Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Use when the user needs to deploy, operate, secure, or scale running infrastructure — cloud architecture (multi-region, VPC, FinOps), CI/CD and deployment strategies, secrets/IAM/supply-chain security, observability and SLO alerting, SRE and incident response, Kubernetes vs ECS and autoscaling, Terraform/Pulumi/CDK, or platform engineering and DORA metrics. Also for generating runbooks, pipeline configs, Terraform modules, or Kubernetes manifests. For choosing the system's architecture or stack before it runs (monolith vs microservices, which database), use software-architect.
A hands-on skill for operating Hermes Agent. Use it when the user mentions "operating hermes", "troubleshooting hermes issues", "gateway anomalies", "platform disconnects", "cron not executing", "messy profile configuration", "skills or tools not taking effect", or "wanting another agent to help maintain hermes". Based on the hermes-agent source code and official command entry points, it prioritizes the four steps of check, locate, fix, and verify, and does not make blind changes based on guesswork.
"Deploy Dify - an open-source LLM app development platform on Huawei Cloud with ECS via Terraform. Use when the user wants to deploy Dify (or an LLM application development platform) on Huawei Cloud and directly implement it with a Terraform/SAC template. Trigger: Dify 一键部署, Dify development, Agentic workflow, build AI App"
Systematic Kubernetes troubleshooting and incident response. Use this skill whenever the user mentions Kubernetes, K8s, kubectl, pods, containers, or clusters. Triggers include diagnosing CrashLoopBackOff, ImagePullBackOff, OOMKilled, or Pending pods, responding to production incidents, troubleshooting node NotReady or DiskPressure, debugging service connectivity or networking, investigating PVC or storage failures, analyzing performance degradation, checking cluster health, troubleshooting Helm releases, and conducting post-incident reviews.
Kaggle runtime environment, paths, accelerators, and reproducibility. PROACTIVELY activate for: (1) `/kaggle/input` path errors, (2) `/kaggle/working` output placement, (3) local vs Kaggle notebook behavior, (4) GPU/TPU/accelerator selection, (5) internet enablement, (6) package/version pinning, (7) memory cleanup and timeout issues, (8) DEBUG flags for fast runs, (9) Kaggle Secrets usage guidance, (10) quota-consuming runtime settings. Provides: path conventions, runtime checklist, accelerator IDs, reproducibility patterns, and resource safeguards.
Help Litium partner developers build, configure, and deploy e-commerce sites and backoffice UI extensions. Use for React Accelerator (Next.js, GraphQL, blocks, cart, checkout, wishlist), MVC Accelerator (.NET Razor views, controllers, view models, client builds), local setup, Litium Cloud deployment, data modelling and product fields, Litium Admin, Storefront GraphQL, Connect, and Extension Management APIs, or forum.litium.com solutions. Covers @litiumab/platform-extension-sdk extensions in React, Vue, Angular, or Vanilla: scaffolding, extension.manifest.json, window.litiumExtension, sub-path routing, IIFE/Vite builds, testing, installation, and deployment. Triggers: build Litium site, create Litium project, product field, block, accelerator, Litium API, wishlist, cart, placeOrder, custom field, backoffice extension, platform-extension-sdk, UI extension, panel, or settings page extension.
Automatic model fallback and failover. When the primary model's request fails, times out, hits rate limits, or runs out of quota, it automatically switches to a backup model to keep service continuity. Supports intelligent model selection across multiple providers and priorities, with health monitoring, automatic retries, and error recovery mechanisms.
Guides and best practices for working with Lakebase Postgres on Neon: connections, pooled vs direct, schema migrations, branching, autoscaling, scale-to-zero, instant restore, read replicas, IP allow lists, logical replication, and Lakebase Search. Use when the work is an existing DATABASE_URL, SQL, schema, inspect, or search. New backends, Auth, files, Functions, and LLM calls go to the parent `neon` skill. Also use for "@neondatabase/serverless", "@neondatabase/neon-js", "neon inspect db", "semantic search", "vector search", "full-text search", "BM25", or "hybrid search".
