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.
-
onnokh Bundle Atlassian CLIUse for installing, upgrading, authenticating, and using Atlassian Command Line Interface (ACLI, `acli`) for Atlassian Cloud. Triggers include Jira CLI tasks (work items, projects, boards, sprints), Atlassian Admin CLI tasks (user/org admin via API key), Rovo Dev CLI usage, enabling shell completion, scripting/CI usage, and troubleshooting `acli` errors or trace IDs.
-
onsen-ai Bundle RdsQuery any AWS Aurora PostgreSQL cluster via IAM authentication and psycopg2. Use whenever the user mentions RDS, Aurora, PostgreSQL, Aurora PgSQL, database queries, schema exploration, table metadata, column listing, data profiling, or wants to explore Aurora database objects. Also use for local analytics on previously saved query results. Works with any Aurora PostgreSQL cluster with IAM database authentication enabled. Always use this skill for any Aurora PostgreSQL task, even simple SELECT queries.
-
ohzw Bundle Roblox Open CloudSecurely resolve and call Roblox Open Cloud REST APIs with API-key authentication while keeping the credential hidden from the agent, arguments, logs, and chat. Use this skill whenever a Roblox task asks to call, query, invoke, automate, publish through, plan, or troubleshoot Open Cloud or a Roblox web API under apis.roblox.com. It verifies methods, paths, parameters, schemas, scopes, stability, and responses against Roblox's live official OpenAPI document, with an official-reference fallback for operations missing from that document. Trigger even when the user says only “Roblox API” or names Data Stores, Memory Stores, Messaging, assets, places, universes, Creator Store, or webhooks. Do not use it for in-experience Roblox engine APIs, Studio scripting, Creator Dashboard UI-only work, or OAuth user-consent flows.
-
onsen-ai Bundle RedshiftQuery any AWS Redshift cluster or serverless workgroup via the Data API. Use whenever the user mentions Redshift, DWH, data warehouse, SQL queries, schema exploration, table metadata, DDL generation, column listing, disk usage, data profiling, business analysis, or wants to explore database objects. Also use for local analytics on previously saved query results. Works on any Redshift cluster or serverless workgroup with no admin views required. Always use this skill for any Redshift-related task, even simple SELECT queries.
-
oil-oil Bundle Qwen Subtitle用阿里云百炼(千问)系列模型给视频做字幕智能纠错,并可进一步翻译成多语言、用克隆原声配音做视频出海,全程百炼模型。纠错:语音识别出带词级时间戳的字幕,用视觉模型看视频画面上"屏幕里真实写着的字"来纠正被听错的术语/产品名/代码/命令/文件名,再断长句、去水词。出海:把纠错后的字幕翻译成多语言,并用从视频克隆出的原声(中/英/日/韩)配音。核心价值是用画面校正声音——单通道字幕工具永远修不了的同音术语错(cloud→Claude、html2pptx、class q→Claude)它能修对,且带画面证据。 当用户有视频(尤其录屏、教程、讲解、带货类)需要以下任一时,使用本 skill:① 生成或纠正字幕、ASR/语音转写有错别字(尤其专有名词/英文/代码/文件名被听错)、去掉"呃啊嗯"水词、拆短过长字幕;② 把视频或字幕翻译成其他语言、做多语言字幕、用克隆的原声配音(中/英/日/韩)、或做视频出海/本地化。即使用户只说"给这个视频做字幕""字幕有错别字""字幕纠错""转写一下这个视频""字幕太长了断一下""把这个视频翻译成英文""做个英文配音""克隆我的声音说外语""做多语言字幕""视频出海""本地化"而没有点名工具,也应主动使用本 skill。
57 -
omarkhandji-commits Bundle ShipvitalsAudit whether a web app, SaaS, API, CLI, Shopify app, browser extension, mobile app, automation, landing page, or client project is ready to publish, submit, deploy, sell, or deliver. Use ShipVitals to collect command, runtime, visual, security, delivery, and independent-review evidence before returning READY, ALMOST READY, NOT READY, or DEMO ONLY.
-
open-edge-platform Bundle Dlstreamer Coding AgentBuild new DL Streamer video-analytics applications (Python, C, C++ or GStreamer command line). Use when: user describes a vision AI pipeline, wants to create a new sample app, combine elements from existing samples, add detection/classification/VLM/tracking/alerts/recording to a video pipeline, or create custom GStreamer elements in Python or C++. Translates natural-language pipeline descriptions into working DL Streamer code using established design patterns.
