Skill UI

A comprehensive framework for rigorously testing and benchmarking LLM agents. It moves beyond simple pass/fail checks to assess complex behaviors, reliability metrics, and capability consistency across multiple runs. Ideal for production monitoring and identifying subtle failure modes in advanced AI agents.

This advanced skill analyzes an existing codebase to identify architectural patterns, dependencies, and technical stacks. It recommends tailored Claude Code automations—including Hooks, Subagents, Skills, Plugins, and MCP Servers—to optimize development workflows, improve code consistency, and enhance overall project scalability. Use this when setting up a new project or looking to refine existing Claude Code configurations.

Guides creation of Cursor-specific subagents with isolated contexts, structured prompts, and frontmatter so multi-step workflows, verifiers, or specialists follow Cursor’s directories and delegation rules.

Daily News Report orchestrates agents to scrape a curated URL list, filter high-quality technical findings, and compile them into daily Markdown summaries while monitoring batch progress and leveraging smart caching for reliability.

Guides Claude Code skill authors through designing and structuring workflow-based skills with numbered phases, decision routing, subagent delegation, and progressive disclosure so multi-step automations remain predictable and auditable.

HR-Pro is a comprehensive, ethical, and compliance-aware subagent designed to guide users through the entire employee lifecycle. It provides best practices, standardized checklists, and templates for key HR processes, including hiring and recruiting, onboarding/offboarding, performance management, PTO/leave policy, and complex employee relations. It prioritizes legal compliance and minimizing bias, while always advising consultation with local legal counsel for high-risk actions.

Guides multi-agent workflows through an iterative context retrieval loop—dispatching broad queries, evaluating relevance, refining criteria, and looping up to three times so sub-agents gather exactly the files they need without overwhelming limits.

This guide details advanced architectural patterns for building complex AI systems using multiple Language Model instances (agents). It addresses the single-agent context bottleneck by distributing work, enabling parallelism, and facilitating specialization across different subtasks. Key patterns include Supervisor/Orchestrator, Peer-to-Peer/Swarm, and Hierarchical designs, providing guidelines for context isolation and effective coordination protocols.

Monitors Nx Cloud CI pipelines by running the ci-watcher subagent, polling execution status, and applying self-healing fixes or rerun requests while honoring user overrides and Nx Cloud connection requirements.

Orchestrates multiple agents for complex workflows, decomposing feature, review, refactor, test, or documentation requests into parallel subtasks tracked via cc-mirror and TodoWrite for live visibility.

Guides orchestrating multiple Task tool subagents with run_in_background for concurrent work, covering when to trigger parallelism, how to craft prompts, launch in one message, synchronize results, and integrate TodoWrite status updates.

This workflow guides developers through the systematic process of requesting and acting upon code reviews. It emphasizes the core principle of reviewing early and often, providing structured inputs (commits, requirements, implemented features) via a subagent to catch technical issues, ensure compliance with requirements, and maintain high code quality before merging.