Agent Skills Hub

web-design-guidelines

Audit UI code for Web Interface Guidelines compliance. Automatically checks accessibility, design standards, and UX best practices.

theme-factory

Toolkit for applying consistent, professional styling to artifacts like slides, documents, and web pages using pre-set or custom-generated themes.

drift

Frameworks and tools for AI agents exploring consciousness, identity, and persistent autonomy. Includes session handoff, memory infrastructure, and self-reflection protocols.

generate-e2e-test

Automated end-to-end test generation using Playwright. Converts user workflows into functional test specs by interactively executing actions and following project conventions.

mcp-rails

Implement a full Model Context Protocol (MCP) stack in Rails. Connect to external servers, expose your Rails app as an MCP server, or manage subprocess MCP containers via Docker with OAuth 2.1 PKCE support.

creating-opencode-agents

Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.

docs-generator

Generate hierarchical, AI-optimized documentation structures (AGENTS.md, agent.d) to streamline codebase context, setup, and navigation for AI coding assistants and developers.

frontend-design-pro

Build $50k-grade frontend interfaces with production-ready code, professional typography, and high-fidelity image integration.

ascii-art

A generative agent skill for creating ASCII art, optimized for rapid, single-pass artistic output without iterative refinement.

moonbit-refactoring

Refactor MoonBit code for idiomatic style: minimize public APIs, implement methods, leverage pattern matching with views, and enforce high test coverage for maintainable MoonBit projects.

socratic

Deep inquiry framework using Socratic questioning to examine beliefs, uncover hidden assumptions, test evidence, and reach nuanced understanding without lecturing.

condition-based-waiting

Replaces arbitrary test timeouts with robust condition-based polling to eliminate flaky tests, race conditions, and timing-dependent failures in software testing suites.