Railway's official agent skill: create projects, provision databases and buckets, deploy, manage variables and domains, and read build failures back — from the CLI, API or MCP server.
DevOps & Infrastructure Skills
Deploy, run and observe software: cloud, CI/CD, infrastructure as code and monitoring.
Skills in DevOps & Infrastructure
Google's official skill for driving the gcloud CLI safely from an agent: validate every command against its own help text, cap the output, and refuse the operations that should never run unattended.
Official AWS skill for authoring, deploying and debugging CDK stacks — construct patterns, bootstrap, drift, resource import and the CloudFormation errors that trap people.
67 views
Microsoft's official skill that turns an agent into an Azure solution architect — 10 design principles, 6 architecture styles, 44 design patterns and a Well-Architected review workflow.
Cloudflare's official platform skill — Workers, Pages, storage, AI, networking, security, and IaC in one reference.
Skill: ngrok Agent Skills
by ngrok
ngrok's official skill pack: expose localhost, secure endpoints, receive verified webhooks and run an MCP gateway from your coding agent.
Skill: GoLive
by mikehasa
Open-source agent skill that takes an AI-built app live on your own accounts: hosting, database, domain, email and payments, with a plan-and-approve workflow.
AMD's official skill for CPU inference: brings up a single vLLM + zentorch endpoint on an EPYC server, sized to the socket it runs on.
AMD's official skill for standing up a vLLM endpoint on Instinct MI300X/MI325X/MI350X/MI355X GPUs — detection, recipe lookup, launch and health check in one flow.
Skill: Workers Best Practices
by Cloudflare
Production review rules for Cloudflare Workers — compatibility dates, observability wiring, and the runtime anti-patterns that only bite at the edge.
Skill: Next.js on Cloudflare
by Cloudflare
Cloudflare's routing skill for Next.js on Workers — sends the agent to vinext, the Vite-based Next.js runtime Cloudflare now recommends ahead of OpenNext.
Skill: Azure Kubernetes Service (AKS)
by Microsoft
Microsoft's official AKS planning skill: separates the Day-0 decisions you cannot undo (networking, API server) from the Day-1 features you can switch on later.
Skill: Azure Cost Management
by Microsoft
Microsoft's official Azure skill for cost work: query historical spend, forecast it, and hunt down waste like orphaned disks and oversized VMs.
Skill: Datadog Triage Flaky Test
by Datadog
Official Datadog skill for investigating one flaky test — pulls its history and failure pattern, categorises the root cause and recommends fixing, quarantining or escalating.
Skill: Datadog Unblock PR
by Datadog
Official Datadog skill that triages a failing PR pipeline, attributing every CI failure as flaky, infra or genuine regression and proposing a targeted fix.
Skill: Datadog Browser RUM Instrumentation
by Datadog
Official Datadog skill that adds or repairs Browser RUM in a web app — detects framework, router, bundler and existing setup, then wires init once and verifies the build still passes.
Skill: Datadog Pup CLI
by Datadog
Official Datadog skill for the pup CLI — OAuth2 login with token refresh, plus a command map covering logs, monitors, traces, metrics, incidents, SLOs, on-call, security signals and audit logs.
Skill: Grafana Alloy Collector Configs
by Grafana Labs
Grafana's official Alloy skill: write one collector config that carries metrics, logs, traces and profiles, validate it locally, and prove samples are actually leaving the box.
Skill: Grafana Tempo & TraceQL
by Grafana Labs
Grafana's official Tempo skill: stand up a tracing backend that needs nothing but object storage, then write TraceQL that finds the slow span instead of scrolling for it.
Skill: Grafana Loki & LogQL
by Grafana Labs
Grafana's official Loki skill: write LogQL that returns rows instead of timeouts, ship logs through Alloy, and reason about a store that indexes labels rather than log text.
Skill: NVIDIA Holoscan SDK Setup
by NVIDIA
Inspects the host's hardware, OS, CUDA driver and existing tooling, recommends one Holoscan SDK install method with a reason, then hands off to the matching install skill.
