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.
-
ellmos-ai Bundle AI Portable SetupErstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.
-
ellmos-ai Bundle Cloud Communication ProtocolsDach-Skill für Cloud-gestützte Kommunikationsprotokolle zwischen Agenten auf unterschiedlichen Maschinen (Ping-Pong, agent-beam, Listener und künftige Protokolle). Nutzen, wenn Arbeit über Maschinen hinweg per gemeinsamem Sync-Ordner oder Message-Yard koordiniert wird.
-
wyre-ai Skill Pax8 ProductsThe Pax8 product catalog: cloud software SKUs, vendors, pricing tiers and margins, and provisioning details across Microsoft 365, Azure, security tools, and backup products.
-
wyre-ai Skill Hubspot DealsHubSpot deal records and sales pipelines: deal fields, default and custom pipeline stages, deal amount conventions (MRR vs. TCV), forecast categories and weighted forecasting, and associating deals with contacts and companies.
-
wyre-ai Skill Azure MCP ObservabilityThe read-only observability half of the azure-mcp connector — the monitor, resourcehealth, applens, and advisor namespaces: Azure Monitor metrics, Log Analytics KQL, alert-rule state, platform health states, AppLens detectors, and Advisor recommendation categories, plus the degraded-resource investigation order.
-
wyre-ai Skill Sentinelone InventorySentinelOne's unified asset inventory across four surface types — agent-managed endpoints, AWS/Azure/GCP cloud resources, AD/Entra identities, and Ranger-discovered network devices. Covers the read-only inventory tools, the REST (not GraphQL) offset-pagination and filter model, asset field reference, and agent-coverage audit workflows.
-
wyre-ai Skill Cloud Cost ManagementCloud spend anomaly detection and reclaimable-spend hunting on whatever platforms (Azure, DigitalOcean) are connected: the signals that make a spend increase an anomaly rather than expected cost, the per-platform orphaned/idle resource catalog (unattached storage, idle load balancers, stopped-but-not-deallocated compute, idle managed databases, orphaned network resources), and how to build a monthly cost trend view — or a clearly labeled inventory-and-list-pricing estimate when a platform exposes no billing data.
-
wyre-ai Skill Inforcer Tenant ManagementInforcer's managed Microsoft 365 tenant list and the resolution step that turns a friendly name, DNS domain, or Azure AD GUID into the integer Client Tenant ID. The starting point for almost every Inforcer workflow, since alignment, secure score, identity, and audit calls are all tenant-scoped.
-
wyre-ai Skill Azure MCP Cost And CapacityThe read-only cost and capacity half of the azure-mcp connector — the pricing, quota, subscription, and group namespaces: retail meter-rate lookups, quota and usage headroom, subscription and resource-group inventory, and the retail-versus- actual-billing distinction that shapes every estimate.
-
wyre-ai Skill Salesbuildr OpportunitiesSalesbuildr opportunities: pipeline search, opportunity creation, stage updates, and deal values, plus how opportunities link companies and contacts to potential revenue.
-
wyre-ai Skill Sentinelone Threat HuntingPowerQuery against the Singularity Data Lake: the Scalyr-based pipeline syntax (distinct from SPL, SQL, KQL, and Elasticsearch DSL), the powerquery, get_timestamp_range, and iso_to_unix_timestamp tools, time-range and row-limit handling, common hunting scenarios, and the Purple AI generation path.
-
wyre-ai Skill Sentinelone MisconfigurationsCloud security posture findings from SentinelOne's XSPM module across AWS, Azure, GCP, Kubernetes, identity providers, and infrastructure-as-code. Covers the read-only misconfiguration tools, view types, severity and status values, compliance-standard and MITRE ATT&CK mappings, evidence fields, and remediation guidance.
-
fabioc-aloha Bundle KqlKQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.
-
fabioc-aloha Skill Skill CreatorCreate effective skills for AI agents — Azure SDK patterns, progressive disclosure, acceptance criteria, test scenarios
-
fabioc-aloha Skill Sse StreamingPOST-based Server-Sent Events streaming for Azure Functions — HTTP streaming, chunked response parsing, reconnection
-
fabioc-aloha Bundle Text To SpeechCloud TTS via Replicate — 15 models, voice cloning, emotion control, and multi-language support
-
fabioc-aloha Skill Book PublishingMarkdown-to-PDF pipeline via Pandoc and LuaLaTeX with emoji rendering, dual output, and print-ready formatting
-
fabioc-aloha Skill Sales EnablementSales methodology, pipeline management, negotiation frameworks, and customer engagement patterns.
-
fabioc-aloha Skill Bicep Avm MasteryAzure Verified Modules (AVM), Bicep best practices, and MCP-powered infrastructure as code for Azure
-
s3yed Skill Mission ControlDeploy, configure, and troubleshoot Mission Control (OpenClaw/Appie fleet dashboard). Use when setting up MC, fixing access issues, or managing gateways.
