Agent Skills Hub

color-palette

Generate complete, accessible colour systems from a single hex. Includes 11-shade scales (50-950), semantic tokens, dark mode variants, and Tailwind v4 CSS output.

cloudscape-codegen

Generate production-ready Cloudscape Design System React + TypeScript UI code, components, and scaffolds with accessibility, responsive patterns, and robust state handling.

nuxt-ui-v4

Production-ready Nuxt UI v4 component library featuring 125+ accessible components, Tailwind CSS v4, Reka UI, and specialized dashboard, chat, and editor layouts.

agent-sdk

Expert skill for building and maintaining AI agents using the Claude Agent SDK, covering architecture, tool integration, MCP servers, and agentic workflows.

Test Skill A

A CLI tool that automates the discovery and symlinking of agent skills distributed via npm packages, simplifying integration for AI-powered coding agents.

Project Context Analyzer

Analyze project structures, dependencies, and patterns using parallel agent execution to generate comprehensive context documentation for rapid codebase onboarding and AI-assisted development.

godot-gdscript-patterns

Master Godot 4 GDScript patterns, including signal-based communication, state machines, scene architecture, and performance optimization for professional game development.

Verification & Quality Assurance

A robust verification and QA system for software agents featuring real-time truth scoring, automated code validation, and instant rollback capabilities to maintain high reliability.

test-reporting-analytics

Advanced QE reporting, quality dashboards, and predictive analytics for test metrics, code coverage, and deployment readiness to drive data-informed quality decisions.

document

Interactive terminal canvas for rendering, editing, and selecting markdown text, emails, and project documentation in Claude Code.

predict-lucky-number

Generates a random lucky number between 0 and 9999 for games, decision-making, or entertainment.

eval

Evaluate Deca agent prompts and behavioral consistency through automated test runners, manual LLM judgment, and structured reporting.