Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Set up a monitored progressive rollout ("safe rollout") for a GrowthBook feature flag — combining a ramp schedule with guardrail metric monitoring, automated signals, and optional auto-rollback. Use when the user says "roll this out safely", "monitor the rollout with guardrail metrics", "set up a safe rollout", "I want to ramp this with automatic rollback if metrics regress", "configure monitoring on the ramp", "check the monitoring status of this rollout", "approve the next monitored step", or "roll back because guardrails are failing". For unmonitored ramps (just progressive coverage, no metrics), use flag-ramp directly. For simple on/off time windows, use flag-schedule.
Methodology for pivoting from GCP to Google Workspace. Use when GCP Service Account or Project access has been obtained and the target organization uses Google Workspace; when moving from the cloud platform into corporate email, documents, or the admin console is needed; or when Domain-Wide Delegation is configured. Covers Domain-Wide Delegation abuse, OAuth scope exploitation, Workspace API data theft (Gmail/Drive/Calendar/Admin Directory), and Workspace persistence techniques.
Use when adding GitHub Actions CI/CD to a project scaffolded with genesis (services/<app>-server Go API, services/<app>-web pnpm React app). Asks which CD target (Railway, Kubernetes, VM + Overwatcher) and which branch model (main = production, or main = staging + release = production), then writes one ci.yml wired with needs so GitHub renders a single pipeline graph.
Use when deploying a project scaffolded with genesis (services/<app>-server Go API, services/<app>-web React app, Postgres) to Railway — creating the Railway project, services, variables, volume, GitHub auto-deploy, and public domain via the Railway MCP server.
Support Go services by keeping infrastructure, security boundaries, and automated tests aligned with the application architecture. Use when working on Terraform, Cloud Run, Cloud Build or CI, docker-compose environments, integration or component test setup, repository authorization boundaries, service-to-service authentication, or secure internal operations.
Use when managing multiple Google Play apps with GPC. Make sure to use this skill whenever the user mentions multiple apps, multi-app, monorepo, white-label, batch operations, bulk upload, several apps, --app flag, app switching, profiles for different apps, fleet management, app portfolio, multiple package names — even if they don't explicitly say 'multi-app.' Also trigger when someone has more than one Android app and wants to manage them efficiently, when they need different configurations per app, when they're running the same command across multiple apps, or when they have a monorepo with multiple Android modules. For single-app setup, see gpc-setup. For CI automation, see gpc-ci-integration.
Use when monitoring Android app health metrics from Google Play. Make sure to use this skill whenever the user mentions gpc vitals, gpc watch, gpc status, crash rate, ANR rate, startup time, Android vitals, crash monitoring, threshold alerting, vitals gating, rollout monitoring, auto-halt, breach notification, webhook alerting, frame rate, battery usage, memory issues, error tracking, app quality, user reviews, review replies, Play Store reviews, star rating, negative reviews, review export, financial reports, stats reports, gpc reports, reports list, reports download, bulk reports, earnings report, sales report, play balance, installs report, subscriptions report, reports bucket, GPC_REPORTS_BUCKET, pubsite_prod, REPORT_ACCESS_DENIED, download bulk reports permission, or wants to check app health, monitor a staged rollout, respond to reviews, or download Play Console reports. Also trigger when someone asks about gating deployments on crash data, monitoring app performance after a release, watching a rollout for regressions, or tracking review sentiment — even if they don't mention GPC. For releases, see gpc-release-flow. For CI gating, see gpc-ci-integration.
Huawei Cloud penetration testing methodology. Use when the target uses Huawei Cloud services, assets under obs.*.myhuaweicloud.com are found, Huawei Cloud AK/SK credentials are obtained, OpenStack-style metadata at 169.254.169.254 is accessible from an ECS instance, or security assessment of Huawei Cloud services such as IAM/ECS/OBS/RDS/CCE/FunctionGraph is needed. Covers IAM privilege escalation (OpenStack Keystone), ECS takeover, OBS object storage exploitation, RDS database attacks, CCE container clusters, FunctionGraph, ELB load balancing, LTS logging, and KMS key management. Huawei Cloud uses three interfaces: OpenStack CLI, obsutil, and REST API.
Set up self-hosted Inngest on macOS as a durable background task manager for AI agents. Interactive Q&A to match intent — from Docker one-liner to full k8s deployment with persistent state. Use when: 'set up inngest', 'background tasks', 'durable workflows', 'self-host inngest', 'event-driven functions', 'cron jobs', or any request for a local workflow engine.
Manage KASM Workspaces - a container-based VDI platform streaming desktops to browsers. Covers installation, workspace configuration, persistent profiles, S3 storage, backup/recovery, troubleshooting, and API operations for single-server and multi-server deployments. Use when: installing KASM, configuring workspaces, setting up persistent profiles, troubleshooting "No Resources Available", container destruction errors, backup to Backblaze B2, Cloudflare Tunnel setup, database operations, or managing KASM services.
Implement Okta as a centralized cloud identity provider: configure SSO with AWS, Azure, and GCP, deploy phishing-resistant MFA with Okta FastPass, automate user provisioning/deprovisioning, and enforce adaptive access policies on device posture and risk signals. Use when standing up Okta SSO, rolling out FastPass MFA, automating identity lifecycle, or building risk-based conditional access for cloud environments.
Nextcloud files and administration via WebDAV and the OCS API. Use for any Nextcloud file or instance task: upload or download a file, PROPFIND directory listing, MKCOL, MOVE, COPY, chunked upload of large files, trash bin and file versions, sharing a file, public link with password and expiry, share permissions, creating or disabling accounts, quotas, groups, subadmins, app tokens, enabling apps, instance capabilities. Triggers: nextcloud, webdav, remote.php/dav, ocs, user-provisioning, quota, облачное хранилище, публичная ссылка на файл, шаринг файла, загрузить файл, пользователи.
