Agent skills

DevOps & Cloud skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
1,266 found
625672 · page 14 / 27
microsoft-foundryUse this skill to work with Microsoft Foundry (Azure AI Foundry): deploy AI models from catalog, build RAG applications with…majiayu000microsoft-skill-creatorCreate agent skills for Microsoft technologies using Learn MCP tools. Use when users want to create a skill that teaches agents…githubmicrosoft-skill-creatorCreate agent skills for Microsoft technologies using official documentation. Use whenever the user wants to build, generate, or…MicrosoftDocsmistral-prod-checklistExecute Mistral AI production deployment checklist and rollback procedures. Use when deploying Mistral AI integrations to…jeremylongshoremistral-prod-checklistExecute Mistral AI production deployment checklist and rollback procedures. Use when deploying Mistral AI integrations to…majiayu000mlflowMLflow is an open-source platform for managing the machine learning lifecycle, including tracking, packaging, and deploymajiayu000mlops-advancedImplement advanced MLOps practices for production ML systems. Use for: building CI/CD pipelines for ML models, implementing…majiayu000mlops-engineerExpert in Machine Learning Operations bridging data science and DevOps. Use when building ML pipelines, model versioning, feature…majiayu000model-registryCentralized model versioning, staging, and lifecycle management. Activates for "model registry", "model versioning", "model…majiayu000model-servingDeploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2) creating…majiayu000model-serving-kubernetesDeploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary deployments…majiayu000navan-deploy-integrationUse when deploying Navan integrations with ERP systems (NetSuite, Sage Intacct, Xero), HRIS platforms (Workday, BambooHR), or…jeremylongshorewritesoktkLLM Token Optimizer - Reduce AI API costs by 60-90%. Compresses CLI outputs (git, docker, kubectl) before sending to…majiayu000ollamaDeploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents.Prism-Shadowonenote-deploy-integrationDeploy OneNote integrations with MSAL token persistence, health checks, and container best practices. Use when containerizing…jeremylongshorewritesonenote-local-dev-loopSet up a local development loop for OneNote integrations with mock Graph API responses. Use when developing OneNote features…jeremylongshorewritesopen-forgeSelf-host any open-source app on the user's own infrastructure (cloud VM, VPS, Raspberry Pi, localhost, k8s, PaaS). Walks the…zhangqi444oraclecloud-ci-integrationConfigure CI/CD pipelines for OCI with Terraform and GitHub Actions. Use when setting up automated infrastructure deployments…jeremylongshorewritesoraclecloud-deploy-integrationDeploy containers to OCI using OKE (Kubernetes) or Container Instances. Use when deploying applications to Oracle Cloud, pushing…jeremylongshorewritesoraclecloud-migration-deep-diveMigrate workloads from AWS or Azure to OCI \u2014 IAM translation, networking\ \ mapping, compute image import, and data…jeremylongshorewritesoraclecloud-reference-architectureStandard 3-tier OCI reference architecture with VCN, subnets, gateways, load balancer, compute, and Autonomous DB. Use when…jeremylongshorewritesoraclecloud-upgrade-migrationSafely upgrade OCI Python SDK and Terraform provider \u2014 version\ \ pinning, breaking change detection, and rollback.\nUse…jeremylongshorewritespave-envSet up local development environments — devcontainers, Docker Compose, one-command setup, dev/prod parity. Use when asked to "set…jeremylongshorewritespave-goldenDefine a golden path — the opinionated, supported way to do a common developer task (create a new service, set up an environment…jeremylongshorewritespipeline-atacseqExecute ENCODE ATAC-seq processing pipeline from FASTQ to peaks and signal tracks. Child of pipeline-guide. Provides…majiayu000pipeline-chipseqExecute ENCODE ChIP-seq processing pipeline from FASTQ to peaks and signal tracks. Child of pipeline-guide. Provides…majiayu000portaljs-deployDeploy a PortalJS portal to PortalJS Arc — Datopian-managed static hosting on Cloudflare. Builds a static export, uploads it, and…datopianwritesqodo-pr-resolverReview and resolve PR issues with Qodo - get AI-powered code review issues and fix them interactively (GitHub, GitLab, Bitbucket…nanocoairdsAWS RDS relational database service for managed databases. Use when provisioning databases, configuring backups, managing…itsmostafarecommendation-systemDeploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low latency…majiayu000recommendation-systemDeploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low latency…majiayu000relay-deploySet up a complete deployment configuration — Dockerfile, deployment manifest, environment config, and rollback procedure. Use…jeremylongshorewritesrelay-shipEnd-to-end ship workflow — merge base, run tests, review diff, bump version, commit, push, create PR. Use when asked to "ship"…jeremylongshorewritesretellai-deploy-integrationRetell AI deploy integration \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice…jeremylongshorewritesrun-experimentDeploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to…majiayu000writesrun-experimentDeploy and run ML experiments on local or remote GPU servers. Use when user says \"run experiment\", \"deploy to server\"…majiayu000s3AWS S3 object storage for bucket management, object operations, and access control. Use when creating buckets, uploading files…itsmostafaseldon-model-deployerSeldon Core deployment skill for model serving, A/B testing, and canary deployments on Kubernetes.a5c-aiwritesseo-traffic-diagnosisDiagnose organic traffic changes (drops, stalls, or unexpected wins) using Ahrefs MCP plus Search Console data. Use this skill…rampstackcoserverless-modalRun GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto…majiayu000writesserverless-modalRun GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto…majiayu000writessignal-partyParallel metrics collection using G-6 SIGNAL. Deploy 6 probes to gather metrics from all sources for data-driven decisions.majiayu000smithy-sdk-generatorAWS Smithy-based SDK generation for enterprise-grade APIsa5c-aiwritessnsAWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message…itsmostafasof-partyRapid cross-domain assessment using 18-series SOF Operators. Deploy 7 probes for immediate situational awareness before task…majiayu000speak-deploy-integrationDeploy Speak language learning features to Vercel, Cloud Run, or containerized environments. Use when implementing deploy…jeremylongshorewritessqsAWS SQS message queue service for decoupled architectures. Use when creating queues, configuring dead-letter queues, managing…itsmostafastep-functionsAWS Step Functions workflow orchestration with state machines. Use when designing workflows, implementing error handling…itsmostafa
← Prev14 / 27Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going