DevOps & Infra
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.
-
nhouseholder Skill Engram SaveALWAYS ACTIVE on Cloud Agents. Save decisions, conventions, and finished work to the existing Engram MCP (mem_save / mem_session_summary) so other agents can mem_search them. Do not wait for /wrap-up. If the Engram namespace is error, say so.
-
nhouseholder Skill Tailscale CloudALWAYS ACTIVE on Cloud Agents. Join the tailnet in userspace, reach JobHub on nicholass-imac, fix Cloud git extraheader, use GitHub and Cloudflare APIs already injected. Do not print secrets. Do not wait to be asked.
-
wolski Skill Mixed R Python PipelineThis skill should be used when the user asks to "create a CLI tool from a Snakemake project", "make a pipeline deployable", "wrap a workflow as a pip package", "turn an analysis into a reusable tool", or "package a Snakemake workflow". Also use when the user has a working Snakemake + R/Python analysis project and wants to make it pip-installable with init, validate, update, clean, and info commands — even if they do not explicitly mention CLI packaging.
-
anubisrooster Skill Gitlab SkillUse this skill for GitLab repository operations that should be performed consistently across teams: creating and updating files, branching strategy, merge request workflows, and repository standardization tasks. Also covers publishing/synchronizing Cursor skills across the LATC GitLab repo, the GitHub mirror, and the Confluence skills catalog. Apply when users ask to publish skills, sync operational docs, open MRs, push a SKILL.md to GitLab/GitHub, or automate codebase updates in self-hosted or cloud GitLab.
-
anubisrooster Skill Jira Create Issues 2Create Jira Epics/Features and child sprint issues via mcp-atlassian. Default target is self-hosted Jira Data Center (`user-mcp-atlassian`) with a mandatory field set (Summary, Description, Epic Link/Parent Link, Estimate, Components, Labels, Function area, Business Value, Acceptance Criteria, Definition of Ready, Definition of Done) and hierarchical WBS numbering (Initiative X.0 -> Epic/Feature X.Y -> Story/Task/Test/Defect X.Y.Z). Business Value/AC/DoR/DoD live in dedicated custom fields ONLY for every issue type; exceptions are Business Value on Task and all four on Sub-task. Also covers Jira Cloud Premium trial (`user-mcp-atlassian-cloud`) with different field IDs and no DC WBS/governance contract unless the user asks. Enforces pillars=components, teams=labels, programs=initiatives. Always show the proposed payload for approval before creating. Use when the user asks to create, draft, file, scaffold, or open a Jira Epic, Feature, Story, Task, Test, Defect, or sub-task.
-
anubisrooster Bundle Infra Leadership SyncWeekly Infrastructure Leadership Sync notes for LATC. Runs as a Windows Scheduled Task every Wednesday at 3:00 PM Eastern. Uses the Cursor SDK (model grok-4.6) to scrape Jira Operations & Infrastructure, publish a dated Confluence notes page under the Infrastructure Leadership Sync hub, and point the hub Latest notes link. Use when setting up, troubleshooting, or changing the sync page format, schedule, or leadership filter.
-
anubisrooster Bundle Scheduled Status ReportAutomated weekly LATC pillar status reports (Ops & Infra, Evaluation, Models). Runs as a Windows Scheduled Task every Monday at 9:00 AM Eastern — uses the Cursor SDK (model grok-4.6) to query Jira for Done issues in the last 7 days, publish a detailed Confluence report with native chart macros, and publish a decision-grade condensed Weekly Pillar Update (so-what pulse, Good/Watch/Bad workstreams, concrete risks/asks). Use when setting up, troubleshooting, or changing the automated weekly status report format or schedule.
-
stacksjs Skill Stacks Deploy 3Use when deploying a Stacks application — the deployment workflow (build → deploy), pre/post deploy hooks, server vs serverless mode selection, first-time deployment setup, deployment troubleshooting, or the buddy deploy command. For cloud infrastructure details (EC2, Lambda, CloudFormation, Route53, IAM), see stacks-cloud.
-
foryourhealth111-pixel Bundle Clinical ReportsWrite comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.
-
foryourhealth111-pixel Bundle Latchbio IntegrationLatch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
-
migoxlab Bundle Mse Nacos CLIGet or publish Nacos / Alibaba Cloud MSE config by DataId using a small Go CLI. RAM auth from a local JSON keyed by host:port; publish only from a file produced by get then edited. CLI reads flags only (no process env). Needs Go 1.21+ and python3 for helpers. Copy skill dir into your agent's skills root per vendor docs.
