Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Bootstrap, configure, extend, and operate ObjectStack runtimes. Covers project setup (`defineStack`, drivers, scaffolding), declaring platform capabilities (`requires:` — which service plugins boot), plugin and service development (PluginContext, DI, kernel hooks like `kernel:ready`), and operations (CLI commands, migrations, deployment, test harnesses via LiteKernel). Use when the user is writing `objectstack.config.ts`, building a plugin or driver, turning a platform capability on, mounting the Hono HTTP layer, running `os` CLI commands, or planning deployment. Do not use for data schema design (see objectstack-data) or query patterns (see objectstack-query); data lifecycle hooks (beforeInsert / afterUpdate) belong in objectstack-data — only kernel / service-level events live here
Deep-dive security posture assessment by analyzing IAM policies, encryption configs, network rules, and security controls in code to produce evidence-backed findings aligned with the Well-Architected Security pillar
Alibaba Cloud Security Center (SAS) Overview Data Query Skill. Retrieves security score, asset status, risk governance, asset risk trends, and billing info. Supports flexible scope: query a single data item, a specific module, or the full overview based on user intent. 阿里云云安全中心（SAS）总览数据查询技能。可获取安全评分、资产状态、风险治理、资产风险趋势及账单信息。支持灵活查询范围：根据用户意图查询单个数据项、特定模块或完整总览。Triggers: “SAS overview”, “security center overview”, “SAS 总览”, “云安全中心总览”, “security score”, “安全评分”, “安全分”, “fixed vulnerability statistics”, “baseline risk”, “handled alerts”, “已修复漏洞统计”, “基线风险统计”, “已处理告警”, “host assets”, “uninstalled clients”, “主机资产”, “CPU 核数”, “未安装客户端”, “risk governance”, “WAF blocks”, “asset risk trend”, “风险治理”, “WAF 拦截统计”, “资产风险趋势”, “SAS billing”, “订阅状态”, “云安全中心账单”, “按量模块开关”. Out of scope: This Skill only covers SAS overview data queries. It does not perform remediation, modify configurations, or manage non-SAS services
Use this skill when the user asks to “pentest AWS,” “test AWS security,” “enumerate IAM,” “exploit cloud infrastructure,” “AWS privilege escalation,” “S3 bucket testing,” “metadata SSRF,” or “Lambda exploitation,” or needs guidance on Amazon Web Services security assessment.
Complete Base development playbook. Covers: (1) Network — Base RPC URLs, chain IDs (8453/84532), explorer config, testnet setup, connect to Base, Base Sepolia; (2) Contracts — Foundry deployment, forge create, BaseScan verification, CDP faucet, testnet ETH, deploy contract to Base; (3) Builder Codes — ERC-8021 attribution suffix, referral fees, dataSuffix for Wagmi/Viem/Privy/ ethers.js/window.ethereum, transaction attribution, earn referral fees, append builder code; (4) Agent registration — trading bots, AI agents, automated senders, ERC-8021 attribution wiring, base.dev API, register agent, builder code registration; (5) Node operation — run Base node, Reth setup, hardware requirements, self-hosted RPC, sync.
Forecast Azure spend and price planned resources or workloads. WHEN: "forecast Azure spending", "project next month cost", "compare forecast to my planning target", "how much will Azure cost", "estimate VM cost", "compare storage tiers", "compare Azure regions", "retail price", "EA rate card", "negotiated pricesheet". DO NOT USE FOR: configured budget health or alerts, bill analysis, cost spikes, rightsizing, or commitments.
Creates durable, resumable workflows using Vercel's Workflow DevKit. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow devkit", or step-based orchestration
Expert knowledge for Azure Databricks development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use with Unity Catalog, Lakeflow pipelines, Lakebase, AI Runtime/agents, external connectors/BI tools, and other Azure Databricks development tasks. Not for Azure Synapse Analytics (use azure-synapse-analytics), Azure HDInsight (use azure-hdinsight), Azure Data Factory (use azure-data-factory), or Azure Machine Learning (use azure-machine-learning).
Expert knowledge for Azure AI Document Intelligence development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using AnalyzeDocument APIs, custom/classification/template models, batch analysis, containers, or v4.0 migration, and other Azure AI Document Intelligence related development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI Custom Vision (use azure-custom-vision), Azure AI Search (use azure-cognitive-search), Azure AI Video Indexer (use azure-video-indexer).
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Favors retrieval from Cloudflare docs over pretrained knowledge.
Use when the user asks for a GCP or Google Cloud architecture diagram—VPC/networking, GKE, Cloud Run, landing zone, multi-region, or any diagram built with GCP service icons. Builds with the declarative layout engine using ground-truth GCP stencils, validates stencils, colors, nesting, and geometry, then runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Evaluate a workload's performance efficiency by analyzing resource selection, scaling configs, caching patterns, and data access patterns in the codebase against the Well-Architected Performance Efficiency pillar.
