Building ADK agents involves many steps — scaffolding, evaluating, deploying, and monitoring. This skill provides a structured workflow so you can develop agents correctly using Google's agents-cli toolkit without missing critical steps.

Release coordination is fragmented across checklists, chat threads, and scattered documents. This skill consolidates release inputs into one reusable packet with rollout, rollback, migration, and stakeholder coverage.

Accessing multiple AI models requires juggling different APIs and tools. This skill provides a unified CLI to run 250+ AI apps for image, video, text, and search tasks.

Developers waste time integrating multiple AI APIs separately. This skill provides the belt CLI to access 250+ AI models for images, video, LLMs, and search through a single command-line interface.

Developers need a reliable way to manage feature flags and dynamic app behavior without releasing updates. This skill provides step-by-step guidance for integrating Firebase Remote Config, managing templates via CLI, and following best practices for fetching and activating values.

Setting up databases, auth, and other infrastructure manually is slow. This skill lets you provision third-party services and retrieve credentials directly through the Stripe Projects CLI.

Managing submissions across many AI skill marketplaces is time-consuming and error-prone. This skill automates the entire publishing workflow from inspection and planning to verified submission across 25+ marketplaces.

Local web application testing requires reliable browser automation without manual setup. This toolkit provides Playwright scripts and server management utilities to streamline frontend testing workflows.

Deploy any project to Vercel without authentication or configuration. The skill packages your code, detects your framework automatically, and returns live preview URLs in seconds.

Git worktrees enable simultaneous branch work without context switching. This skill provides systematic directory selection and safety verification for reliable workspace isolation.

Random fixes waste time and create new bugs. This skill provides a four-phase debugging framework that finds root causes before implementing solutions, preventing wasted effort on symptom-based fixes.

Creating MCP servers that work well with AI assistants requires careful design decisions. This guide provides proven patterns for tool design, API integration, and evaluation that ensure reliable LLM interactions.

Maintaining identical configuration files for multiple AI agents is tedious and error-prone. This tool automatically keeps AGENTS.md, CLAUDE.md, and GEMINI.md files in sync across your entire project with real-time file watching or manual triggering.

This skill automates the entire deployment process by guiding users through creating a GitHub repository and deploying to Vercel, eliminating manual deployment steps and reducing errors.

Stop struggling with complex git workflows and accidental sensitive file commits. This skill automates the entire GitHub deployment process with built-in security scanning, large file detection, and intelligent .gitignore generation.

Package downloads and container pulls can be slow from distant registries. Xget rewrites URLs to accelerated mirrors, and this skill applies the configuration across your tools automatically.

Web automation tasks require different approaches - some need your live browser session, others work better with public-web tools. This skill teaches AI agents to choose the right tool layer for each task while preserving your browser state.

Finding and installing reusable AI capabilities is fragmented and tedious. The skills CLI provides a unified package manager to discover, install, and manage skills across Claude, Codex, and other agents.

Setting up a secure cloud server requires navigating distro differences and avoiding common pitfalls. This skill provides a structured, verified workflow for SSH hardening, firewall configuration, Nginx setup, HTTPS deployment, and optional performance tuning.

Reduce Anthropic API costs by routing Claude Code requests through a local LiteLLM proxy to GitHub Copilot. This skill provides step-by-step setup instructions for configuring the proxy workaround.