-
pollyglot Skill Gplay SigningEnroll an app into Play App Signing with a self-hosted Cloud KMS key, or rotate to a new KMS key, with gplay `signing`. Use only when the organisation must keep signing-key custody in its own Cloud KMS (compliance or policy); standard Google-managed Play App Signing has no API and stays in the Play Console.
-
pollyglot Skill Gplay RecoveryDrive Google Play app recovery actions with gplay `recovery`, the incident-response remediation that force-updates users stuck on a bad release to a safe version. Use when a shipped build is broken and you need to push affected users off it, or to inspect and steer an existing recovery (deploy, widen targeting, cancel).
-
initializ Skill K8S Incident TriageRead-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
-
initializ Bundle K8S Pod RightsizerAnalyze Kubernetes workload metrics and produce policy-constrained CPU/memory rightsizing recommendations with optional patch generation and rollback-safe apply.
-
initializ Bundle K8S Cost VisibilityEstimate Kubernetes infrastructure costs by querying cluster node, pod, PVC/PV, and LoadBalancer data, applying cloud pricing models, and producing cost attribution reports with storage and LoadBalancer cost tracking, grouped by namespace, workload, node, label, or annotation.
-
initializ Skill K8S Incident Triage 2Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
-
shoji9x9 Bundle AWS Architecture Diagram 2AWS 構成図を spec(ノード・エッジ・グループの配列)から SVG として生成・更新するスキル。IaC(AWS CDK / Terraform / CloudFormation 等)や説明を情報源に spec を起こし、環境(prod / staging / local 等)ごとに出し分け、PNG にラスタライズして作図ルール(交差最小・直交配線・軸整列・ラベル可読)で目視確認しながら反復する。初回は `setup` で対話的に導入(配置・アイコン取得・環境確定・初期作図)、以降は `update` で生成する。描画エンジン・環境レジストリ・render/preview・AWS アイコン取得を starter kit として同梱。「AWS 構成図を作って」「アーキテクチャ図を SVG で描いて」「構成図を更新して」「CDK/Terraform から構成図を」「aws-architecture-diagram setup」や、環境別の構成図を作りたい依頼で発動する。手描き GUI ではなくテキスト差分で管理できる図を作る。
-
rysweet Bundle Azure Admin 3Azure Administration Skill
-
rysweet Skill Remote Work 2Execute amplihack work on remote Azure VMs with automatic region and resource selection
-
fusedio Skill Fused InfraReference for the infrastructure managed by fused — what resources exist, why each one is needed, and when they are created, updated, or deleted. Covers the AWS backend (IAM, Lambda, ECR, S3) and the local backend (data directories + venvs, see "Local backend infra"). Use when helping users understand, provision, or troubleshoot the resources that back an fused environment.
-
fusedio Skill Fused SetupStep-by-step guide for installing and setting up fused for the first time, including AWS credential checks, detecting an existing installation, provisioning infrastructure, and verifying the setup. Use when a user asks how to install, configure, or get started with openfused.
-
fusedio Bundle Fused StorageThe fused storage and secrets MCP tools — inspecting cloud-native datasets and managing secrets. Use when finding/listing/counting S3 objects, reading a Parquet/Arrow/CSV schema, minting a download URL, uploading content, or storing/reading/deleting secrets, via mcp__openfused__{list_files,count_files,get_file,get_file_schema,upload_file,get_secret,put_secret,list_secrets,delete_secret}. For running code over the data see fused-execute; for the equivalent CLI commands see fused-cli. If this is a step in building or running a project, load `fused-projects` first for the end-to-end model.
-
fusedio Skill Fused ProjectsThe canonical end-to-end guide for an agent driving Fused — pick an environment, create a project, decompose a task into UDFs, author specs and code, validate + commit, run/preview locally (often as a rendered widget), and deploy through preview to release. Code is authored by the driving agent (no codegen command, no API key); fused supplies validation, the spec↔code pairing hook, and run/deploy. Use to take a user request from prompt to a running, viewable result.
-
heypinchy Bundle Run Model EvalUse when running the Eval-v1 agent-reliability benchmark (packages/web/eval) — benchmarking a newly released Ollama Cloud model, re-running or adding scenarios, refreshing the published dataset in packages/web/eval/data/, or when a long sweep needs unattended keep-alive (watchdog), stalls, or produced suspicious/contaminated results.