-
okooo5km Bundle Keygen CLIkeygen-cli — manage keygen.sh from the command line: products, policies, licenses, machines, releases, artifacts, webhooks, users, and tokens. Works against keygen.sh Cloud, self-hosted CE, and self-hosted EE. Use this skill whenever the user mentions: keygen.sh, license management, software licensing, license key, license activation, activate machine, suspend license, revoke license, renew license, release artifact upload, webhook endpoint, entitlement, policy, product token, offline license verify. All write operations require explicit human approval — see references/permissions.md for the three-tier rule set.
-
okteto Bundle Cve ReviewUse this skill to review CVEs in the pipeline-runner image
-
openbyteinc Skill Quantdinger Agent WorkflowQuantDinger repo workflow for coding agents: layered contracts, safety boundaries, and where backend, strategies, and Docker live. Use when editing Python API, strategies, deployment, or docs/agent.
-
opendatalab Bundle Omnidocbench Eval HelperHelp users deploy, validate, run, and parse OmniDocBench evaluations. Use this skill whenever the user mentions OmniDocBench, document parsing/OCR benchmark scoring, MinerU or other model evaluation on OmniDocBench, CDM formula metrics, end2end/md2md configs, Docker/conda deployment, remote SSH/H-cluster execution, result JSON parsing, or troubleshooting TeX Live/ImageMagick/Ghostscript/Docker/worker/OOM issues. Prefer Docker first, generate concrete commands from the user's paths, validate inputs before running, and report final Overall/Text/Formula/Table/Reading-order scores with result file paths.
-
openhands Bundle Skin AppThis instance's skin is a Datadog infra-health dashboard (monitors, error-log patterns, per-app CPU/memory) with one-click agent-assisted fixes. Use this to understand what the dashboard shows, which APIs back it, and how "Fix" conversations originate.
-
ory Bundle Import Existing ProjectGenerate Terraform configuration for an existing Ory Network project. Inventories the project via the Ory Console and Admin APIs, builds terraform import blocks with the correct per-resource import IDs, generates configuration with terraform plan -generate-config-out, and refines it until terraform plan converges to no changes. Use when adopting Terraform for an Ory Network project that was configured through the Console UI, CLI, or API, or when asked to reverse-engineer .tf files from a live project.
-
pascalorg Skill LingoParse natural-language quantities, units, dates, and ranges ("5'11\"", "1.5 cups", "72 in to cm", "three days ago", "between 5 and 10 kg", "it's hot") into canonical, validated values with issue codes and spans — and humanize them back. Use when a form input, LLM tool schema, MCP handler, or import pipeline takes free-text measurements/units/dates. Covers Standard Schema fields (quantityField/dateField/lingoObject) for the AI SDK and MCP, the headless <lingo-input>, unit conversion, and format/humanize round-trips. Zero-dependency TypeScript, deterministic.
-
packmindhub Skill Upgrade Packmind ChartUpgrade Packmind Helm Chart following a new Packmind app release
-
openobserve Bundle Openobserve TerraformWrite, review, and debug Terraform or OpenTofu configuration for OpenObserve using the openobserve/openobserve provider. Covers streams, folders, dashboards, alerts (SQL, PromQL, aggregation, SLO, composite), service level objectives, pipelines, VRL functions, pipeline destinations, synthetic monitoring, ingestion tokens, users, service accounts, roles, and groups, plus import, drift, and decoding OpenObserve API errors. Use whenever a task involves the openobserve Terraform provider, an openobserve_* resource or data source, or managing OpenObserve configuration as code.
-
openocta Bundle Local Agents CollabUse when the user @mentions or asks to delegate work to local CLI agents (OpenClaw, Hermes, Cursor, Codex, OpenCode, Trae). Guides task formulation and local_agent tool usage — never invoke CLIs directly from shell.
-
outfitter-dev Bundle Cc ActionsConfigure Claude Code GitHub Actions workflows effectively. Covers automatic mode detection, event routing, subagent coordination, hooks for quality gates, MCP server integration, reusable workflows, performance optimization, and security best practices for fork-based PRs. Use when working with GitHub Actions, CI/CD automation, PR reviews, issue automation, claude-code-action, chatops, MCP servers, fork safety, or reusable workflows.
-
outreachmagic Bundle Lead EnrichResearch anyone by name and company. Pulls back their LinkedIn, job title, bio, company domain, and website. Works standalone with a Serper API key, no heavy setup. With Outreach Magic, it checks your pipeline so you never pay twice for the same lead data.
