Skill UI

This guide provides a comprehensive reference on Agent Skills, a standardized and powerful method for providing structured context, workflows, and tools to Large Language Models (LLMs). It details the anatomy of the SKILL.md file, the three-stage progressive disclosure loading process, and best practices for creating both capability (tool-based) and process (workflow-based) primitives. Use this resource when designing, reviewing, or debugging agent-driven applications to ensure reliable and context-efficient performance.

This skill executes the DeepSWE benchmark, a comprehensive coding-agent evaluation suite. It uses OpenRouter and mini-swe-agent to score various Large Language Models (LLMs) on 113 tasks, providing reproducible results for model comparison, development assessment, and research benchmarking. Use this when a standardized, deep evaluation of LLM coding capabilities is required.

Generates a precise, evidence-based installation plan for a project's component catalog (ECC). Instead of loading a full, noisy bundle, this skill analyzes the repository's actual code structure, dependencies, and CI/CD evidence to classify skills, rules, and commands into 'DAILY' (essential) and 'LIBRARY' (referenceable) buckets. It ensures only necessary components are active, optimizing the development environment.

This comprehensive guide outlines a rigorous, human-in-the-loop engineering workflow for leveraging advanced AI agents to complete complex implementation tasks. It mandates defining clear completion criteria, decomposing work into manageable units, and strategically routing models (Haiku, Sonnet, Opus) based on task complexity. The workflow emphasizes continuous evaluation, regression testing, security review of invariants and edge cases, and strict cost discipline to ensure robust and reliable software development using AI assistance.

This model provides an engineering operational framework for teams that leverage AI agents to generate large volumes of code. It shifts the focus from simple syntax to process quality, robust architecture design, rigorous testing, and systematic risk control, ensuring the development of highly stable and reliable systems in AI-assisted environments.

A comprehensive strategy for regression testing in AI-assisted development. It focuses on identifying systematic blind spots, such as schema inconsistencies between sandbox and production paths, and integrating automated bug checks into the development workflow. This guide teaches how to build robust, database-free API tests to ensure code quality when AI models contribute to the codebase.

A specialized tool for generating long-form content, including guides, blogs, and tutorials, that maintains a unique, human-like brand voice. It ensures structural integrity and factual accuracy, preventing the generic, boilerplate feel often associated with raw LLM output. Ideal for content teams needing sophisticated, reliable narrative development.

A comprehensive guide covering patterns and architectures for automating code execution using LLMs. It spans simple sequential pipelines (e.g., daily dev scripts) to advanced, RFC-driven multi-agent Directed Acyclic Graph (DAG) orchestration. Ideal for building CI/CD style continuous development pipelines, managing complex state, and automating quality gates without human intervention.

A comprehensive tool for establishing performance baselines across multiple dimensions. It measures Core Web Vitals (LCP, CLS, INP), API latency (p50, p95, p99), and development build efficiency. Essential for detecting performance regressions before merging code, ensuring stability in CI/CD pipelines, and comparing alternative stack implementations.

This tool serves as a persistent memory and state manager for complex coding projects within the Claude environment. It allows users to initialize new projects with structured metadata, track detailed session progress (including summaries, decisions, and next steps), and save the entire context reliably. By ensuring project continuity across disconnected sessions, it drastically improves the flow and consistency of the development workflow.

A robust framework for orchestrating complex, multi-step coding tasks using multiple AI agents. It functions by first planning the entire project into a mission dependency graph (DAG), then dispatching specialized agents to isolated Git worktrees for parallel development. The system automatically monitors progress, handles merges, and generates structured, comprehensive reports detailing changes, completed tasks, and next steps.

This comprehensive guide establishes foundational coding standards and best practices for enhancing code quality, readability, and maintainability across all projects. It covers naming conventions, immutability patterns, error handling, and core design principles like KISS, DRY, and YAGNI, applicable to TypeScript, JavaScript, and React development. Use it when starting a new module or performing code reviews.