Cloud & Infrastructure Skills

Skills for working with cloud platforms and infrastructure-as-code. From provisioning Azure resources to writing Terraform modules, these skills help Claude Code manage your cloud infrastructure.

340 skills

find-skills

vercel-labs/skills

1.1M

14.2k

When users ask "how do I do X" or "can you help with Y," this skill searches the open agent skills ecosystem instead of making you reinvent the wheel. It checks skills.sh for existing solutions, runs CLI searches with specific keywords, and verifies quality by checking install counts and source reputation before recommending anything. The skill prioritizes battle-tested options from sources like vercel-labs and anthropics over unknown packages with low install counts. It's essentially a package manager interface that prevents you from manually coding solutions that already exist as installable skills.

vercel-react-best-practices

vercel-labs/agent-skills+6 more

320.4k

25.2k

This is Vercel's internal performance playbook turned into actionable code guidance. It runs 69 specific checks across React and Next.js codebases, catching things like barrel import performance hits, async waterfall patterns, and unnecessary re-renders. The rules are prioritized by actual impact, so it tackles bundle size killers and server-side bottlenecks before micro-optimizations. Each rule includes before/after code examples showing exactly what to fix. If you're shipping React apps at scale or just want to stop guessing about performance patterns, this codifies what the Vercel team actually follows internally.

agent-browser

vercel-labs/agent-browser+5 more

186.7k

29.3k

A comprehensive browser automation CLI that handles the full spectrum of web interaction tasks through Chrome DevTools Protocol. What impressed me most is the thoughtful authentication handling with six different approaches, from importing existing browser sessions to encrypted credential vaults. The element reference system (@e1, @e2) makes DOM interaction reliable across page changes, and command chaining keeps workflows efficient. The network inspection and download management features push it beyond basic scraping into serious testing territory. If you're doing any programmatic web work beyond simple HTTP requests, this covers the gap between lightweight scraping libraries and heavyweight testing frameworks like Selenium.

AppSignal

Monitor with ease. Code with confidence.

monitoringapmdevtools

Start Free Trial

Sponsored

microsoft-foundry

microsoft/azure-skills+24 more

182.7k

633

A comprehensive toolkit for Microsoft Foundry's AI agent lifecycle, from containerized deployment through production optimization. Handles the complete workflow: builds Docker images, pushes to ACR, creates hosted agents, runs batch evaluations, and optimizes prompts based on performance data. The skill enforces a `.foundry/agent-metadata.yaml` workspace standard and includes specialized sub-skills for deployment, evaluation, troubleshooting, and RBAC management. It's designed for teams running production AI agents who need repeatable deployment pipelines and data-driven prompt optimization. The evaluation workflows are particularly robust, harvesting production traces into datasets and tracking performance regressions across agent versions.

skill-creator

anthropics/skills+2 more

150.6k

118.1k

Creates and iterates on Claude skills through a structured workflow: captures your intent, writes the SKILL.md with proper triggering descriptions, generates test cases for objective outputs, and runs evaluation cycles to refine performance. Handles the full lifecycle from initial draft to optimization, including quantitative benchmarks and description tuning for better triggering accuracy. Most useful when you want to systematize a workflow you've been doing manually or when an existing skill isn't performing well. The evaluation framework is solid, though you'll still need to manually review outputs for subjective improvements. Saves significant time on the boilerplate and testing infrastructure.

azure-ai

microsoft/github-copilot-for-azure+25 more

103.7k

160

Azure AI provides developers and cloud architects with tools to integrate Azure's AI services—including AI Search, Speech, OpenAI, and Document Intelligence—into their applications through MCP tools and CLI commands. The skill solves the problem of implementing complex AI capabilities like vector search, speech-to-text conversion, OCR, and semantic search by offering simplified access to these services. It serves users building AI-enhanced applications who need quick reference guides, SDK documentation, and command-line access to Azure's cognitive services.

