Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
RouterOS v7 domain knowledge for AI agents. Use when: working with MikroTik RouterOS, writing RouterOS CLI/script commands, calling RouterOS REST API, debugging why a Linux command fails on RouterOS, or when the user mentions MikroTik, RouterOS, CHR, or /ip /system /interface paths. Scope: RouterOS 7.x (long-term and newer) only — v6 is NOT covered and accuracy for v6 problems will be low.
Build and deploy web apps to the cloud. Supports React, Vue, Astro, Next.js (static), vanilla HTML/CSS/JS, and serverless functions. Sites deploy to *.rebyte.pro with automatic SSL. Use when user asks to "deploy", "publish", "host", or make their app "live". Triggers include "deploy my app", "make it live", "publish site", "host my app", "deploy website", "put it online".
Comprehensive health inspection tool for Alibaba Cloud network products (EIP, CBWP, NAT Gateway, CEN, Transit Router, Physical Connection, VBR, Global Accelerator, CLB, ALB, NLB). Analyzes bandwidth utilization, connection count, QPS, and packet loss using Cloud Monitor data; generates a Markdown inspection report with monitoring charts, risk assessment, and scaling recommendations. All API calls are read-only. Use when users want to inspect network product usage, check bandwidth headroom, assess capacity before a business launch, or identify over-limit risk. Triggered by: inspect network products, network health check, bandwidth inspection, EIP/NAT/CLB/ALB/NLB/CEN/VBR/GA inspection, network utilization analysis, pre-launch network inspection, capacity assessment, bandwidth over-limit risk.
Provides comprehensive guidance for Alibaba Cloud OSS including bucket creation, object storage, access control, and OSS management. Use when the user asks about Alibaba Cloud OSS, needs to store files in OSS, configure OSS buckets, or work with Alibaba Cloud storage.
Deploy and manage Cloudflare Workers, Pages, and services via Code Mode MCP (API queries) + wrangler (deploys). OAuth auth for wrangler (tokens lack Pages perms). USE WHEN Cloudflare, worker, deploy, Pages, MCP server, wrangler, DNS, KV, R2, D1, Vectorize.
Load this skill whenever building, editing, or deploying a Goldsky Compose app — it is the reference layer that gives the concrete rules for how to build one: the exact shape of compose.yaml (every top-level, task, and trigger field), every `goldsky compose` CLI flag, the TaskContext API (env, fetch, callTask, logEvent, evm, collection), wallet APIs (smart wallet, BYO EOA), gas sponsorship, contract codegen, the dashboard URL, and pricing. Consult it before writing or editing any compose.yaml or task file — do not synthesize the manifest/CLI/API shape from memory — and also to answer any user question about how Compose works or what a field, flag, or API does. Pairs with /compose (the entry-point build guide, loaded first); use /compose-doctor to debug a broken app. Do NOT load for Turbo, Mirror, Subgraphs, Edge, or Boost — those have their own reference skills.
Deploy HTML/CSS websites to ERPNext/Frappe (v15/v16) as Web Pages via the REST API. Use this skill whenever a user wants to host a website on ERPNext, deploy HTML mockups to Frappe, create Web Pages programmatically, configure Website Settings, or integrate Frappe's Discussion system as a forum. Also use when the user mentions "website on ERPNext", "Web Page API", "Page Builder", "Web Template", or wants to serve custom HTML from Frappe. Covers: Web Pages with Page Builder, custom Web Templates, Website Settings (navbar, footer), CSS management, Frappe Discussion integration, and deployment scripting.
Manage GitLab runner controllers and authentication tokens. Create, inspect, update, delete controllers; manage scopes; and generate, rotate, and revoke tokens. Admin-only experimental feature for managing runner controller lifecycle. Triggers on runner controller, controller token, controller scope, experimental runner, admin runner.
Assess Splunk indexer-cluster membership, factor and searchability state, bucket fix-up evidence, cluster-bundle distribution, rolling-maintenance readiness, multisite behavior, and SmartStore interactions without changing a deployment. Use for cluster-manager or peer health, unmet replication or search factors, incomplete searchability, persistent fix-up, cluster-bundle state, rolling readiness, and cluster-specific incident routing. Preserve Cloud, Enterprise, evidence-collection, storage-design, upgrade-planning, and active-operations boundaries.
Analyzes database migration scripts for lock contention, downtime, rollback strategy, and deployment risk. Triggers on: "analyze this migration", "migration risk", "is this migration safe", "schema change risk", "DDL risk", "rollback strategy", "migration review".
ModelScope unified operations entrypoint. Covers model/dataset search, download, and upload; repository management; Studio deployment; MCP service search, deployment, and configuration; and Skills Center search, install, and publish. Use this skill whenever the user mentions ModelScope or any platform operation. Use ms-studio-deploy for complex Studio deployment workflows; see this skill's references for the expanded MCP and Skills Center details.
Use when users need safe over-the-air update workflows for ESP32-class boards or Arduino Uno R4 WiFi, including OTA sketch requirements, network port discovery failures, remote recovery planning, and rollout safety checks.