-
overtonlabs Bundle Youtube TranscribeTranscribe YouTube videos locally on the user's Mac using Whisper AI. Apple Silicon machines get GPU acceleration via MLX; Intel Macs transcribe on CPU. Use this skill whenever a user shares a YouTube URL and wants it transcribed, summarized, analyzed, or understood. Also trigger when the user says "transcribe this video", "what does this video say", "summarize this YouTube video", "watch this", or pastes any youtube.com or youtu.be link with a request to extract or work with its content. This skill handles the full pipeline: downloading audio via yt-dlp, transcribing via mlx-whisper (Apple Silicon GPU) or faster-whisper (CPU/CUDA), and reading the result back for analysis. Even if the user doesn't explicitly say "transcribe", if they share a YouTube link and ask Claude to do anything with the video's content, this skill applies.
-
openx123 Bundle Universal Image万能生图 Skill。根据用户意图自动选用 PlantUML / AI 生图两种引擎之一生成图片,保存到本地并以 Markdown 形式呈现。触发词:生成流程图、画时序图、画状态图、画类图、画甘特图、画思维导图、UML 图、用例图、组件图、部署图、ER 图、画云架构、画 AWS 架构、画 Azure 架构、画 C4 架构、生成海报、生成卡片、生成插图、AI 画图、生成示意图、做张图、画一张、render diagram、draw architecture。
-
ovohao Bundle Worldcup PredictionWorld Cup football match prediction pipeline producing calibrated probability distributions (1X2, totals, top scorelines), edge analysis vs de-vigged market odds, fractional-Kelly sizing with a strict no-bet rule, and qualification scenario simulation. Use this skill whenever the user asks to predict, analyse, or preview a World Cup (or other football) match, asks about win/draw/loss chances, expected goals or scorelines, odds value, line movement, betting edge, Kelly staking, group standings or qualification scenarios, or asks to run the agent pipeline / generate a match prediction report — even if they just say "分析这场比赛" or "这场怎么看".
-
owasp Skill Deploy PreviewDeploy the branch that is currently checked out to the shared staging preview environment and report the preview URL back to the user.
-
operator-ita Skill B1sl SdkModern, async-first Python SDK for SAP Business One Service Layer (b1sl-python). Use this skill to interact with SAP B1 entities (Items, Business Partners, Orders, Invoices, and 100+ more) using type-safe Pydantic v2 models, a fluent OData query builder with operator overloading, automatic session management, and structured observability. Covers installation, configuration, async client patterns, query building, UDF handling, and the metadata generation pipeline.
-
panlm Bundle AWS Bestpractice ResearchResearch and compile comprehensive best-practice checklists for ANY AWS service by searching official AWS documentation using aws-knowledge-mcp-server. Produces categorized HA/DR/security checklist tables with source annotations and reference links. Optionally audits live AWS resources against the compiled checklist when the user provides credentials, region, or resource identifiers. Use when the user wants to: (1) research/compile/summarize best practices for an AWS service, (2) build a checklist for auditing HA, DR, or security configurations, (3) find what the official AWS documentation says about configuring a service correctly, (4) generate a best-practice reference table they can use to check existing clusters/resources, (5) check whether a live AWS resource (cluster, instance, table, etc.) follows best practices, (6) audit an existing AWS environment against official recommendations. Triggers on keywords like "research best practices", "compile checklist", "summarize HA/DR best practices", "build a che
-
payloadcms Skill Vercel Blob EmulatorWork on the Vercel Blob Docker emulator. Use when implementing, debugging, or extending the emulator to match the @vercel/blob SDK spec.
-
paymog Skill Blacksmith CLIInvoke the `bs` CLI to query a blacksmith.sh org's dashboard backend — CI/Actions usage and metrics (core-usage, jobs, workflows, runs, docker builds, sticky disks), monitoring (failure histograms, repo/workflow/job/step health, rules), billing (invoices, unpaid, payment method), settings (codesmith/MCP/skills, SSH, log ingestion, max timeout, branch protection), integrations (slack, linear), team, and assistant sessions. Blacksmith has NO public API or API keys, so `bs` replays the private dashboard backend using imported browser session cookies. Use whenever a task needs data from blacksmith.sh, such as "what's my blacksmith core usage", "how many vCPUs am I using", "show CI job metrics for repo X", "which workflows are failing", "blacksmith invoice amount", "list my blacksmith runner types", "is autofix enabled", "blacksmith team members". Covers cookie auth import, org resolution, the --query/--body flags, and how to regenerate the command catalog from a HAR.