-
s3yed Skill Fleet Infra FixesResolve recurring Appie fleet infrastructure issues including Node/Homebrew breakage, pnpm install blockers, deploy keys, secrets, browser auth, Tailscale serve, and local model routing.
-
s3yed Skill Vercel DeploymentDeploy static sites and frontends to Vercel — handles both CLI and REST API paths, including the CLI token sanitization workaround.
Audited -
s3yed Skill Whatsapp PipelineUse when managing Ibrahim's WhatsApp lead pipeline — monitoring wacli, checking GHL leads, sending Typeform follow-ups, or generating daily pipeline overviews. Covers the full giveaway-to-client funnel oversight.
-
s3yed Skill Agentic Video ToolsCompare and integrate agentic short-form video editing SaaS tools and OSS alternatives for the Weblyfe Content Factory pipeline. Use when Appie-2 needs to automate: raw clip → Reel/Short/TikTok with captions/SFX/music/transitions → publish to IG/TikTok/YT with zero human editor in the loop. Covers automation depth ranking, API integration recipes, OSS alternatives, and anti-patterns.
-
s3yed Skill Lia Content PipelineCanonical Lia Smeraldi content generation pipeline running on Spark Atlas DGX. Use when the task is to generate, regenerate, batch, inpaint, upscale, or QA any Lia content (Tier 0 SFW, Tier 1 suggestive, Tier 2 explicit). Enforces bible identity lock + ReActor face-swap + Lia LoRA + ADetailer + iPhone aesthetic post-process.
Audited -
s3yed Skill Landing Page WorkflowsBuild, duplicate, and deploy landing pages for Ibrahim Ramzy's coaching funnels. Covers copy patterns, asset linking, Vercel deployment, and client-specific design preferences.
Audited -
s3yed Skill Knowledge Pipelineknowledge-pipeline Skill
-
s3yed Skill Branded Reel PipelineUse when producing a PREMIUM short-form BRAND reel end to end with real on-brand visuals and (optionally) live dashboard/analytics data baked in — e.g. 'make a branded reel', 'cut a premium reel for <brand>', 'turn this dashboard into a reel', 'make an analytics reel', 'reel from the Content Factory brief', 'show our real numbers in a 9:16'. The reusable framework + presets + scripts: script → Higgsfield visuals + music → ElevenLabs VO → Playwright live-data capture → Remotion brand-preset assembly → MP4 + ffprobe verify. Runs gated (human approves script, then assets, before final render) or auto. This is the premium-reel LAYER on top of short-form-video-production; do not duplicate that skill — cross-reference it for ideation/hook/retention craft.
-
s3yed Skill Client Orgo ProvisioningProvision a Weblyfe client bot from scratch: Orgo machine + Hermes + GitHub deploy keys + Telegram gateway.
-
s3yed Skill Drive Knowledge IngestionDrie-fase knowledge pipeline: Drive scanning → document text extraction → SQLite FTS5 knowledge base → entity extraction (heuristics) → knowledge graph → Neo4j export → realtime dashboard. Disk-safe: media wordt alleen metadata, documenten download naar temp en verwijderen direct. Ontworpen voor 8GB+ constraints.
-
s3yed Skill Crm Reactivation CampaignsAudit stale CRM pipeline data, tier leads by stage and contact coverage, build giveaway-anchored re-engagement campaigns, write tiered DM scripts for a setter, write email sequences, and tag/move leads via CRM API. For coaching/agency/client-acquisition businesses using GHL or similar CRMs.
-
s3yed Skill Never Relay Uncaptured OutputGuard-rail against fabricating or relaying command output, URLs, tokens, deploy status, or API data that was not literally captured from a real tool call in this session. Born from a recurring fabrication loop (2026-05-30) where a session claimed successful Vercel deploys and Brevo API responses without real tool output. Use whenever you are about to relay a result to the user or report a task as complete.
-
s3yed Bundle Research Paper WritingEnd-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.
-
s3yed Skill Ad Creative Analyze WinnerAnalyze a proven-winning ad image and produce a structured creative brief with a PROMPT 2/PROMPT 3/BOTH recommendation and a STRONG/WEAK text-angle score. This is always the first step of the ad-creative-variations system (see that skill for the full pipeline) — every later step depends on this brief verbatim.
-
dojogenesis Skill Gap Audit Then FixSpec-to-fix pipeline: audit a codebase against its specification, classify gaps by severity, fix in parallel, track in GAPS.md registry. Use when a spec exists but implementation completeness is unknown.
-
ryan-brosas Bundle Cap FoundationUse when building a screen-recording pipeline: multi-track studio recording actor (pause/resume segmented), crash-safe fragmented MP4 recovery with manifest ladders, browser MediaRecorder spooling, streaming multipart upload with uncertain-completion semantics, getDisplayMedia retry ladders, and VFR-safe duration/sync invariants.
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 ai-portable-setup, cloud-communication-protocols, Pax8 Products. 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.