Use when the user explicitly asks for Flink/Ververica/Realtime Compute Console workspace operations: draft, SQL validation/execution, deployment, job, Session Cluster, namespace, table, member, variable, or checkpoint timeout diagnosis, especially with workspace/deployment/job IDs (w-*, d-*, j-*, sc-*, draft-*). Also use when the prompt asks to test/verify Flink Console lifecycle flow, safety guardrails, or parameter validation for these operations. This includes prompts such as create draft, deploy draft, list deployments, start/stop job, create/list session cluster, get tables, list variables. Also use when the prompt explicitly asks to run `python scripts/flink_ververica_ops.py` for Flink Console workspace operations. Do not trigger for unrelated "workspace" contexts or generic cloud/platform tasks (ECS, OSS, RDS, Kafka, Spark, Kubernetes, billing, weather). Do not trigger for Flink instance lifecycle operations (create/scale/delete/renew); those belong to alibabacloud-flink-instance-manage.
Manage Alibaba Cloud SLS (Simple Log Service) resources using aliyun-cli. Use when working with SLS projects, logstores, log queries, or when the user mentions Aliyun Log, Aliyun SLS, LogStore, Log Collection, or log service operations
Expert knowledge for Cost Management development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing Azure billing APIs, cost exports, budgets/alerts, reservations/savings plans, or subscription transfers, and other Cost Management related development tasks. Not for Azure Advisor (use azure-advisor), Azure Carbon Optimization (use azure-carbon-optimization), Azure Impact Reporting (use azure-impact-reporting), Azure Quotas (use azure-quotas).
Sui networks, gas costs, and epochs. Use when the user asks about Sui network environments (Mainnet, Testnet, Devnet, Localnet), gas cost calculations, gas budgets, epochs, or how the Sui network operates at a high level. For CLI client setup, address management, faucets, and explorers, see the `sui-client` skill. For installing the Sui CLI, see the `sui-install` skill.
Creates reusable Terraform modules with proper structure, variables, outputs, and state management for infrastructure as code. Use when users request “Terraform setup,” “infrastructure as code,” “IaC module,” “cloud provisioning,” or “Terraform module.”
Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and compliance gate gaps. Use when generating, reviewing, refactoring, or migrating IaC and when building delivery/testing pipelines.
Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. Supports multiple datasets (random, sharegpt, sonnet, HF), backends (openai, openai-chat, vllm-pooling, embeddings), throughput/latency testing with request-rate control, and result saving. Use when benchmarking LLM serving performance, measuring TTFT/TPOT, or load testing inference APIs
Alibaba Cloud PolarDB Database AI Assistant. For PolarDB MySQL/PostgreSQL cluster management, instance inspection, performance diagnostics, parameter explanation and change assessment, SQL/log analysis, backup, security audit, HA/DR, event analysis, and other PolarDB O&M operations. Use when user questions involve PolarDB, cluster IDs starting with pc-, PolarDB kernel/proxy versions, parameters, primary-standby switchover, IMCI columnar storage, or PolarDB console operations. This Skill is PolarDB-only.
Use when the user asks for a Databricks lakehouse architecture diagram — medallion architecture (Bronze/Silver/Gold), Delta Lake, Unity Catalog, workspace deployment, data-plane/control-plane, or any diagram built with Databricks icons. Builds with the declarative layout engine using ground-truth stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Expert knowledge for Azure Cache for Redis development including troubleshooting, best practices, decision making, architecture & design patterns, security, configuration, and deployment. Use when configuring geo-replication, persistence, VNet/private endpoints, Entra/RBAC auth, or ARM/Bicep deployments, and other Azure Cache for Redis related development tasks. Not for Azure Managed Redis (use azure-managed-redis), Azure Cosmos DB (use azure-cosmos-db), Azure Table Storage (use azure-table-storage).
Hookdeck Event Gateway — webhook infrastructure that replaces your queue. Use when receiving webhooks and need guaranteed delivery, automatic retries, replay, rate limiting, filtering, or observability. Eliminates the need for your own message queue for webhook processing.
Creates step-by-step incident response runbooks for common outages, with actions, owners, rollback procedures, and communication templates. Use for “incident runbook,” “outage response,” “incident management,” or “on-call procedures.”
Diagnose ECS instance reboot or crash issues. First checks for abnormal maintenance events, then uses Cloud Assistant to check for internal restarts or kernel panics. Use this skill when users report ECS instance unexpected reboot, crash, abnormal shutdown, kernel panic, or OOM. Supports vmcore file analysis, kdump configuration, system log analysis, and Windows crash dump analysis
Expert knowledge for Azure Virtual Network development including best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and deployment. Use when configuring IPs/routing, VNet peering, NSGs/service endpoints, gateways/firewalls, or upgrading Basic to Standard IPs, and other Azure Virtual Network related development tasks. Not for Azure Networking (use azure-networking), Azure Virtual Network Manager (use azure-virtual-network-manager), Azure Virtual WAN (use azure-virtual-wan), Azure Route Server (use azure-route-server).
