Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Best practices for Docker-based ROS2 development including multi-stage Dockerfiles, docker-compose for multi-container robotic systems, DDS discovery across containers, GPU passthrough for perception, and dev-vs-deploy container patterns. Use this skill when containerizing ROS2 workspaces, setting up docker-compose for robot software stacks, debugging DDS communication between containers, configuring NVIDIA Container Toolkit for GPU workloads, forwarding X11/Wayland for rviz2 and GUI tools, or managing USB device passthrough for cameras and serial devices. Trigger whenever the user mentions Docker with ROS2, docker-compose for robots, Dockerfile for colcon workspaces, container networking for DDS, devcontainer for ROS2, multi-stage builds for ROS2, or deploying ROS2 in containers. Also trigger for CI/CD with Docker-based ROS2 builds, CycloneDDS or FastDDS configuration in containers, or shared memory in Docker. Covers Humble, Jazzy, and Rolling distributions across Ubuntu 22.04 and 24.04 base images.
Install, start, stop, inspect, reset, and configure duoduo host-mode channels. Use when the request involves: channel lifecycle (install/list/start/stop/status/logs), Feishu setup card or /setup command, Feishu owner DM / main session / FEISHU_BOT_OWNER configuration, the 'main session is locked' refusal, stale card error, resetting a bound Feishu chat, ACP editor integration, channel descriptor editing (kind vs instance). Also trigger for Chinese: 拉起 feishu 通道, 配置 channel 提示词, 改 stdio 的 workspace, 查看 channel 状态, 飞书机器人怎么配, 设置 owner, 清除 session, 重置 channel.
Take an agent-written app from repo to live production on the user's OWN accounts, with providers they choose (hosting, database, auth, payments, email, domain/DNS). The human connects accounts and approves changes; supported wiring operations run through a local CLI and produce verification evidence with explicit limits. Use when the user wants to ship, deploy, go live, launch, publish, or put their app online, or asks to wire up env vars, webhooks, auth settings (signup, email confirmation, password policy), a real signup → confirmation email → login journey, password recovery, account isolation between two users, auth redirects, email DNS or a custom domain.
Simulates a batch of proposed IAM policy changes using Google Cloud Policy Simulator. Takes an array of simulations (resource, member, proposed_policy or proposed_policy_file), runs the simulation replay, and returns mapped results. Use when you have a batch of proposed IAM policy changes and need to simulate their impact on recent access patterns using Google Cloud Policy Simulator. Don't use for analyzing live IAM policies, applying policy changes, or simulating individual policy changes without a batch structure.
Inspects and configures the web application firewall (WAF) in front of a Power Pages production site. Lists the current state, recommends enabling protection when it is off, and walks the user through adding, updating, or removing custom rules — IP blocks, country blocks, path blocks, and rate limits. Use when the user wants to turn on WAF, block traffic by IP or country, rate-limit login or signup pages, protect pages from brute-force attempts, restrict access to specific paths, review the current firewall configuration, or asks "is my site protected against bots / common web attacks?" — even if they say "add rate limit" or "protect login page" without mentioning "firewall" or "WAF".
Create an application-specific production parity skill by inspecting an app's docs, source, tests, CI, deployment, infrastructure, config, auth, and environment setup, then asking targeted harness questions only for source-unanswerable decisions. Use when local, CI, PR, preview, staging, or other non-production environments may drift from production behavior; when production-only auth, config, identity-provider groups, feature flags, infrastructure, backing services, or policy differences caused bugs; or when a team wants a reusable skill that detects, documents, tests, and helps fix parity drift for one specific application.
