Skill UI

A sophisticated AI system that coordinates multiple specialized agents (e.g., Security Auditors, Performance Analysts, Architecture Specialists) to perform comprehensive, multi-perspective code assessments. It analyzes code context, manages state, and synthesizes conflicting insights to provide deep, holistic reviews for complex software projects.

Guides engineering teams working with AI-assisted code generation to prioritize planning, measurable coverage, resilient architectures, and behavior-focused reviews for safe, reliable delivery.

Analyzes Claude Code auto-memory, promotes stable learnings to CLAUDE.md/.claude/rules, extracts reusable skills, monitors MEMORY.md health, and provides review/promotion/extraction commands to keep project knowledge curated and actionable.

Coordinate multiple AI agents concurrently via dmux’s tmux pane manager, running Claude Code, Codex, OpenCode and other tools in parallel tracks for research, implementation, testing, review, or multi-role coding tasks.

This skill automates the multi-round research review process. It iteratively reviews provided work using advanced AI models (Codex MCP), identifying critical weaknesses, implementing fixes, and re-reviewing until the content achieves a positive assessment or the maximum round limit is reached. Ideal for refining complex academic papers, technical designs, or large codebases that require rigorous, iterative quality assurance.

This autonomous skill orchestrates the entire scientific research lifecycle, guiding users from a vague research direction to a polished, review-ready document. The pipeline systematically executes Idea Discovery (Workflow 1), full-scale Implementation, Experiment Deployment (Workflow 2), automated Review Loops, and optional Paper Writing (Workflow 3). It handles everything from preliminary literature review and novelty checks to generating high-quality, reproducible code and final academic drafts.

This skill acts as a crucial bridge, automating the transition from a conceptual experiment plan to fully deployed and executable code. It parses structured experiment roadmaps, implements necessary training/evaluation scripts, manages dependencies, and deploys the experiment setup to GPU environments. It ensures reproducibility through mandatory code review and structured result collection.