Devops AI Skills

Inspect Neon serverless Postgres: projects, branches, databases. Branch create and delete need exact-match confirmation; connection passwords are masked. Trigger phrases: neon, serverless postgres,…

Configure VPCs, firewall rules, and Cloud NAT. Implement shared VPC and private service connect. Use when designing GCP network infrastructure.

Expert knowledge for Azure Durable Task development including best practices, decision making, architecture & design patterns, limits & quotas, configuration, integrations & coding patterns, and…

F5 BIG-IP health monitoring - virtual server status, pool member health, log analysis, performance statistics, and systematic health assessment. Use for routine/periodic checks: checking F5 load…

Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse v4 LLM tracing (as_type, score_current_span, should_export_span, LangfuseMedia), and drift detection. Use…

Teach agents to build synthetic monitoring as code with Checkly, including Playwright browser checks, API checks, alerting, and CI deploy workflows.

Use when designing the reaction to a class of failures — typed error taxonomies, retry/backoff/timeout policy, circuit breakers, React/Next error boundaries, and the user-message vs operator-log…

Use this skill when the user wants to know whether an Amazon EKS cluster is healthy right now, or asks you to assess, triage, or report on the state of an EKS cluster, its control plane, or its nodes…

Run a Python training/eval script directly in an existing local virtualenv — no docker, no container. Implements the four-verb consumer contract (submit/status/logs/cancel) over a vendored…

Use when designing and producing game levels, worlds, encounters, missions, narrative content, procedural generation, streaming partitions, content schemas, validation, pacing, or multidisciplinary…

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Perform an AWS Well-Architected Framework review of the current workload IaC and architecture, generating findings and GitHub issues for improvements.

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use…

Use curated Korean trending-slang candidates plus best-effort Namu Wiki lookups to write witty Korean text with up-to-date slang, with conservative safety and freshness guardrails.

Produce a complete positioning document using the Dunford framework — competitive alternatives, unique attributes, value, best-fit customer, market category, positioning statement, and tagline. Use…

Aircraft forensics from open public records — tail-number dossiers, fleet research, model-level safety, and NTSB event archaeology. Trigger phrases: `look up tail number`, `who owns this plane N…`,…

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements.…

Inspect Netlify sites and deploys: list sites, list recent deploys. Trigger phrases: netlify, netlify site, netlify deploy.

Provision GCP infrastructure with Terraform. Configure providers and deploy Google Cloud resources. Use when implementing IaC for GCP.

F5 BIG-IP troubleshooting - virtual server failures, pool member health, connection issues, SSL/TLS problems, iRule errors, persistence issues, and performance degradation. Use for an active incident:…

LeanUX backlog management methodology - user story template, story sizing, story states, task types, Definition of Ready/Done, anti-pattern detection and remediation

Write or repair Elixir tests with ExUnit, sandbox isolation, async reliability, Mox, ExMachina, and LiveViewTest. Use for test files, test setup, or failing/flaky tests. NOT for investigating an…

Architectural decision-making framework.

Vercel Agent guidance — dashboard and Slack chat, code review, production investigation, approved actions, and product installation. Use when configuring or working with Vercel's AI assistant.

Use for test coverage with Bun, --coverage flag, lcov reports, thresholds, and CI integration.

Plan, implement, or review kubernetes security policies work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests kubernetes security…

Assign version changes, maintain candidate and production identities, archive major versions, and record release or rollback evidence. Use for staged delivery, rule updates, bug fixes, feature…

Use this skill when someone wants an Amazon EKS cluster graded against best practices. Use it when they ask to review, assess, audit, or grade a cluster; ask for an operations review, security review,…

Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit versions for Docker/local-Docker and Kubernetes…

Autonomous AI agent benchmark evaluation register: task completion rates, planning accuracy, tool invocation precision, and cost benchmarks.

Version, release and migrate the system without breaking consumers.

Verl 单异步 DAPO 训练配置生成器。触发场景：(1) 启动单异步 DAPO 训练 (2) 生成训练脚本 (3) 配置特性参数 (4) 训练前检查。**特性策略**：用户未指定时默认开启性能特性（flash_attn/dynamic_batch/remove_padding/gradient_checkpointing），显存特性（offload/recompute）默认关闭。OOM…

Analyze Azure resources used in the app (IaC files and/or resources in a target rg) and optimize costs - creating GitHub issues for identified optimizations.

Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.

Performs Linux memory acquisition using LiME (Linux Memory Extractor) kernel module and analysis with Volatility 3 framework. Extracts process lists, network connections, bash history, loaded kernel…

Use Nara/PNU Korean spell-check surfaces conservatively to proofread Korean text, chunk long input, and return change-focused correction suggestions.

Deploy a free VLESS proxy/VPN node on Cloudflare Pages using edgetunnel. Automates code download, UUID generation, Pages deployment, free domain registration (DNSExit), DNS configuration, custom…

Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.

Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI…

Run a production Base node with Reth client — hardware sizing, port configuration, snapshot bootstrapping, security hardening, and sync monitoring.

Extract features from signals collected on rotating machinery components, including motors, pumps, fans, gears, bearings, and shafts. Signals can include vibration, electrical, or environmental sensor…

Deploy static sites and full-stack apps on Cloudflare Pages with previews, functions, and custom domains.

Set up, configure, and troubleshoot Salesforce Code Analyzer for any project. Handles installation, prerequisite checks, diagnosing broken setups, creating and editing code-analyzer.yml overrides,…

Expert knowledge for Azure Elastic SAN development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations &…

DDD-guided legacy refactoring patterns -- strangler fig, bubble context, ACL migration, 14 tactical/strategic/infrastructure patterns, and incremental monolith-to-microservices methodology

Dockerfile best practices, multi-stage builds, docker-compose, container networking, volume management, and image optimization.

Opinionated backend development standards for Node.js + Express + TypeScript microservices. Covers layered architecture, BaseController pattern, dependency injection, Prisma repositories, Zod…

Use when the user says 'shard this', 'split file', or when working with files over 1000 lines.

Use when querying distributed traces or application metrics in Alibaba Cloud ARMS (Application Real-Time Monitoring Service). Use for trace search by service/duration/tags, trace detail and method…

Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, querying metrics, managing domains, managing feature flags with vercel flags, or…