Agent Skills Hub

gtm-mcp

Operate Google Tag Manager via MCP. Handles OAuth, resource discovery, and CRUD operations for tags, triggers, and variables directly from your LLM agent.

playwright-skill

Complete browser automation with Playwright. Features local dev server detection, script generation, screenshot capture, form filling, responsive testing, and UX validation.

doncheli-visual-test

Perform automated visual regression testing by comparing UI screenshots against established baselines to identify layout shifts, color changes, and rendering regressions.

project-scaffolding

IDE-grade project scaffolding wizard for 70+ types of web, mobile, desktop, and backend projects, featuring interactive setup for SDKs, databases, and DevOps configurations.

task-folder-migrator

Automates the migration of legacy single-file task lists to a structured, folder-based project management system.

use-railway

Operate Railway infrastructure: manage projects, services, databases, object storage, deployments, environments, variables, logs, and performance metrics.

xcodebuildmcp

Official MCP server for iOS/macOS development: streamline builds, tests, runs, debugging, and UI automation using Xcode and CLI workflows.

dev-cycle

Interactive development workflow manager. Coordinates discovery, planning, review, and build phases using a specialized team of AI agents (Scout, Bob, Garry, Arlo) for consistent project delivery.

styler

Converts complex bash commands prone to parse errors into reliable temporary scripts for robust execution.

file-todos

A structured file-based system for tracking todos, managing technical debt, and coordinating code review workflows directly within your repository.

home-assistant-master

Home Assistant OS (HAOS) operations skill for agents. Features read-only diagnostics, automation design, health auditing, and safety-first configuration management.

creating-opencode-agents

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