Inspect an agent codebase to decide where tracing belongs, turn on Ratel's native OTLP telemetry, and pick the OTel backend the team already runs to export to, then write a proposal covering instrumentation, backend selection, and the dashboards that prove value. Use when mounting observability, asking where tracing goes or what to instrument/measure, turning on Ratel telemetry, choosing an OTel backend (Langfuse/LangSmith/collector/Ratel Cloud), designing dashboards, asking what proves Ratel's value, or `/ratel-observability-assessment`. Independent observability branch reached from /ratel-assessment; may point to /ratel-integrate when the user separately wants code integration. Writes one living markdown file to <repo>/.ratel/; does not edit code or call a backend API; skips when there's no agent surface.
Operates a local Red Hat Developer Hub environment with the rhdh-local-setup customization system: enable or disable dynamic plugins, apply configuration, switch pristine and customized modes, start or stop containers, inspect health and logs, run plugin verification, and back up or restore customizations. Use for local RHDH, podman compose plugin testing, PR artifact verification, 504 or startup troubleshooting, and local Extensions Catalog checks.
Guides uniCloud cloud development in uni-app including project setup, cloud database CRUD operations, cloud function deployment, cloud storage file management, and datacom component data binding. Use when the user needs to integrate uniCloud services, work with cloud databases, create cloud functions, or manage cloud storage in a uni-app project.
Deploy a local project directory or Git repository to Volcengine as a running, reachable cloud service. USE WHEN: deploy to Volcengine, deploy to 火山引擎/火山, deploy this repo/project, publish current code, launch the app, run it in the cloud, expose it as a service, deploy to ECS/VKE/veFaaS, run on ECS, push to VKE, deploy as serverless/FaaS, or the user wants the agent to choose a Volcengine hosting target. If the user only asks which Volcengine deployment target to choose, use `volcengine-prepare` skill first. Not for creating a single standalone resource — use `volcengine-cli` skill for that.
Analyze project and generate Docker configuration: Dockerfile (multi-stage dev/prod), compose.yml, compose.override.yml (dev), compose.production.yml (hardened), and .dockerignore. Includes production security audit. Use when user says "dockerize", "add docker", "docker compose", "containerize", or "setup docker".
Query Alibaba Cloud DDoS Pro (ddoscoo) block/intercept reasons via SLS full logs and ddoscoo CLI. Analyzes detailed information about intercepted requests including CC protection rules, precise access control rules, region blocking, and IP blacklist policies. Use when users report being blocked by DDoS Pro, encounter block pages, or need to investigate and remediate DDoS protection rules. Trigger words: "DDoS block query", "blocked by DDoS Pro", "DDoS intercept", "ddoscoo intercept query", "CC block", "precise access control block", "高防拦截查询", "request blocked by anti-ddos"
Call Alibaba Cloud SLS from Python (alibabacloud_sls20201230): ListProject (list projects), ListLogStores (list log stores), GetLogsV2 (query logs). Suitable for scenarios such as "list projects", "list LogStores", "query SLS logs", and "search and analyze logs". See reference/*.yml for the API contract; see scripts/ for runnable examples; see scripts/requirements.txt for dependencies.
Upload local files or images to the project's Cloudinary CDN (cloud “cyeam”) via the official `cld` CLI, replicating the /admin/upload behavior. Converts images to webp during storage and uploads them to a target folder. Use when the user wants to upload images or files to Cloudinary, batch-upload a directory, or asks “上传图片到cloudinary”, “传图”, or “upload to cloudinary”.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for live container runtime analysis, mounted secrets, sidecars, namespaces, init containers, entrypoint drift, and route-to-container resolution. Use when the user asks why a live container differs from manifests, where a mounted secret is consumed, how a sidecar or init container changes runtime state, or which route resolves to which live container. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kubernetes API analysis, service-account trust, RBAC edges, admission and controller behavior, cluster secrets, workload mutation, and namespace-scoped drift. Use when the user asks to inspect kube API permissions, service-account tokens, RoleBinding or ClusterRoleBinding edges, admission webhooks, controller-created pods, secret exposure, or why live workloads differ from manifests. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for kernel attack surface, namespace and cgroup boundaries, container isolation assumptions, syscall paths, and escape primitive verification. Use when the user asks to analyze container-to-host escape paths, kernel exploit prerequisites, namespace crossover, capability misuse, or prove whether an exploit primitive crosses the sandbox boundary. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
Configure host-based firewalls (iptables, nftables, UFW) and cloud security groups (AWS, GCP, Azure) with practical rules for common scenarios like web servers, databases, and bastion hosts. Use when exposing services, hardening servers, or implementing network segmentation with defense-in-depth strategies.
Deploys and manages Laravel applications on Laravel Cloud using the `cloud` CLI. Use when the user wants to deploy an app, ship to Cloud, create or manage applications, environments, databases, caches, object storage, queues, domains, instances, background processes, secrets, compute, scheduled tasks, or Laravel Cloud infrastructure; or check billing, usage, or spend. Triggers on deployment, shipping, Cloud management, environment setup, database provisioning, billing or usage queries, the `cloud` CLI, and Laravel Cloud deployment troubleshooting.
