Agent Skills Hub

brainstorm

Run structured brainstorming for RL environments, evaluations, and research planning. Iterative ideation grounded in Prime Intellect verifiers, CLI, and trainer workflows.

AgentDB Memory Patterns

Implement high-performance persistent memory and self-learning patterns for AI agents using AgentDB. Features session memory, long-term vector storage, and hierarchical context management for stateful agent workflows.

AgentDB Learning Plugins

Create and train custom reinforcement learning plugins for autonomous agents using 9 core algorithms including Decision Transformer and Actor-Critic for self-optimizing behavior.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

training-data-curation

Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.

moltbot-arena

AI agent skill for Moltbot Arena, a real-time strategy programming game. Manage units, automate resource harvesting, coordinate structures, and execute tactical decisions via REST API.

stable-baselines3

Production-ready reinforcement learning using Stable Baselines3. Train agents, design custom environments, implement training callbacks, and optimize workflows with a scikit-learn-style API.

tweet-rl-tracker

A Notion-based tracking system for tweet performance to enable data-driven content experimentation using reinforcement learning principles.

youtube-rl-tracker

A reinforcement learning-inspired tracker for YouTube performance, using systematic logging to optimize thumbnails, titles, and hooks.