code▌

Comprehensive code review for diffs with auto-detected domain-specific checks. \n \n Analyzes changed code for security vulnerabilities, anti-patterns, quality issues, and breaking changes across generic, frontend, and backend domains \n Auto-detects domain (frontend, backend, CLI, config) from file paths and applies relevant checklists \n Generates structured markdown reports with severity levels, file locations, code snippets, and actionable recommendations \n Performs impact analysis to ident

Technology-agnostic prompt generator for identifying and documenting high-quality code exemplars across multiple languages. \n \n Supports seven programming languages (.NET, Java, JavaScript, TypeScript, React, Angular, Python) with auto-detection capability \n Configurable analysis depth (Basic, Standard, Comprehensive), categorization method (Pattern Type, Architecture Layer, File Type), and documentation format \n Generates exemplars.md files with real file references, descriptions, and optio

Comprehensive guide to code generation techniques including template engines, AST manipulation, code scaffolding, and automated boilerplate generation for increased productivity and consistency.

AI-powered code review using CodeRabbit, triggered on explicit request or autonomously when quality/security issues are detected. \n \n Identifies bugs, security vulnerabilities, and quality risks; groups findings by severity (Critical, Warning, Info) \n Supports reviewing staged, committed, or all changes; can compare against specific branches or commit hashes \n Offers two output modes: --plain for detailed feedback with fix suggestions, or --prompt-only for minimal agent-optimized output \n E

Verifies code implements exactly what documentation specifies for blockchain audits. \n \n Performs deterministic, line-by-line semantic analysis of code against specification documents, whitepapers, or design docs to identify gaps and misalignments \n Extracts specification intent and code behavior into structured intermediate representations (Spec-IR, Code-IR, Alignment-IR) with full traceability and confidence scores \n Classifies divergences by severity (critical, high, medium, low) with evi

Analyzes code diffs and files to identify bugs, security vulnerabilities, performance issues, and architectural concerns with prioritized feedback. \n \n Detects common issues including SQL injection, XSS, N+1 queries, magic numbers, hardcoded secrets, and design pattern violations \n Follows a structured five-step workflow: context understanding, architecture review, code quality checks, test validation, and categorized reporting \n Produces prioritized reports organized by severity (critical,

Systematic code review practices for constructive feedback, bug detection, and team knowledge sharing. \n \n Covers the complete review workflow: context gathering, high-level architecture assessment, line-by-line analysis, and decision-making with clear severity labeling (blocking, important, nit, suggestion) \n Includes language-specific patterns for Python, TypeScript, and JavaScript, plus specialized review techniques for security, testing, and architectural changes \n Provides templates, ch

Skill by ara.so — Daily 2026 Skills collection.

Comprehensive code reviews covering quality, security, performance, and best practices. \n \n Systematic review process across five dimensions: code quality, security vulnerabilities, performance, testing, and maintainability \n Includes initial assessment, detailed analysis guides, and constructive feedback frameworks \n Covers pull request analysis, coding standards compliance, and developer mentoring through structured review \n Best practices emphasize respectful feedback with explanations a

Comprehensive code analysis covering security vulnerabilities, performance bottlenecks, maintainability issues, and best practice violations. \n \n Scans for critical security flaws including SQL injection, XSS, authentication gaps, unsafe deserialization, and credential exposure \n Identifies performance problems such as N+1 queries, inefficient algorithms, memory leaks, and unnecessary re-renders \n Evaluates code quality across duplication, function length, cyclomatic complexity, naming clari