Skill: PlanetScale CLI Automation
by PlanetScale
How to drive the PlanetScale CLI non-interactively: --format json everywhere, auth check before anything else, pscale sql instead of pscale shell, correct flag placement.
Skill: PlanetScale Change Gates
by PlanetScale
PlanetScale's approval contract for agents: five operation classes that decide what a database agent may do freely, what needs a named approval, and what it must never do alone.
Skill: Deploy to Vercel
by Vercel
Vercel's official deployment skill — inspects project state, picks the right deploy path, and defaults to preview deployments with a claimable URL when no account is linked.
Skill: SageMaker HyperPod Cluster Debugger
by AWS Labs
Read-only diagnostics for cluster-wide SageMaker HyperPod failures on EKS or Slurm — CloudFormation errors, EFA health checks, lifecycle scripts, capacity, dangling nodes and autoscaler conflicts.
Skill: Jetson LLM Serve
by NVIDIA
Picks the right vLLM or SGLang runtime for your Jetson generation and JetPack version, then produces a working OpenAI-compatible serving command.
Skill: Cloudflare One Zero Trust
by Cloudflare
Cloudflare's official skill for designing, configuring and troubleshooting Cloudflare One — Access, Gateway, WARP, Tunnel, DLP, CASB, device posture and identity — with retrieval over recalled docs.
Skill: Sentry AI Agent Monitoring Setup
by Sentry
Sentry's official skill for instrumenting LLM and agent code — detects your installed AI SDK and wires up traces for model calls, tool use and token spend.
Skill: Sentry SDK Setup
by Sentry
Sentry's official router skill: detects your language or framework, then loads the matching Sentry SDK setup guide for error monitoring, tracing and session replay.
Skill: OpenAI gh-fix-ci
by OpenAI
OpenAI's skill for debugging failing GitHub Actions checks on a pull request: pull the logs with the gh CLI, summarise the failure, plan the fix, implement only after approval.
Skill: LaunchDarkly Guarded Rollout
by LaunchDarkly
Design a staged LaunchDarkly rollout — traffic steps, monitoring windows, regression thresholds and automatic rollback — and start it from your coding agent.
Skill: Google Cloud Spanner Basics
by Google Cloud
Google's official Spanner skill: provision instances, design primary keys that do not hotspot, write SQL and client-library code, and diagnose slow queries — with DDL and DML gated behind your approval.
Skill: bitdrift Critical User Journey Monitoring
by bitdrift
Stands up end-to-end monitoring for a business-critical flow — path discovery, conversion funnel, completion SLO, step-duration alerts and a dashboard.
Skill: bitdrift Instrumentation
by bitdrift
Adds the bitdrift Capture SDK to an iOS, Android or React Native app and wires up logging, network monitoring, screen views and TTI correctly.
Skill: Dynamo Router Starter
by NVIDIA
NVIDIA's official skill for bringing up Dynamo inference routing — pick a router mode, enable KV-aware routing, and smoke-test the frontend endpoint before claiming anything works.
Google's official Well-Architected Framework skill for the security pillar — turns an architecture review into a structured interview, gap analysis and prioritised recommendations.
Skill: Cloud SQL Basics
by Google
Google's official Cloud SQL skill — create and connect MySQL, PostgreSQL and SQL Server instances with the right gcloud commands, Auth Proxy setup, HA and backup model.
Skill: AlloyDB Basics
by Google
Google's official AlloyDB for PostgreSQL skill — cluster and instance lifecycle from gcloud, plus hard rules on private connectivity, IAM database auth and backup behaviour.
Skill: Packer AWS AMI Builder
by HashiCorp
HashiCorp's official Packer skill for building Amazon Machine Images with the amazon-ebs builder, covering template structure, plugin pinning and the cost and timing caveats.
Skill: Terraform to Pulumi Migration
by Pulumi
Pulumi's official migration skill for moving Terraform or OpenTofu projects to Pulumi — translating HCL and importing tfstate without recreating live infrastructure.