Manage the full lifecycle of ADBPG Supabase projects. Use for listing or querying projects, creating, pausing/resuming, resetting passwords, managing API Keys, and security IPs. Triggers: “Supabase,” “supabase project,” “spb-xxx,” “ADBPG Supabase”
昇腾（Ascend）推理生态开源代码仓库智能问答专家旨在为 vLLM、vLLM-Ascend、MindIE-LLM、MindIE-SD、MindIE-Motor、MindIE-Turbo 以及 msModelSlim (MindStudio-ModelSlim) 等仓库提供专家级且易于理解的解释。在处理昇腾（Ascend）推理生态相关项目的用户询问时，务必触发此技能（Skill），可解答使用方法、部署流程、支持模型、支持特性、系统架构、配置管理、调试、测试、故障排查、性能优化、定制开发、源码解析以及其他技术问题。支持中英文双语回复，并可借助 deepwiki MCP 工具检索仓库知识库，生成具备上下文感知且基于证据的回答。Ascend inference ecosystem open-source code repository intelligent question-and-answer (Q&A) expert. Provide expert-level yet comprehensible explanations for repositories such as vLLM, vLLM-Ascend, MindIE-LLM, MindIE-SD, MindIE-Motor, MindIE-Turbo, and msModelSlim (MindStudio-ModelSlim). Use this skill when addressing user inquiries related to these Ascend inference ecosystem projects, including topics such as usage, deployment process, supported models, supported features, system architecture, configuration management, debugging, testing, troubleshooting, performance optimization, custom development, source code analysis, and any other technical issues about these projects. Support responses in both Chinese and English. Use deepwiki MCP tools to query repository knowledge bases and generate context-aware, evidence-based responses.
Caddy web server configuration for reverse proxy and automatic HTTPS. Use when: (1) writing Caddyfile configurations for reverse proxy setups (2) configuring automatic HTTPS with Let's Encrypt (3) setting up wildcard certificates with DNS challenge (4) integrating Caddy with Docker containers (same network or host services) (5) configuring request matchers, handle blocks, and routing patterns (6) setting up load balancing and health checks (7) troubleshooting TLS, upstream connectivity, or configuration issues (8) configuring header manipulation (header_up, header_down)
Launch Proteina-Complexa pipelines on a remote SLURM cluster — binder search, LaProteina monomer design, or multi-node distributed training. Reach for this skill whenever the user says "launch on SLURM", "submit to the cluster", "submit binder search to SLURM", "kick off training on the cluster", "multi-node training", "cluster job", "sbatch", "remote GPU run", "complexa slurm", "launch_protein_binder_search.sh", "launch_laproteina_train.sh", "launch_laproteina_design_pipeline.sh", "launch on grizzly / polar", "--on-cluster", "run distributed training", "sweep on SLURM", "run all targets on the cluster", "kick off a multi-target binder search", "rsync to cluster", "submit a singleton requeue chain", or whenever a Hydra config / sweep needs to escape a single workstation. This skill drives the launcher scripts under `slurm_utils/`, **always previews with `--dry-run` first**, then submits, captures SLURM job IDs, and emits a replayable manifest. SLURM submission costs cluster time and is hard to reverse, so the dry-run gate is non-optional.
Comprehensive guide to installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway. Use when the user asks about OpenClaw setup, configuration, channel management (WhatsApp/Telegram/Discord/Slack/iMessage/etc.), model provider setup, Gateway operations, multi-agent routing, security hardening, troubleshooting, or any maintenance task related to their local OpenClaw installation. Also use when encountering errors from `openclaw` CLI commands or the Gateway daemon.
Run a local read-only HTML topology UI for a project already deployed by Sealos Skills and return a localhost URL. Use when the user asks to view, inspect, visualize, render, open, or run a local canvas for deployed Sealos resources, mentions “.sealos”, Sealos deployment state, Kubernetes resources, topology, resource graph, localhost UI, or invokes “/sealos-canvas”.
Provides comprehensive guidance for Spring Cloud Alibaba including Nacos, Sentinel, RocketMQ, and Alibaba Cloud integration. Use when the user asks about Spring Cloud Alibaba, needs to use Alibaba Cloud services, implement service discovery with Nacos, or work with Spring Cloud Alibaba components.
Manage AWS accounts, organizations, IAM, and billing. Use when setting up AWS Organizations, managing IAM policies, controlling costs, or implementing multi-account strategies. Triggers on AWS Organizations, AWS IAM, AWS billing, Cost Explorer, SCPs, multi-account, AWS SSO, and Identity Center.
