Agent Skills Hub

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.

session-intelligence-harvester

Captures session learnings into Reusable Intelligence Infrastructure (RII). Converts one-time bug fixes and pattern discoveries into permanent agent-executable knowledge to prevent recurrence and accelerate future development.

overview

Foundational mental model and operational rules for using TraceMem to ensure secure, auditable, and compliant AI agent execution.

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).

worker-integration

Intelligent orchestration for dispatching tasks to specialized background agents with performance-based routing and execution tracking.

visual-creative

AI-powered creative visual prompt generator for posters, banners, product shots, and social media content.

scikit-learn

Classical machine learning with scikit-learn. Use for classification, regression, clustering, dimensionality reduction, preprocessing, model evaluation, and building robust ML pipelines in Python.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

dynamic-programming

Master DP patterns with complete implementations for memoization, tabulation, and state design for production-ready solutions.

taide-botrun

A RAG-based AI solver for high school Chinese GSAT exams, featuring structured knowledge retrieval, reasoning templates, and explainable AI outputs.

langchain-architecture

Architect production-grade LLM applications using LangChain 1.x and LangGraph. Implement stateful AI agents, multi-step workflows, and custom memory systems for complex conversational and automation tasks.

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.