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.

This skill implements an autonomous, multi-round review loop for refining complex research or codebases. It iteratively reviews content using specified external backends (e.g., Codex, manual review), implements necessary fixes based on feedback, and re-reviews until the positive assessment criteria are met or the maximum round limit is reached. It manages state persistence and allows for configurable difficulty levels, making it ideal for projects requiring rigorous, self-correcting quality assurance.

Get a deep, multi-round, and adversarial critical review of your research work, ideas, or drafts. This skill simulates the perspective of a senior ML reviewer (e.g., NeurIPS/ICML level) using dedicated external backends (Codex or Manual). It is designed to find logical gaps, missing experiments, and narrative weaknesses, providing brutal honesty to elevate your academic contribution.

This tool audits the integrity of machine learning experiments by checking for common fraud patterns such as fake ground truth, score normalization fraud, and phantom results. It utilizes an external reviewer backend (like Codex or manual review) to perform an adversarial review across all project artifacts, ensuring reported results are trustworthy and methodologically sound.

This command runs a high-stakes business memo through multiple advanced AI models (Claude, Codex, Gemini) to achieve a robust consensus review. It identifies areas of agreement, divergence, and critical concerns, providing an independent sanity check before irreversible corporate decisions like M&A, fundraises, or major pivots. It includes graceful degradation for API availability.

A generic entry point for delegating self-contained, multi-step tasks to specialized LLM agents (Codex, Claude Code, Pi). Utilizes background processing tools to manage the full lifecycle of AI-driven sub-tasks, such as policy review, complex report synthesis, document generation, or large-scale code refactoring. Ideal for meta-skill workflows requiring full agent agency.

This skill structures a highly controlled, bounded development life cycle for AI agents. It mandates a structured three-phase workflow: Planning (Spec), Implementation (Build), and Verification (Review). It is essential for building complex features from scratch, especially when dealing with ambiguous requirements, high risk, or needing explicit human approval gates to ensure the resulting code meets all defined specifications.

A powerful plugin enabling Claude Code to delegate complex tasks to external AI CLIs (such as OpenAI Codex or Google Antigravity/Gemini) without exiting the conversation. It supports multi-model workflows, allowing users to seek a second opinion, cross-check deep analysis, or delegate side tasks (like research or code review). The core value is that Claude synthesizes the raw outputs, providing a critical review and reconciliation of findings across all consulted models.

This comprehensive guide provides authors with best practices for preparing supplementary artifacts for AAAI submissions. It outlines how to structure technical appendices, package reproducible code and data ZIPs, maintain strict anonymity (by removing author metadata and paths), and maximize the evidence for reproducibility. The goal is to ensure that external reviewers can easily verify the research claims without specialized or private tools.

This guide provides comprehensive instructions for packaging multiagent system (MARL) and game theory evidence for academic submissions, particularly for conferences like AAMAS. It emphasizes that the artifact must be inspectable, containing not just a trained model, but the game definition, environment code, opponent sets, and interaction protocols, ensuring rigorous reproducibility and reviewability.

A guide for researchers submitting to conferences like ACM Multimedia, detailing how to achieve robust result reproducibility. It covers the necessary steps—including logging code commits, data versions, media preprocessing parameters, and hardware details—to allow independent reviewers to successfully rebuild the reported findings and achieve official reproducibility badges.

A comprehensive guide for authors on best practices for packaging, documenting, and ensuring the reproducibility of LLM artifacts (weights, data, code, prompts, etc.). It addresses requirements for anonymous academic review and public post-acceptance release, focusing on reproducibility, licensing, and transparency.