DevOps & Infra

googlecloudplatform-generative-ai Bundle

Synthesizes and deploys complete, domain-specific Gemini Enterprise demo environments directly to Google Cloud. Use when the user asks to create an AI agent demo for any customer domain (e.g. 'example.com', 'example.co.jp', 'example.de', 'example.fr' - any company, any industry, any region) or business goal, generate realistic BigQuery/Firestore sample datasets, create external demo files (PDF, Excel, scanned images), stage them in Cloud Storage and upload them to the deploying account's Google Drive, scaffold ADK multi-agent architectures with MCP tools and A2UI cards, deploy to Cloud Run, publish to Gemini Enterprise, and generate 7 structured demo prompts in any language. Confirms the requirements interactively and presents a demo architecture & data model plan (Mermaid ER diagram, external file lineage, target project) for approval before anything is deployed. Also triggered by /ge-demo-generator.

pluginagentmarketplace Bundle

Secure backend applications against OWASP threats. Implement authentication, encryption, scanning, compliance, and incident response procedures.

wjgoarxiv Bundle

Universal shipping workflow: 8-phase linear pipeline from verification to deploy. Reads type-checklists.md to select the right checklist for the artifact type. The ONLY pause is Phase 7 (user confirmation before irreversible deploy/publish). TRIGGER when: user wants to ship, release, publish, or deploy something; user asks "is this ready to ship?"; user wants a pre-release checklist; user wants to publish a package, CLI, API, web app, ML model, skill, docs site, infrastructure, or research paper; user invokes /autoresearch:ship. DO NOT TRIGGER when: user wants iterative development (use autoresearch); user wants to debug errors (use autoresearch:fix); user just wants a code review.

sjdv1982 Bundle

Assesses whether an existing Python, bash, or hybrid pipeline is a good fit for Seamless (content-addressed caching, reproducible execution, local-to-cluster scaling). Triggers when wrapping scripts or functions without rewriting them, avoiding recomputation, comparing workflow frameworks (vs Snakemake, Nextflow, CWL, Airflow, Prefect), migrating a pipeline, or setting up remote/HPC execution. Covers direct/delayed decorators, seamless-run CLI, nesting, module inclusion, scratch/witness patterns, deep checksums, and execution backends (local, jobserver, daskserver). Provides safe guidance on remote execution and determinism — avoids naive "copy code to server" suggestions.

vibe-any Bundle

将本地静态网站或已构建前端项目发布到 Surge 或 Cloudflare Pages 的可移植部署 skill。

aws-sbg-at-the-university-of-kentucky Skill

Check AWS spend, cost, budget status, or "how much am I spending" using the FREE Budgets/CloudWatch APIs — never the paid Cost Explorer API. Use whenever a task involves inspecting AWS costs, budgets, month-to-date spend, forecasts, budget-action status, or verifying whether a budget/tripwire has been crossed. Cost Explorer (aws ce ..., ce:GetCostAndUsage) and the console cost widgets bill $0.01 per request — repeatedly querying them to "quickly check" a small budget can itself trip that budget.

aws-sbg-at-the-university-of-kentucky Skill

Research documented AWS patterns and existing solutions before recommending, comparing, or reviewing AWS architectures. Ask targeted follow-up questions to tailor decisions to the user's workload, budget, constraints, and operating model. Use for AWS service selection, design reviews, and architectural changes.

hairyf-skills Bundle

Veil is a rendering library for Minecraft mods (Fabric, Forge, NeoForge) that brings game-engine-level graphics to Java Minecraft: a full GLSL shader pipeline, JSON-driven framebuffers and post-processing, deferred lighting, data-driven particles and effects, procedural skeletal animation, and custom render types. Use these skills when adding shaders, post FX, lights, particles, animations, or custom render pipelines to a mod.

julianobarbosa Bundle

Azure DevOps Wiki Skill

pedronauck Bundle

Build investor lists, warm intros and cold emails; prepare meetings, manage a raise pipeline, and run diligence through close. vc-pitch-deck owns slides; vc-strategy owns round design, narrative, and terms.

syou6162 Skill

Devin CLIから /handoff でDevin Cloudにタスクを引き継ぐ際に発動。ハンドオフ先のDevin Cloudに対して、タスクの実行をCursor Cloud Agentに委譲するよう指示を含める。

pluginagentmarketplace Bundle

Game server deployment with Docker, Kubernetes, and global distribution strategies

agentfront Bundle

Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod schemas, E2E tests), an authenticated task manager (CRUD tools, Redis storage, OAuth, Vercel deploy, authenticated E2E tests), and a multi-app knowledge base (vector search, semantic resources, an AI research agent, audit logging). Triggers: tutorial, walkthrough, how do I build, getting started, end-to-end example, sample project, learn FrontMCP, full app example.

microsoft Bundle

Checks whether Azure Container App deployments comply with the organization's CI/CD-only deployment policy. Uses three signals: Activity Log caller identity, Docker image labels (tamper-proof), and resource tags. QueryLogAnalyticsByWorkspaceId

entityprocess Skill

This skill should be used when asked to "rollback a deployment", "revert services", or "undo deploy". Reads deploy-plan.md and reverses completed steps.

jochenyang Skill

Vercel Deploy Skill

erhankaraarslan Skill

Production deployment workflow. Testleri çalıştırır, build alır ve deploy eder.

fr-e-d Skill

Search local GAAI OSS project memory without using GAAI Cloud MCP tools.

ehtbanton Bundle

Generate Helm chart files for Kubernetes application deployment. Triggers on "create helm chart", "generate helm template", "kubernetes helm", "helm package".

