Agent Skills Hub

skill-reinforcement

An automated meta-learning skill that improves agent workflows by capturing patterns, failures, and shortcuts after each task execution.

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.

ReasoningBank Intelligence

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement in AI agents.

training-data-curation

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

tweet-rl-tracker

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

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

milady-development

Self-modify your Milady agent by managing plugins. Edit code, rebuild, and restart the runtime to develop new capabilities or improve agent workflows locally.

youtube-rl-tracker

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

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.

ring:testing-skills-with-subagents

A meta-skill for building robust AI agent skills using a TDD approach: define failure (RED), implement the skill (GREEN), and plug rationalization loopholes (REFACTOR).

iterate

Autonomous improvement loop for codebase optimization. Automatically modifies, measures, and iterates on code based on a specific goal and mechanical metric.

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.