Build AI agents with AWS Bedrock AgentCore. Use when developing agents on AWS infrastructure, creating tool-use patterns, implementing agent orchestration, or integrating with Bedrock models. Triggers on keywords like AgentCore, Bedrock Agent, AWS agent, Lambda tools.
Helps estimate and calculate Azure resource costs. Use this skill when users ask about Azure pricing, cost estimation, resource sizing costs, comparing pricing tiers, budgeting for Azure deployments, or understanding Azure billing. Triggers include questions like "how much will this cost in Azure", "estimate Azure costs", "compare Azure pricing", "budget for Azure resources".
Run a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField Arm. Use this skill to launch and supervise it (directly, with tmux, or with systemd), and when it “exits 1 right after launch”, “systemd keeps restarting it”, reports “no matching device on the BF”, or the BlueField itself is unhealthy: “bfb-install exited 0 but DPU is dead”, “ping 192.168.100.2 works but ssh fails”, “host PFs aren't showing netdevs”. Refuse service containers under kubelet (doca-container-deployment). Covers PCI/NUMA/CPU/IRQ binding, co-tenant isolation (cgroup-v2/netns/numactl), a seven-layer error taxonomy, platform lifecycle (BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery), and a six-state BlueField lifecycle classifier. Destructive firmware burn / mlxconfig set requires explicit confirmation via doca-hardware-safety; library APIs, environment preparation, and builds use other skills.
Explain and manage a host-mode duoduo installation after onboarding. Use when the user asks how duoduo works, how stdio/daemon/channel/session fit together, where duoduo stores config and state, how to inspect current setup, how to upgrade duoduo itself, where something lives on disk (kernel_dir, runtime_dir, .env, descriptor.md), how to archive or recover a specific session (`duoduo session archive`, sessions-archive directory, restoring an archived session), or for broad 'configure duoduo' / 'fix my duoduo' requests that haven't narrowed to a specific channel or runtime setting yet. Also trigger for Chinese: 帮我理解 duoduo, duoduo 是怎么工作的, 看看我现在的 duoduo 配置, 帮我管理 duoduo, 升级 duoduo, 升级要注意什么, duoduo 哪个路径存什么, 归档 session, 删掉 session, 恢复归档 session.
Work with GitLab CI/CD pipelines, jobs, and artifacts. Use when checking pipeline status, viewing job logs, debugging CI failures, triggering manual jobs, downloading artifacts, validating .gitlab-ci.yml, or managing pipeline runs. Triggers on pipeline, CI/CD, job, build, deployment, artifact, pipeline status, failed build, CI logs.
Remote command execution and file transfer on SageMaker HyperPod cluster nodes via AWS Systems Manager (SSM). This is the primary interface for accessing HyperPod nodes — direct SSH is not available. Use when any skill, workflow, or user request needs to execute commands on cluster nodes, upload files to nodes, read/download files from nodes, run diagnostics, install packages, or perform any operation requiring shell access to HyperPod instances. Other HyperPod skills depend on this skill for all node-level operations.
Sets up and manages local Magento 2 development environments. Use when setting up local development, configuring local environments, or troubleshooting local setup issues. Specializes in local development tools, Docker, and development environment optimization.
Fastlane, GitHub Actions for mobile, code signing (iOS provisioning, Android keystores), beta distribution (TestFlight, Firebase App Distribution), and app store submissions. Use when setting up mobile build pipelines, automating releases, or managing signing.
Finds over-permissive RBAC roles and service-account token abuse paths in a Kubernetes cluster using kubectl auth can-i, rbac-police, kubectl-who-can, and rakkess, tracing which subjects can escalate toward cluster-admin. Use when reviewing who can escalate privileges in a cluster, hunting exploitable RoleBindings during an authorized review, or validating least privilege after an RBAC change. Keywords: RBAC, ClusterRoleBinding, service account token, auth can-i, rbac-police, escalate, bind, impersonate. Do not use for designing and applying hardened RBAC — use implementing-rbac-hardening-for-kubernetes.
