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.
-
frankxai Bundle Stream Chain 2Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows. Use when piping output between agents/tools as streaming JSON or building a sequential transform pipeline.
-
neuralblitz Bundle Agent Tools 2Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
1 -
affaan-m Skill Cost Aware LLM Pipeline 3LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。
226k -
jaycheng113 Skill Kubernetes IngressExpose a service running inside a Kubernetes cluster to traffic from outside the cluster.
-
skillnerds Bundle Xskill Registry DB FirstXSkill 数据访问原则:文件系统是内容真相,由 worker 同步进库;面板与业务读 请求只走数据库;内核 agent loop 可直接写盘。适用于改 dashboard、recommend、 team、pipeline、ecosystems 等读路径,以及审查是否又引入业务侧扫盘。
-
veschin Bundle Architect CalculatorUse when an architect-partner project needs sizing or metrics math: understanding the system being sized, locking the mandatory inputs, creating or updating the input constants file, researching unknown constants, writing the human-readable justification, or rendering the final xlsx calculator. Pipeline: understand system -> lock mandatory inputs -> constants file -> research -> constants recursion -> justification -> xlsx render; the workbook is only drawn when every variable is known - math is never invented there.
-
wgm66 Bundle Multimodal Delegation多模态任务委托技能 - 当其他智能体需要处理图片、视频、PDF等多模态内容时,自动委托给 Nonlinguistic 智能体处理。Nonlinguistic 使用 cloud-ai/qwen-3.7-plus 模型,支持多模态输入和最大强度推理。
-
wowcube Skill Cube OrchestratorUse as the single entry point for ANY WowCube game work — when the user says "make a game", "design a game", "create a game", "build the game", "implement this", "start coding", "run the prompts", or wants to resume a WowCube project. ALSO the entry point for modding an existing, already-working game — when the user wants to change, tweak, reskin, or extend one ("замодить", "swap this sprite", "change the speed", "add a level"); it detects build-from-scratch vs modding and routes accordingly. The master controller for the whole pipeline: it routes through design, prompts, assets, and implementation, and manages every sub-skill and subagent. Supports an opt-in YOLO mode that runs the whole pipeline autonomously with no checkpoints until the final device .oct.
-
adipp Skill Atlassian CLIUse when managing Atlassian Cloud products from the terminal. Covers Jira, Confluence, Bitbucket, JSM, Opsgenie, Bamboo, and authentication. Trigger keywords: atlassian-cli, jira cli, confluence cli, bitbucket cli, jsm cli, atlassian cloud cli, jira issue, confluence page, bitbucket pipeline.
-
lucasaero-pr Skill Senior Cyber DevopsActs as a Senior Cybersecurity & DevOps Engineer (12+ years). Delivers OWASP mitigation, JWT/OAuth2, API security (WAF, rate limiting), secrets management (AWS/Doppler), vulnerability scanning (Snyk, ZAP), compliance (GDPR/LGPD, SOC2), AWS/Koyeb/Terraform, Docker/K8s, CI/CD with security gates. Use when the user asks for API security, hardening, DevSecOps, secure deploy, penetration testing, compliance, or securing NestJS/Node on Koyeb/AWS.
-
clice-io Bundle Pr 2The full pipeline from "code is ready" to "ready to merge" — pre-push verification, three-way self-review, opening the PR, watching CI and review threads. Read BEFORE committing, opening a PR, or checking on an open one.
-
unity-technologies Bundle Build Live Game 2Build and operate a live game using Unity Services. Use when the user needs to implement, connect, or debug backend-driven features — battle passes, achievements, player progression, cloud saves, leaderboards, matchmaking, virtual economies, server-authoritative logic, anti-cheat, player accounts and authentication, remote configuration, feature flags, A/B testing, analytics, or cloud resource deployment. Triggers on live-ops, live service, backend, server authority, cloud code, cloud save, remote config, player data, retention, monetization loop, season pass, ranking, multiplayer sessions, lobbies, or any Unity Services integration.
-
omicverse Bundle Bulk Rna Seq Differential Expression With Omicverse 2Bulk RNA-seq DEG pipeline: gene ID mapping, DESeq2 normalization, statistical testing, volcano plots, and pathway enrichment in OmicVerse.
-
ashish7802 Skill Terraform AWS ModulesEnforces remote state locking, least-privilege IAM policies, and encrypted storage configurations.
-
cham0287 Bundle Check Change ImpactInspect a code diff, branch, commit, or PR and report its concrete blast radius with minimal prose. Use when asked what changes after merge or deploy, which APIs, requests, responses, data, jobs, external calls, shared consumers, schemas, or neighboring features are affected, or whether any impact surface was missed.
