Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use for generic GKE cluster node pool creation or standard non-TPU workload management (use gke-basics or gke-cluster-creation instead).
Design and implement microservices architecture including service boundaries, communication patterns, API gateways, service mesh, service discovery, and distributed system patterns. Use when building microservices, distributed systems, or service-oriented architectures.
SSH/server operations assistant. Use for remote servers, user@host, SSH configuration, uploads and downloads, deployments, jump hosts, tunnels, port forwarding, server command execution, and related tasks. Treat Host aliases in ~/.ssh/config as the sole server inventory, prefer key-based authentication, and wrap OpenSSH operations with this skill’s Python scripts.
Automated security scanning for dependencies, code, containers with Trivy, Snyk, npm audit. Use for CI/CD security gates, pre-deployment audits, compliance requirements, or encountering CVE detection, outdated packages, license compliance, SBOM generation errors.
DataWorks data development Skill. Create, configure, validate, deploy, update, move, and rename nodes and workflows. Manage components, file resources, and UDF functions. Covers 150+ node types: Shell, SQL, Python, DI, Flink, EMR, etc. Supports scheduled and manual workflow orchestration via aliyun CLI or Python SDK. WARNING: Supports mutating operations (Move, Rename) requiring explicit user confirmation. Delete operations are NOT supported by this skill. Triggers: DataWorks, data development nodes, workflows, FlowSpec, scheduling tasks, data integration, ETL pipelines, .spec.json. Also triggers for Alibaba Cloud data development, scheduling node configuration, FlowSpec format, or DI task orchestration.
Build, optimize, and troubleshoot Docker containers and images. Create efficient Dockerfiles, manage container lifecycle, configure networking and volumes, and debug container issues. Use when working with Docker, containerization, or container troubleshooting.
Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger keywords - debug inference, managed inference endpoint, local inference, ollama, lm studio, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, credential_endpoint_mismatch, host.openshell.internal.
EdgeOne Makers full-stack development skill pack — covers AI agent development (DeepAgents、LangGraph、 Claude SDK、OpenAI Agents、CrewAI), cloud functions (Node.js/Go/Python), edge functions, KV storage, middleware, and rapid deployment, helping AI coding assistants build and release applications on the EdgeOne platform accurately and efficiently.
Plan, build, scaffold, or safely extend Atlassian Forge apps using current official documentation. Use for new Forge apps, feature work in existing apps, module and manifest changes, UI Kit or Custom UI implementation, backend functions and events, Atlassian or external APIs, storage, permissions, environment configuration, distribution-affecting implementation, validation, and explicitly authorized deployment or installation; route standalone debugging and specialist reviews to their dedicated skills
Oracle Cloud Infrastructure guidance for designing, operating, and troubleshooting OCI services, including OCI Kubernetes Engine (OKE), OCI Internet of Things Platform, OCI Functions deployment and troubleshooting, and Enterprise AI workflows for OCI Generative AI models, Responses API agents, RAG, cost estimation, governance, private endpoints, hosted agentic applications, and Oracle platform integrations. Use when the user asks about OKE cluster design, Terraform or Resource Manager planning, OKE incident troubleshooting, Generic VNIC Attachment, Multus, pod networking, node pools, add-ons, ingress, load balancers, OCIR image pulls, Workload Identity, Kubernetes workloads on OCI, OCI IoT domains or digital twins, device publish flows, OCI Functions setup, deployment, invocation, or troubleshooting, OCI Generative AI, Enterprise AI Models, Enterprise AI Agents, governed GenAI applications, agentic workflows, RAG on Oracle Cloud, or OCI Generative AI pricing.
A bidirectional interactive terminal session tool for serial terminals, SSH interactive shells, local shells, device consoles, AT/CLI menus, and interactive debugging that requires context to be preserved. Trigger when users mention an interactive terminal, serial terminal, SSH terminal, opening a shell, continuing to read output after sending commands, keeping a session open, operating after login, or menu-based command lines. Also supports explicit invocation with /terminal
Set up Prometheus monitoring for applications with custom metrics, scraping configurations, and service discovery. Use when implementing time-series metrics collection, monitoring applications, or building observability infrastructure.
Installs and uses the Render CLI for deploys, logs, SSH, psql, Blueprint validation, and automation. Use when the user needs to run Render CLI commands, script deploys in CI/CD, authenticate with an API key, query services non-interactively, or troubleshoot CLI auth issues. Trigger terms: render CLI, render login, render deploys, render logs, render ssh, render psql, render blueprints validate, render skills, RENDER_API_KEY, non-interactive, CI/CD deploy.