Set up reproducible dev environments via devbox (Nix-backed) or pure Nix flakes. Templates for MoonBit, Rust, TypeScript+pnpm, Python+uv, Haskell, OCaml, OxCaml preloaded with just / ast-grep / apm. Covers devbox.json, buildNpmPackage, direnv, GitHub Actions, and bootstrapping in sandboxed envs (Claude Code web). Use when starting, adding, or troubleshooting a Nix or devbox setup.
Use when reviewing whether code has enough operational evidence: structured logs, correlation IDs, metrics, traces, run summaries, error normalization, and safe redaction. Trigger for production readiness reviews, sync/job reviews, incident-prone code, or before delivery of backend workflows. Do not use for visual UI-only review.
Deploy OSMO using the unified chart on Azure AKS, AWS EKS or an existing Kubernetes cluster. Use for cluster provisioning, deployment storage, KAI Scheduler or GPU Operator installation, and post-install smoke tests. General workflow usage and running-cluster diagnosis belong to osmo-user.
Assesses the security posture of the etcd cluster backing Kubernetes: encryption at rest, TLS peer and client transport, access control, backup encryption, and network isolation. Use when auditing or hardening a control plane, reviewing whether Secrets are encrypted at rest, or protecting etcd backups, since etcd stores Secrets, RBAC policy, and ConfigMaps in plaintext by default. Keywords: etcd, EncryptionConfiguration, encryption at rest, peer TLS, snapshot, backup, control plane. Do not use for broad cluster-wide CIS checks - use performing-kubernetes-cis-benchmark-with-kube-bench.
Push to GitHub main and babysit the change until it is verifiably live in production, fixing CI and deploy failures along the way. Use when the user says "push", "push to github", "push to prod", "ship it", or "deploy". Differentiator: pushing requires the user''s explicit go-ahead; this is the procedure for AFTER they give it (this repo''s CI gate + Vercel promotion).
Deploy RAG systems to production with proper architecture, monitoring, and operations. Use this skill when deploying RAG to production, scaling retrieval systems, implementing RAG monitoring, or building enterprise RAG infrastructure. Activate when: production RAG, RAG deployment, enterprise RAG, RAG architecture, RAG monitoring, RAG scaling, RAG infrastructure, RAG ops.
Query and interact with Prometheus HTTP API for monitoring data. Use when Claude needs to query Prometheus metrics, execute PromQL queries, retrieve targets/alerts/rules status, access metadata about series/labels, manage TSDB operations, or troubleshoot monitoring infrastructure. Supports instant queries, range queries, metadata endpoints, admin APIs, and alerting information.
Use when setting up or repairing a Roblox team project outside Studio: Rojo or Script Sync, Wally packages, Rokit pins, luau-lsp type checking, Selene, StyLua, unit tests in Lune or the engine, GitHub Actions CI on pull requests, Open Cloud place publishing, Luau Execution or API key scopes, merging builders' Team Create map with code from files, Studio plugins, or proving a pipeline works. Also when users say "set up Rojo", "CI for my Roblox game", "run tests in CI", "publish from GitHub", "Script Sync stopped syncing", "Rojo deleted my parts", "wally packages not found", "luau-lsp can't find ReplicatedStorage", "selene errors on types", "the release wiped the map" or "my LocalScript doesn't run".
Senhasegura PAM platform integration — A2A OAuth 2.0, PAM Core credentials, SSH key rotation, DSM CLI for CI/CD, External Secrets Operator (Kubernetes), MySafe, and a runnable MCP server. USE WHEN senhasegura, segura, A2A application, DSM CLI, runb, MySafe, ExternalSecret + senhasegura, OAuth client_credentials for PAM, credential custody release, /iso/coe/senha endpoint, SCIM provisioning. NOT FOR HashiCorp Vault, AWS Secrets Manager, Azure Key Vault, GCP Secret Manager, 1Password, or generic OAuth 2.0 flows (use those directly).
Publish a stable version of Specsfy from the promovaweb/specsfy monorepo, keeping VERSION, CLI, skills, especialistas, ebook, changelog, tag and GitHub Release on the same SemVer. Use when the person asks to release or resume a Specsfy version. Do not use for pre-releases or for updating only a consuming project.
