguments. It retrieves the current system status from the system-monitor server.

```xml
<use_mcp_tool>
<server_name>system-monitor</server_name>
<tool_name>get_current_status</tool_name>
<arguments>
{}
</arguments>
</use_mcp_tool>
```

--------------------------------

### Create HTML File

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/advanced-usage/available-tools/write-to-file.md

This example shows how to create a basic HTML file. Ensure the path and content are correctly defined.

```xml
<write_to_file>
<path>src/index.html</path>
<content>
<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>My Application</title>
  <link rel="stylesheet" href="styles.css">
</head>
<body>
  <div id="app"></div>
  <script src="app.js"></script>
</body>
</html>
</content>
<line_count>13</line_count>
</write_to_file>
```

--------------------------------

### Codebase Search: Scoping to Test Files

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/advanced-usage/available-tools/codebase-search.md

To search only within test files, specify the 'tests' directory using the `path` parameter. This example searches for 'mock data setup patterns' in test files.

```xml
<codebase_search>
<query>mock data setup patterns</query>
<path>tests</path>
</codebase_search>
```

--------------------------------

### Download Qwen2.5-coder Model

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/providers/ollama.md

Example of downloading the `qwen2.5-coder:32b` model from Ollama.

```bash
ollama pull qwen2.5-coder:32b
```

--------------------------------

### Example Prompt Template for Code Explanation

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/code-actions.mdx

This template demonstrates how to structure a prompt for explaining code, utilizing placeholders for file path and selected text.

```plaintext
Please explain the following code from ${filePath}:

${selectedText}
```

--------------------------------

### Install Git on macOS with Xcode Command Line Tools

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/checkpoints.mdx

Install Git on macOS by installing the Xcode Command Line Tools. This is an alternative method if Homebrew is not used.

```bash
xcode-select --install
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/advanced-usage/available-tools/execute-command.md

Installs specified npm packages for a project.

```xml
<execute_command>
<command>npm install express mongodb mongoose dotenv</command>
</execute_command>
```

--------------------------------

### Execute Built-in Initialization Command

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/advanced-usage/available-tools/run-slash-command.md

Use this snippet to run the built-in `init` command for project initialization. It requires no additional arguments.

```xml
<run_slash_command>
<command>init</command>
</run_slash_command>
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/README.md

Installs project dependencies using pnpm.

```bash
$ pnpm install
```

--------------------------------

### Serve Ollama Models

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/providers/ollama.md

Start the Ollama server to make models available. Ensure this command is running in your terminal.

```bash
ollama serve
```

--------------------------------

### Create Skill Directory and File

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/skills.mdx

Demonstrates the bash commands to create a new directory for a skill (e.g., 'pdf-processing') and its corresponding SKILL.md file within the global skill path.

```bash
# Example: PDF processing skill
mkdir -p ~/.roo/skills/pdf-processing
touch ~/.roo/skills/pdf-processing/SKILL.md
```

--------------------------------

### SKILL.md Frontmatter and Instructions

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/skills.mdx

Provides a template for the SKILL.md file, including required frontmatter (`name`, `description`) and example instructions for handling PDF processing. It outlines steps for checking dependencies, choosing libraries, and managing potential issues.

```markdown
---
name: pdf-processing
description: Extract text and tables from PDF files using Python libraries
---

# PDF Processing Instructions

When the user requests PDF processing:

1. Check if PyPDF2 or pdfplumber is installed
2. For text extraction, use pdfplumber for better table detection
3. For simple text-only PDFs, PyPDF2 is sufficient
4. Always handle encoding errors gracefully
5. Offer to save extracted content to a file

## Code Template

[Your detailed code patterns here]

## Common Issues

- Encrypted PDFs: Explain they require password parameter
- Scanned PDFs: Recommend OCR tools like pytesseract
- Large files: Suggest page-by-page processing
```

--------------------------------

### Name property examples

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/custom-modes.mdx

Examples of the name property in YAML and JSON formats.

```yaml
name: 📝 Documentation Writer
```

```json
"name": "Documentation Writer"
```

--------------------------------

### Example System Prompt Context

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/settings-management.md

Illustrates the content of a system prompt when 'Include Current Time' and 'Include Current Cost' settings are enabled.

```text
# Current Time
Current time in ISO 8601 UTC format: 2025-10-28T23:06:08.458Z
User time zone: America/Edmonton, UTC-6:00

# Current Cost
$0.14
```

--------------------------------

### Slug property examples

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/custom-modes.mdx

Examples of the slug property in YAML and JSON formats.

```yaml
slug: docs-writer
```

```json
"slug": "docs-writer"
```

--------------------------------

### Verify Git Installation on macOS/Linux

Source: https://github.com/zoo-code-org/zoo-code-docs/blob/main/docs/features/checkpoints.mdx

Verify that Git has been successfully installed by checking its version in the terminal.

```bash
git --version
```