Expert guidance on Oracle Cloud Infrastructure services, architecture patterns, cost optimization, and deployment strategies. Use when designing on OCI, selecting OCI services, estimating cost, or applying OCI enterprise best practices.
OpenTelemetry Transformation Language (OTTL) for OTel Collector pipelines. Use when writing or debugging OTTL statements in the transform processor, filter processor, or routing connector in any collector configuration — context selection, path expression mistakes (`attributes` vs `resource.attributes`), `error_mode`, cardinality reduction with `keep_keys`, JSON body handling with `ParseJSON`, PII redaction with `SHA256` / `replace_pattern`, and span naming. Not for receiver/exporter connectivity, DNS, pipeline wiring, or telemetry that never reaches the processor — those are infra problems, not OTTL problems.
Query and manage PagerDuty — find out who's on call, list and manage incidents, read escalation policies and schedules, trace who got paged and why, acknowledge/resolve/snooze/escalate incidents, and create or update services. Use this whenever the user mentions PagerDuty, on-call, paging, escalation, an incident ID like `PXXXXXX` or `Q...`, asks "who's on call", "page the on-call", "ack this incident", "why wasn't I paged", or pastes a pagerduty.com URL — even if they don't say "API". Always start from this skill when interacting with this service — its bundled scripts and recipes are the fastest path.
Use when handling creation, version management, instantiation, permission control, PAC templates, and store integration for BK-CI pipeline templates. Prefer this when users mention template reuse, template versions, batch instantiation, template migration, store templates, or PAC templates.
Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection with agent-browser. Use when a preview or production URL redirects to a Vercel login page, returns a protection 401 or 403, or needs short-lived Trusted Sources OIDC authentication instead of a static bypass secret or public exception.
Set up a Quiver bolt's three-layer bootstrap stack (public bootstrap repo, private dotfiles repo, private workspace repo, an age key, and an SSH key) and create the bolt. Use when a user wants to configure a new Quiver persona or dotfiles stack, onboard to Quiver, or spin up a bolt dev environment from scratch. Works on macOS, Linux, and Windows.
All-in-one Redis expertise covering data modeling and key naming, client connections (pooling, pipelining, client-side caching, timeouts), clustering and replication, Redis Search (FT.CREATE, vector and hybrid search, RAG pipelines), observability and incident triage, production security hardening, semantic caching for LLM responses via LangCache, and agent memory via Redis Iris (session events, long-term memory, background promotion). Use whenever designing, writing, reviewing, or debugging anything that touches Redis: choosing a data structure, naming keys, configuring a client, sharding across a cluster, building or tuning a search index, monitoring or diagnosing performance, hardening a deployment, caching LLM completions, or wiring persistent memory for an AI agent, merged into one skill so the right domain loads automatically without picking between separate ones.
Reports vendor support phases and end-of-life dates for RHDH and the platforms it runs on: OpenShift, ARO, OSD, ROSA, AKS, EKS, GKE, PostgreSQL, Red Hat build of Keycloak, and Quay. Use for "is OCP 4.16 still supported", "when does PostgreSQL 15 go EOL", "which Kubernetes version should AKS be on", "which OCP versions does RHDH 1.10 support", or an RHBK or Quay lifecycle lookup. Product lifecycle only — RHDH milestone dates such as Code Freeze belong to rhdh-release-schedule.
MikroTik netinstall-cli for automated RouterOS device flashing. Use when: automating netinstall, writing scripts that invoke netinstall-cli, building netinstall tooling, understanding etherboot/BOOTP/TFTP protocols, working with RouterOS package files (.npk), using modescript or configure script, or when the user mentions netinstall, etherboot, or device flashing.
Write an operational runbook for a service, incident type, or deployment procedure. Use when asked to write a runbook, create an ops guide, document an operational procedure, or prepare an incident response playbook. Produces a runbook with overview, prerequisites, step-by-step procedures, rollback steps, troubleshooting table, and escalation paths.
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs.
Design and audit service levels, SLIs, SLOs, SLAs, error budgets, maintenance windows, incident status, support response promises, uptime claims, API latency targets, data freshness targets, recovery objectives, and customer communication. Use when a product needs reliability promises that engineering, support, sales, and customers can trust.
在專案中建立並維護 Zeabur 部署規範，會在專案根目錄的 AGENTS.md 寫入一段部署約束（Zeabur 只支援 Dockerfile、不支援 docker-compose；compose 僅供本地開發測試）。僅在使用者明確指定專案要部署到 Zeabur 時才使用 — 例如使用者明說「這個專案要部署到 Zeabur」「要上 Zeabur」「設定 Zeabur 部署」，或直接呼叫此 skill。不要在僅僅提到 Docker、寫 Dockerfile、討論部署平台、或泛泛談到 Zeabur 時觸發；必須有明確的「部署到 Zeabur」意圖。This skill MUST be used only when the user explicitly states the project deploys to Zeabur, and MUST NOT be triggered by Docker usage, Dockerfile work, or general deployment talk.
Use when the user asks how Twingate works, wants to design or evaluate a Twingate deployment, needs to understand components (Controller, Client, Connector, Relay), or is planning a ZTNA rollout. Activate for: zero trust, ZTNA, remote access architecture, network design with Twingate, VPN replacement, microsegmentation, split DNS, NAT traversal, P2P vs Relay, Remote Network topology, Resource definition strategy, or deployment sequencing. Also activate for community/reference deployment patterns: exposing a self-hosted AI chat assistant (OpenClaw, WhatsApp/Telegram bots) with no public inbound ports, private Railway/PaaS app deployment with zero-ingress, or "what does the twingate-assistant plugin itself do" meta-questions.
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.