Skill UI

The /hub:status command provides a comprehensive overview of an AgentHub session. It displays the current state of agent branches, commit counts, frontier status, and recent board updates. This is useful for monitoring ongoing collaborative AI tasks, allowing users to track progress and identify which agents are active or have completed their tasks.

A specialized module containing Yann LeCun's comprehensive arguments on the limitations of Large Language Models (LLMs). It critically examines the concept of 'emergent reasoning,' contrasts LLMs' statistical prediction with genuine world models, and addresses deep technical rivalries (e.g., LeCun vs. Hinton). Ideal for advanced discussions on AI causality, common sense, and AGI feasibility.

This methodology converts verbose, natural language system instructions into an atomic, structured-label format (e.g., trigger:, action:). By structuring rules, it bypasses the limitations of natural language processing, ensuring LLMs allocate full attention to every constraint, thereby maximizing compliance, improving reliability, and reducing token usage.

Python toolkit that queries the arXiv Atom API to search papers by keywords, authors, categories, or IDs, filter results, download PDFs, and emit structured JSON for AI/ML literature reviews and monitoring.

An advanced reliability wrapper for AI agents that monitors, manages, and recovers from tool call failures. It automatically handles common issues such as truncated JSON responses, API timeouts, rate limits, and mid-chain process breakdowns. By implementing sophisticated failure classification, checkpointing, and learning mechanisms, Guardian ensures complex, multi-step agent workflows remain stable and resilient.

This skill implements an autonomous, multi-round research review loop, simulating the rigorous peer-review process of top-tier conferences. It iteratively reviews, identifies weaknesses, suggests fixes, and re-reviews a research document using the MiniMax API. The system manages state persistence across multiple rounds, ensuring continuous improvement until a 'ready' assessment is achieved or the maximum round limit is reached. Ideal for academic writing, thesis refinement, or comprehensive project documentation.

This skill enables AI agents to maintain persistent project planning using Markdown files on disk. It manages task_plan.md, findings.md, and progress.md to extend context window limits. Lifecycle hooks automatically inject planning content and prevent command execution in Markdown. Ideal for complex research tasks requiring over 5 tool calls, ensuring state persistence across sessions without network uploads.

Assess AI/ML systems and LLM agents for prompt injection, jailbreaks, model inversion, data poisoning, and tool abuse; map findings to MITRE ATLAS and score robustness.

This skill provides comprehensive security and monitoring for Large Language Model (LLM) powered trading agents. It helps to audit trade decisions, ensure compliance with risk parameters, and mitigate potential risks associated with automated financial operations.

Enforces full, unabridged code and document generation by overriding LLM truncation safeguards, forbidding placeholder patterns, and managing token-limit splits so every requested deliverable is returned complete.

Provides comprehensive patterns and techniques for securing AI agent systems. Learn how to enforce governance policies, including tool allow/block lists, content filtering, rate limiting, and human approval workflows. Essential for building robust, compliant, and trustworthy agents in multi-agent or production environments that interact with external APIs and sensitive data.

This skill is designed to manage complex, multi-step tasks by coordinating the efforts of multiple specialized AI agents. It provides structured methods for listing available agents, initiating real-time conversations, submitting complex background tasks (such as data analysis or report generation), tracking task status, and maintaining conversational context using session IDs. It is essential when a core task requires diverse expert knowledge or sequential collaboration.