-
heypinchy Skill Update Ollama Cloud ModelsUse when a new Ollama Cloud model is announced or available (e.g. an ollama-cloud email about a new GLM/Qwen/DeepSeek/Kimi/MiniMax version), when preparing a Pinchy release, or when the curated Ollama Cloud model list may have drifted from ollama.com.
-
managedcode Bundle Mcaf CI CD 3Design or refine CI/CD workflows, quality gates, release flow, and safe AI-assisted pipeline authoring. Use when adding or changing build pipelines, release stages, IaC-driven environments, or deployment rollback policy.
-
jawwad-ali Bundle DockerThis skill MUST be loaded when ANY Dockerfile, docker-compose.yml, docker-compose.override.yml, .dockerignore, or Docker-related configuration file is being read, reviewed, edited, or created. Also use when the user asks to "create a Dockerfile", "write a multi-stage build", "add a .dockerignore", "set up docker-compose", "containerize an application", "optimize a Docker image", "reduce Docker image size", "fix Docker build issues", "add health checks to containers", "set up a local dev environment with Docker", "create a multi-service setup", "debug container startup", "configure Docker volumes", "set up database containers", or mentions Dockerfile, Docker Compose, multi-stage builds, container images, build context, layer caching, ENTRYPOINT, CMD, docker-compose.yml, Docker health checks, or container orchestration for local development.
-
jawwad-ali Bundle Fastmcp DevelopmentThis skill should be used when the user asks to "create an MCP server", "build MCP tools", "add MCP resources", "create MCP prompts", "implement MCP protocol", "deploy MCP server", "create AI tools", "expose API as MCP", "build Claude tools", "create LLM tools", or mentions FastMCP, MCP server, Model Context Protocol, MCP tools, MCP resources, MCP prompts, or server composition.
-
jawwad-ali Bundle KubernetesThis skill MUST be loaded when ANY Kubernetes manifest file (.yml/.yaml) under a k8s/ directory is being read, reviewed, edited, or created — including Deployments, Services, ConfigMaps, Secrets, PVCs, HPAs, Namespaces, StatefulSets, Ingresses, or any resource manifest. Also use when the user asks to "create a Kubernetes deployment", "write K8s manifests", "add health probes", "configure liveness and readiness probes", "create a PersistentVolumeClaim", "set up a ConfigMap or Secret", "add an HPA", "create a K8s namespace", "write a StatefulSet", "expose a service with NodePort or ClusterIP", "set resource limits and requests", "add init containers", "configure envFrom with ConfigMap and Secret", "create a horizontal pod autoscaler", "debug pod startup issues", "fix CrashLoopBackOff", "troubleshoot ImagePullBackOff", "set up persistent storage for databases", "configure Redis persistence in K8s", "deploy a PostgreSQL StatefulSet", "add rolling update strategy", or mentions Kubernetes, K8s, kubectl, pods, deplo
-
lushows Bundle Canales LushowsUse when working on PAPER EMPIRES or any faceless documentary channel of Lushows — producing episodes (script, voice, visual script, collage montage, render), the visual language of the channel, the archive bank and its licensing, monetization and multi-language audio tracks, or the pipeline that turns a story into a finished video at zero cost. Triggers "Paper Empires", "canal de documentales", "historias de dinero", "el piloto", "el motor de montaje", "modo revista", "recortes de archivo", "guion visual", "locución del episodio", "pistas de idiomas", "canal faceless".
-
iliaal Bundle Terraform 2Terraform and OpenTofu configuration, modules, testing, state management, and HCL review. Use for "terraform module", "terraform test", "infrastructure as code", "IaC", "HCL", "tfvars", "terraform plan", "terraform apply", "OpenTofu", "tftest", or multi-environment patterns.
-
neuralblitz Skill Cloud 2Cloud computing, IaaS, PaaS, SaaS, and cloud-native development
1 -
neuralblitz Skill Cloud Native 2-----
1 -
netvar1337 Skill Graphics API HookingGuide for graphics API interception, overlay rendering, and render-pipeline analysis across DirectX, OpenGL, and Vulkan. Use this skill when working with Present or SwapBuffers hooks, DXGI swap chains, shader or draw-call interception, screenshot-sensitive overlays, or graphics debugging in game security research.
-
modsetter Skill PDFCreate polished PDF files for requests such as PDFs, resumes, CVs, reports, letters, one-pagers, and printable documents.
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 engram-save, tailscale-cloud, mixed-r-python-pipeline. Rankings shift as installs change; sort this page by "Most installs" 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@latest add <owner>/<name>, or copy the file into your agent's skills directory.