Gemini CLI for Large Codebase Analysis

Use the Gemini CLI with its massive context window to analyze large codebases or multiple files that exceed typical context limits. Leverage `gemini -p` to tap into Google Gemini's large context capacity.

When to Use This Skill

Use `gemini -p` when:

File and Directory Inclusion Syntax

Use the `@` syntax to include files and directories in your Gemini prompts. Paths should be relative to your current working directory when invoking the `gemini` command.

Single File Analysis

```bash

gemini -p "@src/main.py Explain this file's purpose and structure"

```

Multiple Files

```bash

gemini -p "@package.json @src/index.js Analyze the dependencies used in the code"

```

Entire Directory

```bash

gemini -p "@src/ Summarize the architecture of this codebase"

```

Multiple Directories

```bash

gemini -p "@src/ @tests/ Analyze test coverage for the source code"

```

Current Directory and All Subdirectories

```bash

gemini -p "@./ Give me an overview of this entire project"

```

Alternative: All Files Flag

```bash

gemini --all_files -p "Analyze the project structure and dependencies"

```

Implementation Verification Examples

Check if a Feature is Implemented

```bash

gemini -p "@src/ @lib/ Has dark mode been implemented in this codebase? Show me the relevant files and functions"

```

Verify Authentication Implementation

```bash

gemini -p "@src/ @middleware/ Is JWT authentication implemented? List all auth-related endpoints and middleware"

```

Check for Specific Patterns

```bash

gemini -p "@src/ Are there any React hooks that handle WebSocket connections? List them with file paths"

```

Verify Error Handling

```bash

gemini -p "@src/ @api/ Is proper error handling implemented for all API endpoints? Show examples of try-catch blocks"

```

Check for Rate Limiting

```bash

gemini -p "@backend/ @middleware/ Is rate limiting implemented for the API? Show the implementation details"

```

Verify Caching Strategy

```bash

gemini -p "@src/ @lib/ @services/ Is Redis caching implemented? List all cache-related functions and their usage"

```

Check for Security Measures

```bash

gemini -p "@src/ @api/ Are SQL injection protections implemented? Show how user inputs are sanitized"

```

Verify Test Coverage

```bash

gemini -p "@src/payment/ @tests/ Is the payment processing module fully tested? List all test cases"

```

Instructions for AI Agent

1. When a user requests codebase analysis that involves multiple directories or large file sets, recommend using the Gemini CLI

2. Construct `gemini -p` commands using the `@` syntax to include relevant files and directories

3. Use the Bash tool to execute the gemini command (no `--yolo` flag needed for read-only analysis)

4. For implementation verification queries, craft specific questions that ask Gemini to locate and describe relevant code patterns

5. If the user's working directory is unclear, ask them to confirm the project root before constructing file paths

6. When results are returned, summarize key findings for the user

Important Notes

Example Workflow

1. User asks: "Is authentication implemented in this project?"

2. Agent responds: "I'll use Gemini CLI to analyze your codebase for authentication patterns."

3. Agent runs: `gemini -p "@src/ @middleware/ @api/ Is authentication implemented? List all auth-related files, middleware, and endpoints with their authentication methods"`

4. Agent summarizes Gemini's findings, providing file paths and relevant code snippets