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says \"实现实验\", \"implement experiments\", \"bridge\", \"从计划到跑实验\", \"deploy the plan\", or has an experiment plan ready to execute.
Launch an Antithesis run with snouty by discovering the harness layout, building the right Docker Compose config, running `snouty validate`, bailing on validation failure, and then submitting `snouty launch` with sane metadata. Use when the user wants to send, submit, or launch an Antithesis run. This skill takes duration in minutes as input.
Expert-level ArgoCD GitOps deployment, application management, sync strategies, and production operations. Use when the user mentions GitOps, Kubernetes, continuous deployment, declarative, or automation, or when the task involves ArgoCD Architecture, Application CRD, AppProject, or ApplicationSet.
Set up a Codex monitor for Vercel deployments and preview URLs. Use when the user invokes /vercel or $vercel, asks Codex to watch or monitor a Vercel deployment, waits for a Vercel preview or PR preview to become ready, or wants to be notified with both the deployment URL and preview URL once Vercel is READY.
Input template configuration for Elastic integrations. Covers agent stream templates (agent/stream/*.yml.hbs) for all non-CEL input types: HTTPJSON, AWS S3, CloudWatch, Azure Blob, Azure EventHub, GCS, GCP Pub/Sub, TCP, UDP, HTTP Endpoint, Filestream, Logfile, Journald, Winlog, and WebSocket. Also covers Federated Identity (Cloud Connectors) for agentless AWS integrations, including the auth.aws / use_cloud_connectors block on CEL stream templates. For CEL program logic, use the cel-programs skill.
Use this skill when the user wants to share, publish, or upload a static result through PinMe, especially by generating a static HTML share page for a PinMe project link, deployed full-stack app, Codex conversation summary, report, file, demo, or any 分享/发布/上传分享页 request that should end with `pinme upload`.
Performs a lightweight pre-release readiness review of Atlassian Forge apps across manifest/module wiring, architecture, runtime compatibility, dependency posture, tests, deploy readiness, and obvious security, cost, or reliability smells. Use when the user asks "review my Forge app", "pre-deploy check", "is this app ready to ship", "review manifest", "general app review", "release readiness", or asks for a broad quality pass. Do not use for deep security audits/SAST/exploitability review, cost optimization, or diagnosing a known broken app; route those to forge-security-review, forge-cost-optimizer, or forge-debugger respectively.
Use when building a Kubernetes Operator — custom controllers that reconcile CRD state. Triggers on "build an operator", "CRD design", "reconcile loop", "controller-runtime", "kubebuilder", "operator-sdk", "metacontroller", "KOPF", "operator capability levels", or "custom resource". Ships CRD validator, reconcile-loop linter, and OperatorHub capability auditor (all stdlib Python), 4 references on the operator pattern + CRD design + reconcile patterns + tooling landscape, and a /operator-audit slash command. NOT a generic k8s skill — specifically the Operator pattern.
Manage and troubleshoot Coolify deployments using the official CLI and API. Use this skill when the user needs help with Coolify server management, WordPress troubleshooting on Coolify, debugging service issues, checking SSL certificates, accessing containers, or managing applications and databases through Coolify. Particularly useful for diagnosing down services, fixing .htaccess issues, REST API problems, and performing deployment operations.
Set up Spanora AI observability in any project (JavaScript/TypeScript or Python). Use when user asks to "add spanora", "setup spanora", "integrate spanora", "add AI observability", "monitor LLM calls with spanora", "track AI costs", or mentions spanora in the context of adding observability to their project. Detects the language and installed AI SDKs (Vercel AI, Anthropic, OpenAI, LangChain) and configures the optimal integration pattern.
Manage Celigo Storage — the file and folder store built into integrator.io that flows, MCP servers, trading partners, and people share — plus Storage Query (read-only SQL over stored files) and the Celigo-hosted SFTP file server. Covers stable item IDs, integration system folders, upload, move, copy, merge and replace, the recycle bin and the storage quota. Use when uploading, finding, organizing, restoring, or purging stored files, reading the storage quota, querying a stored CSV, JSON, or Parquet file, or giving a trading partner SFTP access
Diagnoses and fixes issues in Atlassian Forge apps. Use this skill whenever a Forge app has errors, crashes, shows blank UI, fails to deploy, doesn't appear after installation, has permission issues, or produces unexpected output. Trigger on any mention of forge logs, forge deploy errors, resolver errors, blank panels, missing scopes, Custom UI not rendering, production vs dev discrepancies, or any Jira/Confluence app that "stopped working". Also trigger when the user asks to debug, troubleshoot, investigate, or fix a Forge app issue — even if they haven't used the word "Forge" but describe a Jira panel or Confluence macro acting up.
