Agent Skills Hub

context-cascade

A nested plugin architecture for Claude Code that optimizes context by dynamically loading playbooks, skills, and agents to save over 90% in token usage.

text-to-sql

Convert natural language queries to safe, optimized SQL. Automates database interactions with schema awareness and parameterized query generation.

pyhealth

Comprehensive Python healthcare AI toolkit for clinical data processing, medical coding translation, and developing deep learning models like RETAIN and Transformers for EHR, physiological signals, and clinical prediction tasks.

writing-standards

A professional writing standard plugin for high-quality Korean technical content, enforcing omniscient 3rd-person perspectives, AI pattern elimination, and systematic citation systems.

youtube-rl-tracker

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

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.

nvidia-resiliency-ext

Provides resiliency, health monitoring, and fault tolerance utilities for NVIDIA GPU-accelerated distributed applications, including process management and API key handling.

plan-down

Method-driven planning workflow that intelligently decomposes tasks into structured plan.md files using zen-mcp tools, adapting to user clarity and automation needs.

creative-thinking-for-research

Applies cognitive science frameworks for creative thinking to generate genuinely novel research directions in computer science and AI.

dynamic

Fullstack development agent for bkend.ai BaaS. Automates project init, auth/db setup, and API integration for Next.js applications.

xhs-writing-coach

AI-powered coach for Xiaohongshu (XHS) note writing. Generate viral, platform-optimized content with storytelling templates, engagement hacks, and automated compliance tagging.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.