agent-tools

inferen-sh/skills+7 more

96.5k

173

This gives Claude access to 250+ AI models through a single CLI interface, letting you generate images with FLUX, create videos with Veo, call various LLMs, run web searches, and automate Twitter posts without managing separate APIs or GPUs. It handles file uploads automatically and works entirely through serverless inference. The real win is consolidating dozens of AI services into one consistent interface, though you'll need to set up authentication with inference.sh first. Best for prototyping AI workflows or when you need to quickly test different models without the usual API setup overhead.

ai-elements

vercel/ai-elements

83.5k

1.9k

Builds AI chat interfaces using the ai-elements component library, which is basically shadcn/ui components specifically designed for AI apps. It'll help you install components like conversations, messages, and tool displays through their CLI, then show you how to wire them up with the AI SDK's useChat hook. The components get added to your codebase (not hidden in node_modules) so you can customize them directly. Most useful when you're building any kind of chatbot or AI assistant interface and want to skip the tedious UI work. The setup assumes you already have Next.js, shadcn/ui, and the AI SDK installed.

seo-audit

coreyhaines31/marketingskills+34 more

78.7k

21.4k

Claude runs a systematic SEO audit covering crawlability, technical foundations, on-page optimization, and content quality. It checks robots.txt, sitemaps, Core Web Vitals, title tags, heading structure, and internal linking while flagging common issues like duplicate content, canonicalization problems, and keyword cannibalization. The skill includes a helpful warning about schema markup detection limitations since web_fetch can't see JavaScript-injected structured data. It adapts the audit scope based on your site type and provides actionable recommendations in priority order. Good for diagnosing traffic drops, pre-launch reviews, or comprehensive health checks when you suspect SEO issues but aren't sure where to start looking.

browser-use

browser-use/browser-use

66.5k

88k

This automates browser interactions through a persistent daemon that keeps Chrome running between commands, giving you ~50ms response times instead of the usual multi-second browser startup. You get element indices from `browser-use state`, then click, type, or extract data using those indices. It handles the annoying parts well: connects to your existing Chrome profile to preserve logins, runs headless by default, includes cloud browser fallback for zero-config setups. The command chaining works reliably since the browser stays alive. Genuinely useful for web scraping, form automation, or any task where you need to interact with actual web pages rather than just fetch HTML.

next-best-practices

vercel-labs/next-skills+2 more

64.5k

817

Comprehensive Next.js linting that catches the stuff your regular ESLint misses. Detects async client components, non-serializable props across RSC boundaries, and improper Server Action usage. Flags Next.js 15+ async API violations like treating params as synchronous. Enforces image optimization with next/image, proper metadata generation, and correct file conventions for app router. Also checks for hydration gotchas like browser API calls during SSR and missing Suspense boundaries around useSearchParams. Essential if you're working with app router complexity or migrating between Next.js versions where the rules keep changing.

writing-plans

obra/superpowers

60k

154.2k

Takes specs and generates step-by-step implementation plans with actual code snippets, exact file paths, and specific test commands. Maps out file structure first, then breaks everything into 2-5 minute tasks following TDD cycles. Saves plans as markdown with checkbox syntax in `docs/superpowers/plans/`. Runs self-review checks for placeholder content and type consistency. Works best when you have clear requirements but need to think through the implementation approach before coding. The bite-sized granularity keeps you from getting stuck on large, vague tasks.

lark-doc

larksuite/cli+2 more

59.7k

7.9k

A comprehensive Lark document management tool that handles the full lifecycle of Feishu/Lark docs. Creates documents from Markdown, fetches content, performs granular updates (append/overwrite/replace/insert/delete), and manages media uploads and downloads. The standout feature is intelligent whiteboard integration that automatically suggests visual diagrams (flowcharts, architecture diagrams, org charts) based on document content semantics. Also serves as a discovery layer for finding spreadsheets and other cloud resources before switching to specialized tools. Handles the tricky wiki token resolution where wiki URLs don't directly map to file tokens. Essential for anyone building Lark-integrated workflows or documentation automation.