Expert guidance for the Infisical Terraform Provider. Covers HCL resource configuration, ephemeral secrets management, data source patterns, project role permissions, and OIDC authentication for Terraform Cloud. Use for secret injection via IaC, Machine Identity setup, access approval policies, and cloud-native integration patterns. Not for getting secrets into a running app (infisical-setup) or raw REST calls (infisical-api).
Expert RabbitMQ administrator and developer specializing in message broker architecture, exchange patterns, clustering, high availability, and production monitoring. Use when designing message queue systems, implementing pub/sub patterns, troubleshooting RabbitMQ clusters, or optimizing message throughput and reliability.
Monitoring and observability strategy, implementation, and troubleshooting. Use this skill whenever the user mentions monitoring, observability, metrics, logs, traces, alerting, SLOs, Prometheus, Grafana, Datadog, Loki, or OpenTelemetry. Triggers include designing metrics strategy (Four Golden Signals, RED/USE), setting up Prometheus/Grafana/Loki, creating alerts or dashboards, calculating SLOs and error budgets, instrumenting with OpenTelemetry, analyzing performance issues, choosing between monitoring tools, optimizing Datadog costs, migrating to open-source stack, and setting up distributed tracing.
Apifox automated test execution, suites, and CI: test-suite, scheduled-task, runner, apifox run, execution parameters, iteration data, report uploads, and CI regression. For complex test-scenario step modeling, use apifox-test-scenario.
Professional Roblox toolchain - Studio Script Sync vs Rojo, Rokit, Wally/pesde packages, luau-lsp with sourcemaps, StyLua, selene, darklua, Lune, roblox-ts, .luaurc, git, GitHub Actions CI and Open Cloud publishing. Use when creating a Roblox repo, configuring VS Code/Cursor, adding packages, fixing sourcemap/require typing, or automating builds and deploys.
Deploy and manage web applications on remote servers with AppGarden. Use when the user asks about deploying apps, configuring appgarden.toml, managing AppGarden servers/apps, viewing logs/status/metadata, or exposing local work through AppGarden tunnels.
Provision and migrate Fusion databases using the fusion-infra-cli (finf). USE FOR: provision a database for a service, run SQL migrations, provision PR-specific ephemeral databases, check database state. DO NOT USE FOR: application code changes, service deployments, role management, or infrastructure other than databases.
Do work in an Upstash Box, a sandboxed cloud container driven through the remote Upstash MCP server (mcp.upstash.com), instead of on the local machine. Use when the user asks to run, build, test, clone, or edit something remotely, in a sandbox, in the cloud, or in a box, when the deliverable is a pull request, a public preview URL, or a screenshot of a running app, when the local machine cannot deliver (no GitHub login for gh, no way to expose a port, a dirty or slow local checkout), when several independent tasks should run in parallel on separate machines, a code factory that turns a list of tasks into a list of pull requests, or when the deliverable is a video, screen recording, demo or timelapse of a browser, web app, terminal program or agent run. Applies whenever the session has the box_* and blob_* MCP tools, even when Upstash is not named.
AEM as a Cloud Service Java/OSGi best practices, guardrails, and legacy-to-cloud pattern transformations. Use for Cloud Service–correct bundles, deprecated APIs, schedulers, ResourceChangeListener, replication, Replicator, JCR observation (javax.jcr.observation.EventListener), OSGi Event Admin (org.osgi.service.event.EventHandler), DAM AssetManager, BPA-style fixes, HTL (Sightly) Cloud SDK lint warnings (data-sly-test redundant constant value comparison), or any time you need the detailed pattern reference modules under this skill.
Use when planning, running, or learning from chaos engineering experiments. Triggers on “chaos experiment”, “fault injection”, “gameday”, “resilience test”, “blast radius”, “steady state”, “abort criteria”, “Chaos Toolkit”, “Chaos Mesh”, “Litmus”, “Gremlin”, “AWS FIS”, or any deliberate failure-injection question. Ships an experiment designer, blast-radius calculator, and postmortem generator (all stdlib Python), 4 references on chaos principles, experiment design, attack taxonomy, and tooling landscape, and a /chaos-experiment slash command. Composes with feature-flags-architect (kill switches as abort triggers) and kubernetes-operator (common chaos targets).
Manage CompShare GPU cloud resources and MiniMax H3 video, image, and speech tasks through the compshare CLI. Use when Codex needs to install or configure compshare-cli, search GPU specifications and inventory, inspect pricing, create or manage instances, connect over SSH, transfer files, run durable remote jobs, manage images, disks, US3, teams or billing, create or inspect MiniMax H3 media, or diagnose CLI problems.
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.