1. Software Development

Provides streamlined workflows for developing, testing, and maintaining plugins within the Claude Code ecosystem.

Provides comprehensive pull request reviews using specialized agents, covering code quality aspects and delivering improvement action plans.

Analyzes existing codebases to map structure, create documentation, and understand brownfield projects using parallel agent mapping.

Systematically troubleshoots and resolves software bugs, errors, and persistent issues in code.

Enables conversational validation of implemented features via user acceptance testing (UAT) and functional verification.

Enables local execution and testing of agents, including API validation via curl, server configuration, and troubleshooting development issues.

Enforces technical verification before implementing code review suggestions to prevent unverified changes and ensure meaningful outcomes.

Implements Test-Driven Development (TDD) cycle: write failing tests first, minimal implementation to pass, then refactor for clean code.

Defines component interfaces and data contracts for API design before protocol selection, ensuring clear specifications for large-scale projects.

Prevents common testing anti-patterns including improper mocking, test pollution, and dependency misunderstandings to ensure robust test suites.

Offers a four-phase debugging framework (root cause investigation, pattern analysis, hypothesis testing, implementation) to ensure thorough understanding before applying fixes.

Creates 2-5 minute atomic development subtasks with complete code, exact commands, and TDD pattern for large-scale projects.

Replaces arbitrary timeouts in tests with condition polling to wait for actual state changes, reducing flakiness and improving test reliability.

On-demand specialist agents for backend (Go/TypeScript), frontend, DevOps, design, QA, and SRE to deliver deep technology expertise.

Systematically traces bugs backward through call stacks to identify the original error trigger, with optional instrumentation for deeper analysis.

Enforces multi-layer data validation across all application layers to prevent structural bugs by ensuring integrity at every processing stage.

Automates codebase linting and fixes by parallelizing issue resolution through AI agents, ensuring a clean codebase without manual intervention.

Systematically interviews users to uncover ambiguities, preferences, and constraints prior to software development.

Structured skill development methodology using red-green-refactor cycle: test without skill (RED), implement (GREEN), and refactor to close gaps.

Enforces 85%+ unit test coverage for all acceptance criteria using TDD methodology in the development cycle.

Enables concurrent execution of multiple AI agents to independently investigate and resolve issues simultaneously, improving efficiency in problem-solving workflows.

Dispatches five specialized reviewers (code, business-logic, security, test, nil-safety) in parallel for comprehensive code review.

Autonomously explores codebases by identifying structural elements and conducting deep dives to provide actionable insights for developers.

Enforces mandatory validation of technology choices against Ring Standards and PROJECT_RULES.md for versioned, justified selections in Large Track projects.