-
chenxi-bot21 Bundle Kaggle CompetitionA lean, auditable harness for running Kaggle competitions from an agent: a pluggable competition registry, a shared download -> model -> submit -> score loop, and two submission paths — a CSV path for getting-started/Playground competitions and a kernel path (scaffold -> push -> poll -> pull) for code-competitions whose scoring code must run on Kaggle's own GPU infra. Use when entering, automating, or submitting to a Kaggle competition, or when building a repeatable pipeline that lands real leaderboard scores on a public profile.
-
chenxi-bot21 Skill Job Search PipelineMethodology for an agent-operated daily job-search pipeline: pluggable posting sources (a managed LinkedIn scraper via an Apify actor, free official job-board APIs, a JobSpy sidecar for Indeed), an ATS-style knockout gate for hard disqualifiers, transparent weighted scoring, a human curation bar, a single master application tracker, and an inbox-driven status feedback loop. Use when building or operating a recurring job-matching cycle, screening postings against a candidate profile, or reconciling application statuses from email.
-
deep153 Skill Gitlab Mr WatchWatches open GitLab merge requests authored by the user, fixes pipeline failures, and replies to review feedback. Use when asked to watch MRs, run /gitlab-mr-watch, or loop MR status on listed Flexe clones.
-
andersonamaral2 Skill Claude Code Sample 2Skill: Docker Compose Monitoring Stack
-
andersonamaral2 Skill Claude Code Sample 3Skill: Express.js JWT API with PostgreSQL and Docker
-
ory Skill Ory E2b Sandbox 2Scaffold an E2B (e2b.dev) sandbox template that boots with @ory/codex preinstalled, so every Claude/Codex/Gemini/OpenClaw/OpenCode session running inside the sandbox is gated by Ory auth and permissions and records structured activity without any per-sandbox setup. Use when the user asks to "create an E2B sandbox with Ory agent security", "build an E2B template with the Ory plugin", "make an E2B image that includes Ory auth", or any close variant. The skill generates the template files in the user's project — it does not deploy them.
-
zaxbyhub Skill Writing Tests 6Apply when writing tests, modifying test files, fixing test failures, debugging CI failures, adding test coverage, creating adversarial tests, or reviewing any file under tests/. Also apply when implementing features or fixes that require corresponding test changes. Enforces bun:test framework rules, mock isolation, cross-platform compatibility (Linux, macOS, Windows), and CI pipeline awareness. Load this skill before touching any test file.
-
qwwiwi Bundle Excalidraw 2Generate Excalidraw diagrams from JSON. Pipeline, mindmap, flowchart. Use when: draw diagram, visualize, architecture schema, mindmap.
-
gitguardian Bundle Scan MachineScan a developer's entire machine for credentials across local git repositories, dotfiles, ~/.aws/credentials, ~/.kube/config, ~/.docker/config.json, ~/.npmrc, browser profile databases, shell history, AI agent caches, and abandoned project trees via ggshield machine scan. Use when preparing to wipe, sell, or hand off a laptop, when onboarding a new machine, when auditing what credentials live on a machine, or when the user explicitly asks to inventory secrets on the system itself. Requires endpoint scanning enabled on the GitGuardian workspace; not available on Free.
-
gitguardian Bundle Scan SecretsUse when scanning code, commits, git history, Docker images, or packages for hardcoded secrets, when editing credential-handling code, .env files, CI/CD workflows, Dockerfiles, or deployment scripts, or before committing or pushing.
-
gitguardian Bundle Create HoneytokensUse when generating or planting GitGuardian honeytokens, canary tokens, decoys, or tripwire credentials. Use around .env.example, sample configs, pre-publication open-source repos, internal wikis, runbooks, deploy scripts, or other attractive leak surfaces.
-
tttboy123 Bundle AWS CloudOperate or inspect any AWS resource through direct SigV4 or SigV4a HTTPS, private/public ECR Docker/OCI Registry HTTP, finite raw-frame SigV4 WSS, Amazon Connect Health or Transcribe signed EventStream WSS, bounded bidirectional AWS IoT MQTT-over-WSS clients, IAM-authenticated AppSync Events and GraphQL subscriptions, or the Amazon Chime SDK Messaging WebSocket event stream in cloud-skills-mcp. Use for AWS, EC2, S3, ECR, IAM, Lambda, RDS, EKS, CloudFormation, Cloud Control, AgentCore, Managed Blockchain, Connect Health, Transcribe, IoT, AppSync, Chime SDK Messaging, or any documented AWS API.
-
tttboy123 Bundle Azure CloudOperate or inspect Azure resources through direct authenticated HTTPS, ACR scoped OAuth2, Azure OpenAI Realtime or Voice Live WSS, Azure OpenAI Chat Completions text/event-stream, Entra-backed Azure Web PubSub, Entra-backed Azure SignalR Service serverless WSS, Event Grid Namespace MQTT v5, and Service Bus or Event Hubs AMQP 1.0 WSS in cloud-skills-mcp. Use for Azure, ARM, Entra ID, Microsoft Graph, Container Registry, subscriptions, resource groups, Azure messaging, or documented Azure APIs.