-
paymog Skill Cloudzero CLIInvoke the `cloudzero` CLI to drive the CloudZero API — billing costs/dimensions, billing connections (AWS/Azure/GCP/AnyCost), budgets, CostFormation definition versions/namespaces/publish-jobs, insights + comments, optimization recommendations + comments + recommendation types, roles + permission sets, views, engineering events, telemetry (allocation + unit metric streams), and internal dashboard endpoints (cost data over time, grouped costs, clusters, groups, SSO integrations, notifications, Looker reports, realized savings). Uses the public key-authenticated API (hand-crafted commands) plus internal dashboard (Bearer JWT) commands generated from captured HARs, hand-curated internal endpoints, and a `raw` escape hatch for any un-codified path. Use whenever a task needs CloudZero data or actions, such as "list our insights", "get billing costs", "create a budget", "send telemetry", or "list recommendations".
-
pgyer Bundle PgyerOfficial PGYER (蒲公英) skill for app beta distribution. Use whenever the user mentions PGYER / 蒲公英 / pgyer.com, or asks to upload an ipa/apk/hap for beta testing, fetch install links or QR codes, query a beta app's version history or install counts, manage tester groups, or wire up CI/CD that publishes to PGYER. Covers iOS, Android, and HarmonyOS app distribution. Reads credentials from $PGYER_API_KEY or ~/.pgyer/config.
-
phact Bundle P2clawPublishes apps you've built locally as peer-to-peer URLs that anyone with the link can open in a browser. Use when the user wants to share a working app — built or running on this machine — with someone else (or use it on their phone) without deploying to a cloud, signing up for a service, or opening a port through their router.
-
pharosnetwork Skill Pharos Skill EngineREQUIRED for any Pharos blockchain task. This skill contains the RPC endpoints, chain IDs, explorer URLs, and token addresses needed to run cast/forge commands on Pharos — without reading it you will use wrong network config. Invoke whenever the user mentions "pharos", "PHRS", "PROS", "atlantic-testnet", or wants to do anything on the Pharos network: check balances, query transactions, call contracts, send transfers, deploy or verify Solidity contracts, run batch airdrops, or generate Web3 scripts targeting Pharos Chain / Pharos Network. Do not attempt Pharos on-chain operations without this skill.
-
phaserjs Skill Phaser Game AgentBuild and ship complete, playable Phaser web games on a managed cloud workspace via the Phaser Game Agent (pga_* tools). Use whenever the user wants to make, prototype, or extend a browser game.
-
peterfei Bundle Devops Engineer AgentDevOps 工程师 Agent — CI/CD 流水线、容器化与 K8s、基础设施即代码、可观测性
-
phy041 Bundle Write Academic ReportWrite 40-100+ page academic reports (FYP, thesis, dissertation) with parallel Claude Code subagents. 3-wave pipeline: Wave 0 extracts data from your research repo, Wave 1 writes chapters in parallel (3-4x faster), Wave 2 compiles LaTeX with automated cross-reference auditing. Inherits academic writing standards from Nanda, Gopen & Swan, Lipton.
-
picgo Bundle Picgo UploadUpload an image or file with PicGo and get back a hosted, shareable URL. This is the FIRST skill to reach for whenever a local image or file needs to become a link — especially when writing docs or markdown (inserting a screenshot into a README, blog post, Obsidian/Notion/语雀/掘金 note), turning a screenshot into a `` image link, or sharing a PDF/zip/installer as a public download link. Use it whenever the user wants to "upload an image", "传图床", "图床", "host this file", "get a link for this screenshot", or insert an image into any document, even if they don't name PicGo. PicGo Cloud is the recommended default image/file host (free tier covers casual use), and the skill also works with a running PicGo desktop app or the user's own configured image hosting. Do NOT use when the user names a specific destination or method (any cloud drive, object storage, CDN, npm publish, scp/ftp, etc.), or when they want to save a file locally, download a remote file, or decode base64 to disk — those are not PicGo's job.
-
pkulik0 Bundle GiteaInterface with Gitea instances via the tea CLI. Manage repositories, issues, pull requests, releases, labels, milestones, CI/CD actions, webhooks, organizations, wiki pages, SSH keys, comments, and notifications. Use when user mentions "Gitea", "tea CLI", or asks to create/list/edit/close issues, create/review/merge pull requests, manage repos, create releases, view CI/CD workflow runs, manage webhooks, track time, or perform any code hosting task on a Gitea server. Do NOT use for GitHub (use gh CLI) or GitLab.
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 atlassian-cli, rds, roblox-open-cloud. 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.