1. Software Development

Defines standardized rules and patterns for writing test code to ensure consistency and quality in software testing practices.

Orchestrates end-to-end development of a production REST API using Test-Driven Development across planning, architecture, implementation, testing, and deployment phases.

Automates code style and quality audits, applying linting and refactoring to ensure maintainable, readable, and production-ready code without breaking functionality.

Coordinates multi-faceted code reviews across quality, security, performance, and documentation within a 4-hour timeline.

Automates end-to-end feature development from research to deployment with AI-assisted architecture, prototyping, and testing.

Automates comprehensive code review with specialized agents for security, performance, style, tests, and documentation, providing feedback and auto-fix suggestions.

Validates code functionality through sandbox testing, execution verification, and systematic debugging to ensure genuine operation after code generation or modification.

Automates code style and convention audits with automatic fixes to enforce consistent coding standards across projects.

Creates ergonomic slash commands with auto-discovery and parameter validation for efficient micro-skill access in applications.

Provides comprehensive performance profiling, bottleneck detection, and optimization strategies for software applications.

Generates structured templates for Claude Code Skills with proper YAML frontmatter and organized directory structure to streamline development.

Runs parallel code quality checks including linting, security scanning, and basic tests for immediate development feedback.

Provides a structured 2-week REST API development workflow using TDD, covering backend, database, testing, and documentation.

Provides comprehensive software quality verification through static analysis, dynamic testing, integration validation, and certification gates.

Automates comprehensive GitHub PR code reviews with specialized agents for security, performance, style, tests, and documentation.

Validates code functionality through sandbox testing, execution verification, and systematic debugging to ensure reliable behavior after code generation or modification.

Automates bug resolution through AI-driven root cause analysis, code generation, and validation to fix software defects efficiently.

Coordinates multiple repositories using AI agents to maintain architectural consistency, manage dependencies, and synchronize releases across microservices and multi-package ecosystems.

Comprehensive code review with specialized agents for security, performance, style, tests, and documentation in pull requests.

Enables AST-based code search, linting, and structural refactoring across 20+ languages with pattern matching and rule configuration.

System for creating and refining Claude Code skills using systematic engineering and evidence-based prompting to ensure high-quality, well-structured skill development.

Detects non-functional 'theater' code that passes static analysis but fails at runtime, preventing flawed implementations from reaching production.

Collaborative framework for secure, maintainable production code development across all software engineering tasks.

Detects code quality issues like long functions, deep nesting, and duplicated code to guide refactoring and improve maintainability.