Skill: Terraform Style Guide
by HashiCorp
HashiCorp's official skill for writing Terraform that matches the published style guide — file layout, naming, variable validation and secure-by-default resources.
Skill: .NET Crash Dump Collection
by .NET Foundation
The .NET team's official skill for capturing crash dumps from CoreCLR and NativeAOT apps on Linux, macOS, Windows and inside containers — collection only, no analysis.
Skill: GKE Basics & Critical Gotchas
by Google
Google's official GKE skill — when Autopilot beats Standard, Workload Identity instead of JSON keys, Autopilot's 250m CPU rounding, and private-cluster flags.
Skill: Cloud Run Basics
by Google
Google's official Cloud Run skill — deploy services, jobs and worker pools correctly, with the IAM roles, port contract and gotchas that break first deployments.
Skill: Elastic LLM and Agentic Observability
by Elastic
Elastic's official skill for monitoring LLM and agent workloads — token cost, latency, response quality and workflow orchestration, queried with ES|QL.
Skill: NVIDIA RAG Blueprint
by NVIDIA
Deploy, configure and troubleshoot the NVIDIA RAG Blueprint from your agent — Docker Compose, Helm or library, with feature toggles for VLM, guardrails and agentic RAG.
Skill: Aiven for OpenSearch Deployment
by OpenSearch Project
Provision and deploy to Aiven for OpenSearch from an agent — managed clusters on AWS, GCP, Azure, DigitalOcean or UpCloud, with the Aiven-generated password read back after provisioning.
Skill: OpenSearch Trace Analytics
by OpenSearch Project
Investigate OpenTelemetry traces stored in OpenSearch — slow and error spans, reconstructed trace trees, service maps, plus agent invocation and token-usage analysis.
Skill: OpenSearch Log Analytics
by OpenSearch Project
Query and analyse logs held in OpenSearch using PPL and Query DSL — error-pattern discovery, error-rate tracking and anomaly detection, driven from natural language.
Skill: Datadog Audit Trail
by Datadog
Answer "who changed what" from Datadog Audit Trail — configuration-change forensics, API key compromise, cost-spike root cause, SOC 2/PCI evidence and AI activity audits.
Skill: Datadog APM
by Datadog
Install, instrument and analyse Datadog APM from an agent — Kubernetes and Linux Single-Step Instrumentation, service remapping, trace search and service maps.
Skill: Datadog Logs
by Datadog
Search Datadog logs from an agent and keep the bill under control — query syntax, exclusion filters, log-based metrics, archives and PII scrubbing.
Skill: Datadog Monitors
by Datadog
Create and audit Datadog monitors from an agent via the pup CLI — with alerting rules that stop the usual flapping, unscoped and unowned monitors.
Skill: Netlify Deploy
by Netlify
Netlify's official deploy skill: netlify.toml deploy contexts and their precedence, CLI and drag-and-drop deploys, Deploy Previews, build hooks, skew protection, and secrets-scanning build failures.
Skill: Elasticsearch ES|QL
by Elastic
Elastic's official skill for writing and running ES|QL - the piped Elasticsearch query language - covering schema discovery, query patterns, error handling and result formats.
Skill: PromQL Query Patterns
by Grafana Labs
Grafana's official PromQL skill: write, validate, and optimise Prometheus queries, and hunt down the label that blew up your cardinality.
Skill: GitHub Actions Security Review
by Sentry
Audit GitHub Actions workflows for the exploitation patterns that leak secrets or allow code execution from a fork.
Skill: Deno Deploy
by Deno
Deploy Deno applications to production on Deno Deploy — CLI workflows, environment config, KV, and custom domains.
Skill: Hugging Face Spaces
by Hugging Face
Deploy and maintain applications on Hugging Face Spaces — SDK choice, GPU hardware, model loading, and debugging.
Skill: Wrangler CLI
by Cloudflare
Cloudflare's CLI reference skill — correct Wrangler commands for deploying and managing Workers and every binding.
Skill: Vercel Optimize
by Vercel
Vercel's official optimization skill: collects real production metrics first, then returns ranked, citation-checked cost and performance fixes.