Skill UI

This skill functions as a dedicated dependency security expert, specializing in auditing project dependencies. It analyzes codebases for known security vulnerabilities, license compliance issues, outdated packages, and overall supply chain risks. It provides comprehensive, actionable remediation strategies and detailed risk reports to keep software supply chains secure and compliant.

A methodical pathfinder that learns each codebase, storing findings in .notebook/ while guiding developers through bug fixes, feature work, and investigations without guessing.

A comprehensive troubleshooting guide for diagnosing and fixing common operational and configuration issues with the CodeRabbit PR review bot. Use this guide when reviews fail to post, scope is incorrect, comments are excessive, or configurations are ignored. It covers steps for checking GitHub permissions, YAML syntax, and advanced bot interaction commands.

This skill guides users on fine-tuning CodeRabbit's review quality. It teaches the AI agent team preferences through PR feedback, integrates custom code guidelines (e.g., security policies), allows customization of the review tone, and implements path filters to drastically reduce false positives and noise. This ensures that all code feedback is highly relevant, actionable, and aligns with specific team standards.

Collects comprehensive diagnostic evidence for troubleshooting CodeRabbit integration issues. This bundle checks the App installation status, validates the `.coderabbit.yaml` configuration, reviews recent PR history, and verifies GitHub webhook deliveries. Essential for preparing support tickets and diagnosing complex SaaS integration failures.

A comprehensive runbook for handling CodeRabbit service outages or malfunctions. It provides step-by-step procedures for quick triage, emergency bypasses (P1), checking installation health (P2), diagnosing delays (P3), and tuning incorrect review behavior (P4). Essential for maintaining continuous CI/CD workflows when the review bot fails.

This guide provides a comprehensive method for optimizing CodeRabbit's review process, focusing on improving speed, relevance, and the signal-to-noise ratio. Learn best practices for managing PR size, selecting the right review profile (e.g., 'assertive' vs. 'chill'), using path instructions to guide feedback, and filtering out low-value files. Ideal for teams looking to reduce review fatigue and ensure consistent code quality checks.

This comprehensive guide details how to implement robust webhook endpoints for CodeRabbit, an AI-powered code review tool. It covers essential security practices, including signature validation (HMAC-SHA256), and provides structured methods for handling various event types (e.g., PR reviews, check run completions, comments). Use this skill when integrating CodeRabbit into CI/CD pipelines to automate notifications, track metrics, and enforce quality gates.

Provides automated guidance for designing and implementing cron job schedulers in backend projects, covering best practices, production-ready code, and validation for node.js, Python, Go, databases, and microservices patterns.

This skill unlocks advanced multi-step code generation and architectural refactoring capabilities using autonomous agents. It supports parallel agent workflows, complex multi-file migrations, and multi-codebase orchestration by autonomously calling tools (Read, Write, Bash) in controlled, checkpointed cycles, drastically improving large-scale development efficiency.

A powerful AI tool designed for complex, coordinated programming tasks. It enables developers to generate, refactor, and scaffold entire features across multiple files (e.g., schema, API routes, service layers, tests) while maintaining consistency with existing codebase patterns. It supports agent mode for autonomous, multi-step changes and allows systematic migration and review of all affected files via detailed diffs.

This bundle provides a comprehensive framework for diagnosing and fixing common issues when AI code generation is incorrect within Cursor. It systematically covers the root causes of poor suggestions, including context mismanagement (missing, wrong, or overflowing context), model hallucinations, and ambiguous prompting. Use this guide to improve the accuracy and reliability of AI-assisted coding workflows.