Provision, verify, and connect a self-hosted Temps platform instance on an explicitly authorized machine. Use when the user wants an agent to install Temps with the official deploy script, configure a local CLI context, start browser device authorization, present the approval URL, wait for approval, or perform initial platform, DNS, TLS, user, and service setup without exposing credentials.
Analyze incidents in Alert stage and suggest severity, business impact, affected services, communications, and response team. Use when triaging incidents, evaluating incident severity, or when the user asks to analyze incident impact.
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
Use this skill for all Alibaba Cloud 云效 (Yunxiao) DevOps operations on codeup.aliyun.com. Invoke IMMEDIATELY when the user wants to: create or manage Merge Requests (MR) on codeup, update work items/tasks in 云效, query MR lists or task status, create version tags via 云效 API, or push code to a codeup remote. Key triggers: 创建 MR, 提交评审, 云效, yunxiao, codeup, 更新任务, 查看任务, 发布版本, 打 tag. Handles both MCP tool mode and aliyun CLI fallback. Do NOT use for GitHub PRs (use git-workflow), Jira, GitLab, or non-Alibaba platforms.
Comprehensive documentation of Claude's capabilities for visual regression testing, CI/CD integration, and quality assurance automation. Use when setting up testing infrastructure, implementing visual regression, or understanding agent testing capabilities. (project)
Use this skill for AI in WeChat Mini Programs via wx.cloud.extend.AI. Covers generateText and streamText with callbacks (onText, onEvent, onFinish); streamText needs a data wrapper, while generateText returns the raw response. Models are accessed via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed group), or custom-*; the model id goes in the data wrapper’s `model` field. MUST run the two-step preflight before coding — see body. NOT for browser/Web (use ai-model-web), Node.js backends (use ai-model-nodejs), or image generation (use ai-model-nodejs).
Alibaba Cloud scenario-based skill. Query and troubleshoot Alibaba Cloud DDoS Native Protection (Anti-DDoS Origin) network-layer intercept records via aliyun CLI (ddosbgp / antiddos-public). Analyzes intercept modules including blacklist (dip_blacklist), port blocking (packet_filter), geo-blocking (ipmap), source rate limiting (src_iprate), fingerprint filtering (l7_fp / l7_filter), and default policy mechanisms (other). Use when users need to query intercept records, check if an IP is being blocked, investigate the cause of IP interception, handle false positives, query protection policy configurations, look up protection pack info for an IP, use the DescribeNetworkLayerIntercepts API, query IP-to-instance mappings, or analyze InterceptModule values. Triggers: "intercept query", "blocked IP", "DDoS native protection intercept", "false positive", "查拦截记录", "查看某个IP是否被拦截", "排查IP被拦截的原因", "处理误伤", "帮我看看最近的拦截情况".
Use when managing Alibaba Cloud Quan Miao (AiMiaoBi) via OpenAPI/SDK, including the user asks for Alibaba Cloud MiaoBi content operations, including listing resources, creating/updating configurations, querying runtime status, and diagnosing API or workflow failures.
Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.
Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function telemetry missing or stopped after a config/connection-string change, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, lock renewal during long-running processing, service bus dead letter.
Manage dotfiles with chezmoi — the source-state dotfile manager that uses filename attributes (`dot_`, `private_`, `encrypted_`, `run_once_`), Go templates, and password-manager integration to keep one set of dotfiles working across many machines. Use when the user says "set up dotfiles", "manage my dotfiles", "bootstrap a new machine", "chezmoi", "encrypt my SSH key in dotfiles", "template dotfiles per OS", "add secrets to dotfiles", "what should be in my .chezmoi.toml.tmpl", or asks how to share configs across macOS / Linux / servers. Also trigger when the user is staring at a fresh machine and wants the one-liner that gets them home, or when they're about to commit something sensitive into a dotfiles repo. Do NOT use for stow / yadm / rcm or other dotfile managers, generic git repo setup, or password-manager setup unrelated to dotfiles.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.