openclaw-secure-linux-cloud

xixu-me/skills+1 more

56.4k

Deploy OpenClaw on cloud servers with conservative security defaults rather than the typical "expose everything and lock down later" approach. Guides you through Linux hardening, rootless Podman setup, loopback-only gateway binding, and SSH tunnel access before considering Tailscale or reverse proxies. Includes distro-specific firewall commands, baseline configs with token auth and sandboxing enabled, and checklists for auditing exposure. Best for self-hosters who want private control plane access first, then deliberate exposure decisions. Skip this if you just want local OpenClaw setup.

neon-postgres

neondatabase/agent-skills

24.1k

The neon-postgres skill provides guidance on working with Neon Serverless Postgres, a serverless database platform that separates compute and storage to enable autoscaling, branching, and scale-to-zero functionality. It covers getting started, connection methods, local development tools, authentication, data APIs, and the Neon CLI—helping developers of any language or framework integrate Neon into their applications. The skill solves the problem of understanding which Neon features and connection patterns to use for different runtime environments and use cases.

convex-setup-auth

get-convex/agent-skills

22.8k

The convex-setup-auth skill implements secure authentication in Convex applications by configuring auth providers (Convex Auth, Clerk, WorkOS AuthKit, Auth0, or custom JWT), setting up user management with identity mapping, and establishing role-based access control. It serves developers building Convex apps who need to add login/signup functionality or protect queries and mutations with authentication. The skill solves the problem of choosing the right auth provider and properly wiring authentication infrastructure by guiding users through provider selection and providing setup patterns for each supported option.

firebase-ai-logic

firebase/agent-skills

22.7k

225

Integrates Google's Gemini AI models directly into web apps through Firebase's client-side SDK, handling everything from basic text generation to multimodal inputs like images and PDFs. Sets up the Gemini Developer API automatically, generates proper initialization code for Firebase projects, and covers streaming responses, chat sessions, and structured JSON output. The skill emphasizes security with App Check integration and Remote Config for dynamic model switching. Best for developers who want to add AI capabilities without managing backend infrastructure, though you'll need to understand Firebase project structure and billing implications for production use.

ai-sdk

vercel/ai+3 more

19k

23.5k

turborepo

vercel/turborepo

19k

30.2k

This skill helps you properly configure and use Turborepo for JavaScript monorepos. It triggers when working with turbo.json, task pipelines, caching configuration, and monorepo structure. The main value is enforcing correct patterns like creating package-level tasks instead of root-level scripts, using "turbo run" in code versus the shorthand, and setting up proper dependency graphs with dependsOn. It covers practical scenarios like debugging cache misses, running only affected packages with --affected, configuring remote caching for CI, and structuring apps versus packages directories. Most developers initially misconfigure task organization, so the guidance on package tasks versus root tasks saves significant debugging time.

baoyu-image-gen

jimliu/baoyu-skills

17.7k

14.6k

baoyu-image-gen generates images from text prompts using multiple AI providers including OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream, and Replicate. It serves users who need text-to-image generation with support for reference images, custom aspect ratios, and batch processing capabilities. The skill solves the problem of integrating diverse image generation APIs through a unified interface while managing provider preferences and generation parameters.

python-testing-patterns

wshobson/agents+19 more

15.3k

33.7k

Python-testing-patterns enables developers to implement comprehensive testing strategies using pytest, fixtures, mocking, and test-driven development practices for Python codebases. It provides guidance on unit tests, integration tests, test structure, coverage measurement, and test isolation to help engineers write robust test suites and maintain code quality. The skill addresses the problem of setting up effective testing infrastructure and following testing best practices across different test types and scenarios.

ideabrowser.com

Find trending startup ideas with real demand. Launch with a team of AI agents.

startupsai agentsideas

Get trending startup ideas →

FAQ

Can Claude Code help with cloud infrastructure?

Yes — cloud skills teach Claude to write IaC templates, configure cloud services, and follow provider-specific best practices for AWS, Azure, GCP, and other platforms.

Related categories

DevOps & CI/CD683 Backend & APIs1170 Security410