Best Best AI Agent Skills for DevOps & Infrastructure

Automation for browser tasks including navigation, DOM manipulation, and user interactions via command line.

The `browser-use` command provides fast, persistent browser automation. It maintains browser sessions across commands, enabling complex multi-step workflows.

Better Auth is a TypeScript-first, framework-agnostic auth framework supporting email/password, OAuth, magic links, passkeys, and more via plugins.

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools, measured by the quality of task accomplishment.

Systematic debugging focuses on finding the root cause of technical issues before applying any fixes. It emphasizes a structured approach to identify and solve problems efficiently.

Use this skill for ALL networking work including API requests, data fetching, caching, or network debugging.

This skill covers deploying Expo applications across all platforms using EAS (Expo Application Services).

Build agent-facing web experiences with ATXP-based authentication.

API routes in Expo allow developers to handle server-side logic, manage sensitive data, interact with databases, and process HTTP requests within a React Native application.

Load plan, review critically, execute tasks in batches, report for review between batches. Core principle: Batch execution with checkpoints for architect review.

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review. Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.

Help developers write and edit EAS CI/CD workflow YAML files.

Dispatch superpowers:code-reviewer subagent to catch issues before they cascade, promoting early and frequent code reviews.

Verification Before Completion promotes integrity in claiming completed work by requiring evidence of verification before any completion claims are made.

The skill 'using-superpowers' assists users in invoking and utilizing skills optimally during tasks, ensuring the correct skills are applied to maximize productivity.

Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.

Dispatching Parallel Agents enables users to investigate multiple unrelated failures concurrently, improving efficiency in debugging by sending individual agents for specific issues that don't share state.

This skill focuses on effectively receiving and handling code review feedback, prioritizing technical correctness over emotional responses. It emphasizes a structured response pattern to ensure clarity and correctness in implementing feedback.

Guide completion of development work by presenting clear options and handling chosen workflow.

Gemini is a skill designed for conducting code reviews, analyzing architectural plans, and processing large context tasks effectively. It enables practitioners to perform comprehensive evaluations across multiple files and understand relationships within codebases.

Refactor bloated agent instruction files following progressive disclosure principles, keeping essentials at root and organizing the rest into linked, categorized files.

Create clear and safe commit messages and boundaries for Git commits, adhering to best practices like Conventional Commits.

Access ATXP's paid API tools via CLI.

Creates comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves the long-running agent context exhaustion problem.

Smart dependency management for any language with automatic detection and safe updates.

Generate a daily standup/meeting update through an interactive interview. Never assume tools are configured—ask first.

The AI SDK provides tools and resources for developers to integrate artificial intelligence capabilities into their applications using the Vercel platform.

Gepetto orchestrates a multi-step planning process which includes the stages: Research, Interview, Spec Synthesis, Plan, External Review, and Sections. It requires a markdown spec file to operate and generates various planning documents and files for implementation.

This skill guides the creation of Claude Code slash commands - reusable workflows that can be invoked with `/command-name` in Claude Code conversations.

Generate software architecture documentation using C4 model diagrams in Mermaid syntax.

Vitest is a next-generation testing framework powered by Vite, providing a Jest-compatible API with native ESM, TypeScript, and JSX support out of the box.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers and stand the test of time.

pnpm is a fast, disk space efficient package manager. It uses a content-addressable store to deduplicate packages across all projects on a machine, saving significant disk space. pnpm enforces strict dependency resolution by default, preventing phantom dependencies. Configuration should preferably be placed in pnpm-workspace.yaml for pnpm-specific settings.

Converts PRDs to beads (epic + child tasks) for ralph-tui autonomous execution.

Converts PRDs to beads (epic + child tasks) for ralph-tui autonomous execution using beads-rust.

Universal release workflow supporting any project type with multi-language changelog.

Comprehensive guidance for building scalable, maintainable, and production-ready Node.js backend applications with modern frameworks, architectural patterns, and best practices.

Anthony Fu's preferences for setting up a development environment using tools like pnpm, TypeScript, and ESLint tailored towards modern JavaScript development with strict configurations.

Production-ready FastAPI project structures with async patterns, dependency injection, middleware, and best practices for building high-performance APIs.

Master Stripe payment processing integration for robust, PCI-compliant payment flows including checkout, subscriptions, webhooks, and refunds.

Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship code quickly and catch regressions before users do.

Master Retrieval-Augmented Generation (RAG) to build LLM applications that provide accurate, grounded responses using external knowledge sources.

Work like Manus: Use persistent markdown files as your 'working memory on disk.'

Build resilient applications with robust error handling strategies that gracefully handle failures and provide excellent debugging experiences.

Production-ready GitHub Actions workflow patterns for testing, building, and deploying applications.

Build efficient, scalable monorepos that enable code sharing, consistent tooling, and atomic changes across multiple packages and applications.

Firecrawl CLI is used to fetch and search the web, prioritizing data collection over other web data tools. It is designed for web scraping and searching, allowing for organization of results and offering various output formats.

Master microservices architecture patterns including service boundaries, inter-service communication, data management, and resilience patterns for building distributed systems.

Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches.

The Code Review skill provides a structured approach to reviewing code for security vulnerabilities, performance issues, code quality, and testing completeness. It helps developers identify areas that need fixing, considerations for improvement, and recognizes good coding practices.