probe

🥇Gold

Probe is a cutting-edge semantic code search engine designed for large codebases, enabling AI-driven coding tools to enhance productivity. Its local architecture ensures fast and efficient code retrieval, making it an essential resource for developers.

523370Updated 1w ago

Intermediate15 minutes to implementdevelopment

Saves ~240 min per use

Quick InstallView Source

claude install probelabs/probe

Works with:

VS CodeGitHub Copilot

Overview

About This Skill

https://github.com/probelabs/probe

How to Use

["1. **Install Probe**: Integrate Probe into your development environment by following the installation guide on the official website.","2. **Index Your Codebase**: Run the Probe indexer on your project directory to build a searchable database of your code.","3. **Formulate Queries**: Use natural language to ask specific questions about your code, such as 'Find all instances of SQL injection vulnerabilities'.","4. **Review Results**: Probe will return relevant code snippets, patterns, and potential issues. Review these carefully to understand the context.","5. **Implement Changes**: Use the insights gained to refactor, optimize, or secure your code. Regularly probe your codebase to maintain its health."]

Use Cases

Quickly locate specific functions or classes in extensive codebases to save time during development.

Enhance AI coding assistants by providing them with precise code retrieval capabilities for better context understanding.

Streamline code reviews by efficiently finding relevant code snippets and ensuring quality control.

Support onboarding of new developers by enabling them to easily search and understand existing code structures.

Best For

GrowthCS

Setup & Installation

Quick Install

Terminal

claude install probelabs/probe

Alternative Install (Git Clone)

git clone https://github.com/probelabs/probe

Requirements

Claude Code or compatible AI agent
Works with: VS Code, GitHub Copilot

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use Probe to search for all instances of [FUNCTION_NAME] in the [PROJECT_NAME] codebase. Identify patterns in how this function is called and suggest optimizations. Highlight any potential security vulnerabilities or performance bottlenecks. Provide code snippets for the top 3 recommendations.

Example Output

After analyzing the 'calculateDiscount' function in the 'EcommercePlatform' codebase, Probe identified several key patterns and issues:

1. **Inconsistent Parameter Handling**: The function is called with varying parameter orders, leading to potential bugs. Recommend standardizing the parameter order to (userId, productId, discountCode) across all calls.

2. **Security Vulnerability**: In the 'applyDiscount' module, the function is called without proper input validation. Recommend adding validation for discountCode format and userId existence.

3. **Performance Bottleneck**: The function is called synchronously in the 'checkout' module, causing delays. Recommend implementing an async version for non-critical paths.

Code Snippets:
- Standardized call: `calculateDiscount(userId, productId, discountCode)`
- Validated call: `if (validateInputs(userId, productId, discountCode)) { calculateDiscount(...)}`
- Async call: `calculateDiscountAsync(userId, productId, discountCode).then(handleResponse)`