Analyzes Kubernetes resource usage metrics and historical data to suggest optimal CPU and Memory requests and limits. Use to reduce cloud costs, prevent OOMKills, and improve overall cluster reliability by right-sizing your deployments.
Finds Fabric items across every workspace with the Catalog Search API when the workspace is unknown, locating an item by display name, inventorying one item type tenant-wide, and returning the workspace and item IDs needed for later calls. Dataflow Gen1 and Gen2 items are not supported. Use only to locate items; once found, query them with the owning item skill, such as sqldw-cli, spark-cli, eventhouse-cli, or fabriciq.
Advanced ArgoCD operations beyond the core CLI/API: multi-cluster ApplicationSet generators, automated image updates, new-cluster bootstrapping, and workload onboarding via templated ApplicationSets. Use when working with ApplicationSet CRDs (list, cluster, git, matrix, merge, SCM, pull request, plugin generators), configuring ArgoCD Image Updater (semver/digest/newest-build update strategies + git write-back), bootstrapping a new Kubernetes cluster into a multi-repo GitOps setup, registering clusters with proper labels for ApplicationSet targeting, onboarding a new workload via the standard ApplicationSet template, or troubleshooting any of these. For routine app sync/status/diff work use the core `argocd` skill instead.
Expert-level Databricks platform, Apache Spark, Delta Lake, MLflow, notebooks, and cluster management. Use when the user mentions Apache Spark, Delta Lake, MLflow, lakehouse architecture, or PySpark, or when the task involves Cluster Configuration and Management, Delta Lake Architecture, PySpark Data Processing, or MLflow Integration
Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, error-rate trends or spikes, latency distributions, trace IDs, or span attributes — not AI observability traces or product logs. Uses posthog:apm-service-health, posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-spans-sparkline, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.
Check progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).
Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test inside the container. Every other kermt-* skill depends on this; invoke it first.
Expert-level Kubernetes cluster management, deployment strategies, networking, and production operations. Use when the user mentions containers, orchestration, devops, or cloud native, or when the task involves Kubernetes Architecture, Pods, Deployments, or Services
Assess a workload's operational excellence posture by analyzing CI/CD pipelines, observability instrumentation, deployment configs, and incident management patterns in the codebase to produce evidence-backed findings.
Twelve-Factor App patterns for software-as-a-service and long-running process applications. Use when configuring deploy-time environment, backing services, process startup/shutdown, or operational parity. Apply individual principles to frontends, serverless functions, and CLIs only where their runtime and platform make them relevant.
Volcengine Function Service: Use when users want to deploy a local frontend, Node.js or Python app, static site, or API service; create a serverless app from a template; connect an existing project to veFaaS; view its online URL; configure production environment variables, build or start commands, or ports; publish, roll back, invoke, or debug online functions; inspect logs, instance status, or resource configuration; pull or push cloud function code; create and manage sandbox instances; troubleshoot deployment or authentication failures, framework detection errors, missing gateways, and similar issues; call the veFaaS OpenAPI directly for advanced operations; get started with veFaaS and learn its concepts, capabilities, selection, or pricing; consult the official documentation in a terminal; or develop code using the veFaaS SDK or OpenAPI.
Expert knowledge for Azure Advisor development including best practices, decision making, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Advisor alerts, digests, recommendation states, Resource Graph queries, or RBAC access, and other Azure Advisor related development tasks. Not for Cost Management (use azure-cost-management), Azure Monitor (use azure-monitor), Azure Policy (use azure-policy), Azure Security (use azure-security).
Expert patterns for Azure Functions development, including the isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: Azure Function, Azure Functions, Durable Functions, Azure serverless, function app.
A ByteHouse cluster diagnostic and health-check tool for checking cluster health, diagnosing issues and anomalies, viewing node status, and analyzing performance metrics. Use this Skill when users need to check ByteHouse cluster health, diagnose cluster issues and anomalies, view node status, or analyze performance metrics.
Search and analyze Tencent Cloud CLS (Cloud Log Service) logs. Use whenever the user asks to: search logs, debug API errors, trace requests by trace ID, find 5xx errors, run CQL/SQL analytics over log topics, extract structured fields. Backed by the official tencentcloud-sdk-python CLS client
Expert knowledge for Azure App Configuration development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using feature flags, dynamic config refresh, snapshots, Key Vault integration, or CI/CD config sync, and other Azure App Configuration related development tasks. Not for Azure App Service (use azure-app-service), Azure Functions (use azure-functions), Azure Key Vault (use azure-key-vault).
Scans a Docker image with Trivy for vulnerabilities in OS packages and language dependencies, misconfiguration, exposed secrets, and licence violations, emitting SARIF, CycloneDX, or SPDX output. Use when scanning or gating a specific image, wiring an image scan into CI/CD, or checking an image during an incident investigation. Keywords: Trivy, image scan, --severity, --exit-code, SARIF, ignore file, .trivyignore. Do not use for cluster-wide scanning or non-image targets - use performing-container-security-scanning-with-trivy; when the toolchain is Grype use scanning-container-images-with-grype.
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.