Provides comprehensive guidance for Docker Compose including multi-container applications, service definition, networking, and volumes. Use when the user asks about Docker Compose, needs to orchestrate multiple containers, define docker-compose services, or manage multi-container applications.
Manage secure files for CI/CD including upload, update, download, list, and delete operations. Use when storing or replacing sensitive files for pipelines, managing certificates, or handling secure configuration files. Triggers on secure file, CI secrets, certificates, overwrite secure file, secure config.
Design and assess Splunk index, retention, capacity, archive, storage-tier, bucket-lifecycle, and SmartStore plans from supplied requirements and evidence without changing a deployment. Use for index placement, searchable and archive windows, growth and capacity models, storage choices, restore planning, SmartStore readiness, and evidence-backed change validation. Route active incidents and provider-owned operations to their operational owners.
Design implementation-ready Splunk ingestion pipelines from known source requirements. Use for input and collector choice, processor placement, ingestion-time parsing, transformation, filtering, routing, capacity, reliability, security, validation, ownership, and implementation handoff for Splunk Cloud Platform or Splunk Enterprise. Do not use for source-onboarding discovery, production configuration, SPL, HEC endpoint work, fleet rollout, deployment, mutation, or active incident remediation.
Inventory and topology of the monitored Kubernetes estate via KubeSense MCP — clusters, nodes, pods, workloads, detected issues, infra failures (OOM/CrashLoop/probe/scheduling), and recent deploys/scaling changes. Use for "what is running", "what is broken at the k8s layer", and "what changed".
Query spans and distributed traces via KubeSense MCP — latency percentiles, error rates, the exact trace field catalog (service, role, method, status_code, resource — not app_service/kind/subtype/return_code), duration units, and the distributed-trace waterfall for root-causing which hop broke or burned the time.
Replicate the macbook-metrics setup on any Mac — a local, always-on system-metrics collector (CPU, GPU, RAM, disk, network, battery, thermals) built as a Swift CLI, run by launchd every 60s, stored in SQLite, and backed up to a private GitHub repo. Use when someone wants long-term Mac performance tracking, asks how macbook-metrics works, or wants to set up the same monitoring on a new machine. Differentiator: covers the full architecture and setup ideology, not day-to-day querying of an existing install.
NATS cloud-native messaging system. Covers Core NATS, JetStream persistence, and request/reply patterns. Use for lightweight, high-performance microservices communication. USE WHEN: user mentions "nats", "jetstream", "cloud-native messaging", "request/reply", "subject wildcards", asks about "lightweight messaging", "microservices communication", "nats streaming" DO NOT USE FOR: complex routing - use `rabbitmq`; AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; JMS compliance - use `activemq`; persistent queues only - use dedicated broker
Guide for using Netlify DB (managed Neon Postgres). Use when the project needs a relational database, structured data storage, SQL queries, or data that will grow over time. Covers provisioning, raw SQL via @netlify/neon, Drizzle ORM integration, migrations, and deploy preview branching. Also covers when to use Netlify Blobs instead.
Evaluates Kubernetes cluster security by actively simulating attacker techniques against the API server, kubelet, etcd, pods, RBAC, network policy, and secrets, using kube-hunter, Kubescape, peirates, and manual kubectl exploitation to find paths to cluster compromise. Use for an authorized penetration test or hands-on validation that controls actually stop an attacker. Keywords: kube-hunter, Kubescape, peirates, kubelet 10250, anonymous auth, token theft, lateral movement, cluster takeover. Do not use for a configuration-only compliance audit - use performing-kubernetes-cis-benchmark-with-kube-bench.
A focused Cloud Run Admin API CLI with agent-native output, local inventory, and command discovery. Trigger phrases: `inspect Cloud Run services`, `list Cloud Run jobs`, `find Cloud Run revisions`, `check Cloud Run executions`, `search Cloud Run inventory`.
Provides comprehensive guidance for Redis including data structures (string/hash/list/set/zset/geo/hyperloglog/bitmap/stream), common commands with examples, caching patterns, persistence (RDB/AOF), replication & sentinel, cluster, Lua scripting, transactions, pub/sub, pipelining, security hardening, and production best practices. Use when the user asks about Redis, needs to implement caching, choose Redis data structures, configure persistence or cluster, or troubleshoot Redis performance.
Expert Site Reliability Engineer specializing in SLOs, error budgets, and reliability engineering practices. Proficient in incident management, post-mortems, capacity planning, and building scalable, resilient systems with focus on reliability, availability, and performance.
Diagnose Tailscale subnet router connectivity failures. Traces the full route lifecycle: advertisement, approval, client acceptance, policy routing (table 52), and IP forwarding. Use when clients can reach Tailscale peers by IP but not devices on advertised subnets, or when subnet routes appear approved but traffic doesn't flow. Also use when Docker containers fail to advertise routes, when `ip route` shows no subnet route (it's in table 52), or when traffic flows one way but responses don't return.
Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability, quality evaluations, multi-agent orchestration, and MCP server integration.
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.