Use when the user wants to provision infrastructure or third-party services using Stripe Projects.
Recommend sharding, caching strategies, and read-replication patterns for Cloudflare architectures.
Deployment patterns from Kubernetes to serverless and edge functions.
Pre-deployment verification checklist. Use when about to ship a release, deploying a change with database migrations or feature flags…
Create, generate, or scaffold GitHub Actions workflows, action.yml, or .github/workflows CI/CD pipelines.
Build Windows images with Packer using WinRM communicator and PowerShell provisioners.
Audit existing caching implementation — find cache misses, stampedes, and key design issues.
Configures GitHub Actions CI/CD workflows for testing, linting, and deployment.
Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter…
Automatically discover cloud, infrastructure, deployment, and container skills when working with AWS, GCP, Azure, Docker, Kubernetes…
Azure Communication Services common utilities for Java.
Audit existing queue and streaming infrastructure — find missing DLQs, scaling gaps, and reliability issues.
Configures and builds YARS with optimizations for performance testing and benchmarking
Cloudflare Email Routing for receiving/sending emails via Workers.
Assess and plan migrations from existing VPN, SWG, or SASE platforms to Cloudflare One, including policy mapping, parity gaps, and rollout.
/============================================================================/ / SKILL SKILL :: VERILINGUA x VERIX EDITION /…
Generate specialized skills for each subsystem in the monorepo.
Set up a repository for local GitHub Actions verification using act, so Jules can validate CI before pushing
Deploy and configure Microsoft's SaaS Accelerator for marketplace offers.
Deploy the application to a target environment.
Use when designing new high-level system architecture, reviewing existing designs, or making architectural decisions.
Cloud & DevOps agent skills on mcprush hold an agent to the order of operations infrastructure work needs — a dry run before a mutation, a timeline before a root cause, a plan read in full before it is applied. The kinds are workflow, expertise, output format, voice & style and guardrail, and the one a skill belongs to, where its author declared it, is the fastest way to guess what it will do to your prompt.
What to look at before installing one is what it costs in context and what it takes away: a guardrail that refuses an action and a voice that rewrites a sentence are both skills, and only one of them will stop the agent doing something. Every skill here says what it costs in context, which kind it is where its author declared one, what it needs beside it to work and the licence it is published under, next to the publisher it came from and whether that publisher has been verified. The filters on the left narrow it further and the sort at the top decides what comes first.
A skill is not connected to anything: there is no endpoint to authorise and nothing routed through the gateway. Installing one drops a folder of instructions into the client’s own skill folder, and uninstalling it is deleting that folder. The exact line for each client is on the skill’s own page, because it differs by client rather than by skill.