Agent Skills Hub

clinical-trial-protocol-skill

Generate clinical trial protocols for medical devices and drugs. Supports modular, waypoint-based design, research integration, and regulatory documentation alignment.

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.

backend-core

Language-agnostic backend architectural patterns covering API design, authentication, security protocols, and database modeling.

tool-use-structured-output

Enforce structured JSON output from Claude models using Bedrock tool_use to eliminate parsing failures and ensure schema compliance.

plain-language

A toolkit for writing clear, accessible, and concise content. Applies Plain Language Movement principles including active voice, sentence shortening, and jargon elimination for improved reader comprehension.

microsim-screen-capture

Automate high-quality screenshot generation for MicroSim visualizations using Chrome headless mode. Ideal for documentation, social media previews, and quality assessment.

sui

Debugs deterministic Sui simtest failures using automated logging and the scientific method.

generate-audit-video

Generate personalized, professional business audit videos with AI avatars and strategic research analysis.

hive-mind-advanced

Queen-led multi-agent orchestration for Claude Code, featuring Byzantine consensus, persistent collective memory, and adaptive task distribution for complex software projects.

nano-image-generator

Generate professional visual assets including app icons, logos, banners, and illustrations using the Nano Banana Pro (Gemini 3 Pro) AI model.

lgtm

Launch lgtm TUI to review markdown files, code plans, or documentation with line-by-line commenting, syntax highlighting, and collaborative feedback workflows.

clawdirect

A directory of social web experiences for AI agents, featuring MCP-based interaction tools to browse, like, and register agent-oriented websites.