DevOps & Infra Agent Skills
DevOps agent skills automate the delivery side of software: CI/CD pipelines, Dockerfiles, infrastructure as code, releases, and incident checklists. A skill gives your AI agent the exact runbook to follow, so deployments and configs come out consistent every time.
DevOps & Infra
2,864 skills
kensaurus deploy-npm
Release npm packages end-to-end: Changesets version bump, CHANGELOG update, GitHub Actions OIDC publish, and post-release verification. Use when the user says "release to npm", "publish this package", "ship a new version", "cut a release", "update the changelog", or combines a package name with a release verb.
8 · bundle
kensaurus deploy-verify
Post-deploy smoke test combining all 5 tools (Sentry + Supabase + Firecrawl MCPs, plus the Langfuse and Playwright CLIs) into one workflow. Use when asked to: "verify deploy", "post-deploy check", "smoke test production", "check if deploy is healthy", "ship or rollback", "post-release check", "verify release", "deploy.
8
kensaurus audit-infra-cost
Read-only audit of hosting, database, storage, egress, and serverless spend (Supabase, Vercel, S3/R2, edge). Use when "hosting bill is high", "cut infra costs", or a bill jumps. CI minutes → audit-cicd. Model tokens → plan-llm-cost-guardrails. Consumes test-load numbers.
8
kensaurus mushi-integration
Full end-to-end Mushi Mushi integration smoke test: bug capture → AI triage → story mapping → TDD test generation → approval → execution → PDCA cycle. Use when "test mushi integration", "verify full pipeline", "mushi e2e check", "does mushi work end-to-end", "smoke test mushi", or after deploying changes.
8
curiositech deploy
Cloudflare Pages and Workers deployment checklist for wrangler deploys, secret audits, D1 migrations, Worker-compatible SDK checks, and browser-auth verification. Use when shipping Cloudflare changes to production. NOT for general CI/CD architecture, non-Cloudflare deployments, or post-launch UX QA.
10 · bundle
curiositech helm-liang-2022
Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness
10 · bundle
curiositech gpui-rust-console
Build and extend pd-console — Port Daddy's GPU-native macOS operator console (GPUI 0.2.x, Zed's Rust UI). Covers the render-agnostic Block/Pane(Surface) contract, the two-thread reqwest↔smol refresh pipeline, Taffy flexbox layout, uniform_list virtual scroll, focus + keyboard nav, the OKLCH theme and ICS maritime flag badges, GPUI's missing text-input, and the real feature-gated cargo/CI gate. Use when adding panes, visual polish, or debugging GPUI rendering/layout/focus in core/pd-console. NOT for the TypeScript daemon, generic Rust toolchain/borrow-checker help (use rust-with-claude-code), or non-pd GPUI apps with a different theme/architecture.
10 · bundle
ziri22 agent-devsecops
DevSecOps IA — Expert en intégration sécurité dans les pipelines CI/CD (SAST, DAST, SCA, container scanning, compliance automation)
6
ziri22 aws-specialist-ia
Expert en infrastructure AWS (EC2, S3, Lambda, ECS, RDS, CloudFormation, CDK)
6
ziri22 gcp-specialist-ia
Expert en infrastructure GCP (GKE, Cloud Run, BigQuery, Pub/Sub, Firestore, Cloud Functions)
6
ziri22 agent-olympia-v2
Expert en orchestration de modèles IA (free cloud default, local fallback, routing, cost optimization)
6
ziri22 agent-serverless
Expert en serverless (AWS Lambda, Cloudflare Workers, Vercel Edge, cold starts, contexte DZ)
6
ziri22 azure-specialist-ia
Expert en infrastructure Azure (AKS, Functions, Cosmos DB, AD, DevOps, ARM templates)
6
ziri22 agent-devops-infra
DevOps & Infrastructure IA — Gère le VPS, Docker, déploiements, monitoring, sécurité, tunnels Cloudflare. Expert Hetzner + Coolify + self-hosting.
6 · bundle
tianhao909 mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
1 · bundle
tianhao909 modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
1 · bundle
tianhao909 skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
1 · bundle
tianhao909 torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
1 · bundle
tianhao909 nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
1 · bundle
tianhao909 lambda-labs-gpu-cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
1 · bundle
tianhao909 llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
1
tianhao909 prompt-guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
1
tianhao909 deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
1 · bundle
tianhao909 training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
1 · bundle
qcmuu mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
0 · bundle
qcmuu modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
0 · bundle
qcmuu skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
0 · bundle
qcmuu torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
0 · bundle
qcmuu nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
0 · bundle
qcmuu llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
0
qcmuu prompt-guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
0
qcmuu training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
0 · bundle
jackychenlu esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.
0 · bundle
jackychenlu mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
0 · bundle
jackychenlu draw-io
draw.io diagram creation, editing, and review. Use for .drawio XML editing, PNG conversion, layout adjustment, and AWS icon usage.
0 · bundle
jackychenlu inngest
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution.
0
Frequently asked questions
What are DevOps & Infra agent skills?
DevOps agent skills automate the delivery side of software: CI/CD pipelines, Dockerfiles, infrastructure as code, releases, and incident checklists. A skill gives your AI agent the exact runbook to follow, so deployments and configs come out consistent every time.
Which DevOps & Infra skills are most installed?
Popular DevOps & Infra skills on SkillMD right now include helm-liang-2022, deploy-npm, deploy. Rankings shift as installs change; sort this page by "Most downloaded" for the live list.
Do DevOps & Infra skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds add <owner>/<name>, or copy the file into your agent's skills directory.