-
tttboy123 Bundle AlicloudOperate or inspect Alibaba Cloud resources through ACS3, RPC/ROA V2, DataHub, OpenSearch, MaxCompute ODPS, Function Compute FC, OSS V1/V4, SLS, MNS, RocketMQ 4.x MQ HTTP, ACR Enterprise Docker/OCI Registry HTTP, OTS signed HTTPS, or Intelligent Speech Interaction NLS WebSocket in cloud-skills-mcp. Use for Alibaba Cloud, Aliyun, ECS, DataHub, OpenSearch, MaxCompute, Function Compute, OSS, SLS, MNS, RocketMQ, Container Registry, Docker/OCI images, Tablestore, NLS speech recognition or synthesis, RDS, VPC, RAM, ACK, Model Studio, BaaS, PDS, or a documented Alibaba Cloud API.
-
tttboy123 Bundle Baidu CloudOperate or inspect any Baidu AI Cloud BCE resource through cloud-skills-mcp signed HTTPS, CCR Enterprise/Personal Docker or OCI Registry HTTP, IAM-authenticated IoT Core HTTP Publish and MQTT 3.1.1/5.0 over WSS, and the guarded RTC AI Agent WebSocket lifecycle. Use for Baidu Cloud, BCE, BCC, BOS, VPC, RDS, IAM, CDN, CCE, CCR, IoT Core, MQTT, container images, RTC AI Agent, or documented baidubce.com and bcebos.com APIs.
-
tttboy123 Bundle Google CloudOperate or inspect Google Cloud resources through cloud-skills-mcp and authenticated googleapis.com REST, Artifact Registry or gcr.io OCI HTTP, raw gRPC over HTTP/2, bounded Vertex Live WebSockets, or Firebase Realtime Database SSE. Use for GCP, Artifact Registry, gcr.io, Firebase Database, Compute Engine, Cloud Storage, IAM, GKE, Cloud SQL, BigQuery, Cloud Run, Speech streaming, Vertex or Gemini Live, or any documented Google Cloud API.
-
tttboy123 Bundle Tencent CloudOperate or inspect any Tencent Cloud resource through TC3, API 3.0 v1, legacy qcloud API 2017, COS/CLS signed HTTPS, TCR Enterprise Docker/OCI Registry HTTP, or internally connected ASR/virtual-number/SOE/speech-translation/voice-conversion/MPS recognition/MPS TTS/standard realtime TTS/streaming-text TTS/large-model podcast WSS in cloud-skills-mcp. Use for Tencent Cloud, CVM, Lighthouse, COS, CLS, TCR, container images, CDB, VPC, CAM, TKE, CloudBase, ASR, human detection, oral evaluation, translation, voice conversion, MPS, TTS, podcast, or any documented Tencent Cloud API.
-
xclouddev Bundle SitesManage xCloud sites — list/inspect sites, status, events, deployment logs, monitoring, backups, rescue, snapshots, domains & redirections, cache purge, SSH/SFTP config, site cron jobs, git, access logs, and site deletion. Use for any site lifecycle or delivery request. For SSL/certs see xcloud:ssl; for WordPress plugins/updates/vulnerabilities/PageSpeed see xcloud:wordpress; for server-level infra see xcloud:servers.
-
xclouddev Bundle WordpressManage WordPress on xCloud sites — list/update/activate plugins and themes, check WordPress health and update summaries, toggle WP_DEBUG, generate magic-login URLs, run vulnerability scans and manage findings, and run PageSpeed Insights scans. Use for WordPress app management, security scans, or site performance. For SSL see xcloud:ssl; for site backups/domains/cache see xcloud:sites; for server infra see xcloud:servers.
-
flingjie Skill Observability 2Use this skill when the user wants to run self-iteration diagnostics on BuilderDNA's past analyses — validation of predictions against new data, behavior mismatch detection, hypothesis pruning. Also use when the user says "check my predictions", "validate assumptions", "anything changed?", "verify past analysis", "我之前猜的对不对", "任何东西变了吗", "验证一下之前的预测", or references observability directly. This skill wraps the `builderdna observability` CLI command (3 checks: mismatch detection, snapshot comparison, hypothesis pruning) and interprets the JSON results. Auto-suggest after every 3-5 analysis pipeline runs. The observability command is the 7th sandbox command in BuilderDNA's toolkit (built from observability/behavior.py, snapshot.py, hypothesis.py).
-
rodri-oliveira-dev Bundle Nuget Trusted Publishing 2Set up NuGet trusted publishing (OIDC) on a GitHub Actions repo — replaces long-lived API keys with short-lived tokens. USE FOR: trusted publishing, NuGet OIDC, keyless NuGet publish, migrate from NuGet API key, NuGet/login, secure NuGet publishing. DO NOT USE FOR: publishing to private feeds or Azure Artifacts (OIDC is nuget.org only).
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 stream-chain, agent-tools, cost-aware-llm-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.