openshift-eng Bundle

OpenShift Node team assistant. Covers kubelet, MCO, CRI-O, crun, conmonrs, Kueue operator, Jira (OCPNODE/OCPBUGS), Red Hat KB/support cases, Prometheus, and K8s/OCP docs. Triggers on OpenShift node-layer development, deployment, debugging, or team workflow tasks. For CVE/vulnerability triage, analysis, or reporting, defer to node-cve. For bug triage and assignment, defer to node-bug.

notque Skill

Formal 5-phase research pipeline with artifact saving and source quality gates: SCOPE, GATHER, SYNTHESIZE, VALIDATE, DELIVER. Parallel research agents mandatory (min 3). Saves findings to research/{topic}/ for future reference. Use for "research pipeline", "formal research", "research with artifacts".

v1truv1us-ai-eng-system Skill

Weekly research agent for

v1truv1us-ai-eng-system Skill

Daily research agent for

v1truv1us-ai-eng-system Skill

Daily research agent for

delorenj Bundle

Hub skill for any Cloudflare Workers platform task. Triages the request and routes to one or more specialized skills covering CLI/config (wrangler), Worker code authoring & review (workers-best-practices), stateful coordination (durable-objects), and AI agents on Workers (agents-sdk). Load when the user mentions Cloudflare, Workers, Pages, Wrangler, Durable Objects, KV, R2, D1, Vectorize, Hyperdrive, Queues, Workflows, Workers AI, the Agents SDK, MCP servers on Workers, or any deploy/dev/binding/observability task targeting Cloudflare's edge.

microsoftdocs Skill

Expert knowledge for Azure Quotas development including limits & quotas. Use when requesting per-region Storage account quota increases, checking limits, or filing Azure support requests, and other Azure Quotas related development tasks. Not for Azure Cost Management (use azure-cost-management), Azure Monitor (use azure-monitor), Azure Policy (use azure-policy), Azure Resource Manager (use azure-resource-manager).

microsoftdocs Skill

Expert knowledge for Azure Reliability development including best practices, decision making, architecture & design patterns, and limits & quotas. Use when choosing Azure regions, zone-resilient deployments, AKS/DB HA, Queue Storage limits, or Web PubSub scale, and other Azure Reliability related development tasks. Not for Azure Resiliency (use azure-resiliency), Azure Service Health (use azure-service-health), Azure Monitor (use azure-monitor), Azure Site Recovery (use azure-site-recovery).

microsoftdocs Skill

Expert knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with Entra auth, AI Gateway, BYO VNet, M365 publishing, or Foundry IQ retrieval, and other Microsoft Foundry related development tasks. Not for Content Safety in Foundry Control Plane (use azure-content-safety), Azure Content Understanding in Foundry Tools (use azure-content-understanding), Azure Speech in Foundry Tools (use azure-speech), Microsoft Foundry Classic (use microsoft-foundry-classic).

pixartseu Bundle

Docker MCP - gestione container Coolify, debug log, ispezione deployment, monitor risorse

0nate4 Skill

Thin SDD finish pipeline: merge main into feature branch, typecheck then tests, Bugbot plus path-scoped security review, fix loop, push, create or update GitHub PR, remove git worktree. Use after sdd outside-voice passes, with sdd, or when the user says sdd-ship or ship the SDD branch.

aleksej-shherbak Bundle

Verifies .NET solutions end-to-end: build, unit tests, docker-compose, OpenAPI analysis, curl smoke tests, and ai-e2e-tests scenario execution. Discovers all Web API projects in the solution. Use when the user invokes /dotnet-tester, asks to verify a project works, run E2E checks, smoke test APIs, or validate docker-compose and test scenarios.

aleksej-shherbak Bundle

Enforces Clean Architecture for .NET 10: 4-project layout (Domain, Application, Infrastructure, Api), dependency inversion, MediatR handlers with pipeline behaviors, rich domain entities with invariants and encapsulation, Dapper + PostgreSQL persistence, classic ASP.NET Core controllers, multistage Dockerfile and docker-compose. Use when scaffolding, refactoring, or reviewing .NET backends, layered architecture, CQRS, MediatR, Dapper, PostgreSQL, Docker, or Clean Architecture.

greatmark Skill

Get an independent Codex review via the codex CLI (no MCP). Use for code review of uncommitted changes / a branch / a commit, adversarial design review, or a second opinion on any high-risk conclusion (data/pipeline logic, metrics, security, irreversible ops). Trigger words - codex review, second opinion, adversarial review, 让 codex 审, 二次意见, 对抗审查.

marbytebeep Bundle

Continuous quality fix loop. Reads .agents/skills/finalize/pipeline.json (from finalize postinstall). Runs every script in pipeline.preflight[], then repeatedly executes all configured loop[] phases according to their loop semantics until the pipeline is green. Communication style follows pipeline.communication ({{communication}}). Use only when the user invokes /finalize.

omayka-tech Skill

Runs Lumi ERP tests and git/worktree work the factory way: Docker-only pytest via official wrappers, never host Python; Fusion worktree vs runtime clone; Conventional Commits; no auto-merge. Use when coding on lumi-erp, running pytest/Vitest/e2e, cherry-picking onto main, opening PRs from Fusion/MiniMax, or when a ticket mentions worktree, dev-infra, KB-xxx, or scan_matching tests.

sevenjustin21 Bundle

Deploy and operate GPT-SoVITS for local voice cloning on Windows: ask for the install location before any download, inspect GPU/CPU/CUDA/7-Zip/FFmpeg, choose a compatible version, prepare accurately transcribed recordings, fine-tune GPT and SoVITS, troubleshoot WebUI/API/checkpoint failures, load custom weights, and verify a real local WAV. Trigger for GPT-SoVITS installation, voice-clone training, speaker fine-tuning, local TTS API setup, or failures during dataset preparation and model training.