Skill UI

This skill acts as a high-level orchestrator for complex, multi-stage software development tasks. It manages workflows requiring broad codebase exploration, multi-file implementation, test execution, or deep debugging. By enforcing delegation via `delegate_task`, it ensures that workers operate in fresh, self-contained, ephemeral contexts, which prevents context overload and maintains structured, verifiable development processes.

This document defines the critical architectural contract for standardizing advisory transport across diverse AI code review runtimes (e.g., Claude Code, OpenCode, Codex). It mandates that all integrations adhere to a shared Go contract, governing how review results, evidence, and validation are processed. This is essential for ensuring system integrity, managing architectural transitions, and preventing the creation of isolated, proprietary review systems.

This specialized sub-agent is responsible for transforming high-level feature proposals and technical specifications into a formal, comprehensive 'design.md' document. It systematically captures all necessary technical details, including architectural decisions, data flow diagrams, detailed file changes, API contracts, and thorough testing strategies. Use this skill during the planning phase of any complex software change to ensure technical completeness and feasibility.

This agent is dedicated to systematically exploring technical ideas, such as new features, refactoring, or bug fixes, *before* committing to code changes. It investigates the existing codebase, analyzes current architecture, compares multiple potential approaches (including pros, cons, and effort), and generates a structured 'exploration' report with a clear recommendation and identified risks. It ensures thorough planning and risk mitigation during the design phase.

This advanced skill initializes the Software Development Documentation (SDD) context within a project. It detects the entire technical stack, conventions, testing tools, and persistence mode across all discovered projects. It then structures and persists this comprehensive context, including building a skill registry and determining the strict TDD status, ensuring a robust starting point for development.

This sophisticated sub-agent takes comprehensive Software Design Documents (SDD), proposals, and specifications to generate a detailed, actionable task breakdown in the format of a tasks.md file. It structures the work into distinct phases (e.g., Foundation, Core Implementation, Testing, Cleanup), providing concrete, verifiable, and small units of work suitable for immediate engineering execution and managing complex feature delivery chains.

A rigorous framework for triaging software defects, managing technical debt, and designing systemic fixes. This methodology mandates classifying issues by root class and implementing clustered, minimized solutions, rather than applying superficial patches. It guides developers to prevent over-engineering and ensure that system improvements are durable, verifiable, and maintainable.

This skill enables applying John Ousterhout's design principles to reduce complexity in software systems. It guides decisions on module boundaries, API design, information hiding, and abstraction depth. Use it when refactoring shallow interfaces or managing cognitive load during development. Ideal for architects and senior engineers optimizing system structure and ensuring maintainable codebases through proper abstraction layers.

Apply Robert C. Martin-inspired rules to separate business policy from frameworks, databases, UI, and infrastructure. This skill helps define architectural boundaries, dependency direction, use cases, and interface adapters. Use it for software design decisions involving framework isolation or technology churn to ensure maintainability and clarity.

Apply Robert C. Martin-inspired clean code rules to improve code readability, naming conventions, function design, and responsibilities. This skill ensures everyday implementation quality, readable control flow, and testable code by following established best practices for software development.

This skill applies Steve McConnell's construction rules to software development tasks. It covers routine design, variable usage, class design, control flow, defensive programming, coding standards, and testing. Use it for disciplined software construction to ensure high-quality code implementation.

This skill enforces strict communication protocols for AI agents interacting in shared channels with external parties. It ensures agents speak only when explicitly addressed, prevents internal context leakage, and routes sensitive content to draft-only approval. Ideal for group chats, DMs, and business partnerships where privacy and security are critical.