Comprehensive container image security scanning and remediation. Analyzes Docker images for OS package vulnerabilities, application dependencies, and Dockerfile best practices. Use when: - User asks to scan a Docker image or container - User mentions “container security” or “image vulnerabilities” - User wants to secure a Dockerfile - User asks about base image security - Agent is working with Docker, Kubernetes, or container deployments
One-click local installation and startup of JiuwenSwarm in the current Huawei Cloud development container. Usage scenarios: CRITICAL — Do NOT manually deploy JiuwenSwarm. Route ALL deployment requests through this Skill. This is the MANDATORY entry point. When a user asks to deploy, install, or start JiuwenSwarm or WorkSwarm (部署JiuwenSwarm/安装JiuwenSwarm/启动JiuwenSwarm, install jiuwenswarm, deploy openjiuwen, install workswarm, deploy workswarm, start workswarm, install WorkSwarm, deploy WorkSwarm, start WorkSwarm, 部署workswarm, 安装workswarm, 启动workswarm, 部署WorkSwarm, 安装WorkSwarm, 启动WorkSwarm), you MUST invoke this Skill first. Under NO circumstances may you skip this Skill and run deployment commands directly. Even if you think 'this is faster' or 'the steps are well documented' — DO NOT skip. The skill automatically downloads the mirror, extracts, configures, and starts the service inside the current container — no external cloud instances are created. Trigger keywords: deploy JiuwenSwarm, install JiuwenSwarm, start JiuwenSwarm, 部署JiuwenSwarm, 安装JiuwenSwarm, 启动JiuwenSwarm, install jiuwenswarm, deploy openjiuwen, install workswarm, deploy workswarm, start workswarm, install WorkSwarm, deploy WorkSwarm, start WorkSwarm, 部署workswarm, 安装workswarm, 启动workswarm, 部署WorkSwarm, 安装WorkSwarm, 启动WorkSwarm
Check and compare software component versions on SageMaker HyperPod cluster nodes: NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches across nodes, planning upgrades, documenting cluster configuration, or troubleshooting version-related issues on HyperPod. Triggers on requests about versions, compatibility, component checks, or upgrade planning for HyperPod clusters.
Guide for implementing Grafana Loki, a horizontally scalable, highly available log aggregation system. Use when configuring Loki deployments, setting up storage backends (S3, Azure Blob, GCS), writing LogQL queries, configuring retention and compaction, deploying via Helm, integrating with OpenTelemetry, or troubleshooting Loki issues on Kubernetes.
Provides comprehensive Oracle Cloud Infrastructure (OCI) guidance including compute instances, networking (VCN, load balancers, VPN), storage (block, object, file), database services (Autonomous Database, MySQL, NoSQL), container orchestration (OKE), identity and access management (IAM), resource management, cost optimization, and infrastructure as code (Terraform OCI provider, Resource Manager). Produces infrastructure code, deployment scripts, configuration guides, and architectural diagrams. Use when designing OCI architecture, provisioning cloud resources, migrating to Oracle Cloud, implementing OCI security, setting up OCI databases, deploying containerized applications on OKE, managing OCI resources, or when users mention "Oracle Cloud", "OCI", "Autonomous Database", "VCN", "OKE", "OCI Terraform", "Resource Manager", "Oracle Cloud Infrastructure", or "OCI migration".
OpenTelemetry Collector component configuration. Use when authoring, reviewing, or debugging Collector YAML for a specific receiver, processor, exporter, connector, or extension — config keys, defaults, validation rules, signal support, stability levels, and component-level gotchas. Triggers on Collector component questions including receivers, processors, exporters, connectors, extensions, component renames, signal support, and pipeline wiring.
Use when deploying a database to Zeabur. Use when the user needs MySQL, PostgreSQL, MongoDB, or Redis. Use when the user says “I need a database,” “add database,” “deploy postgres,” “set up MySQL,” “add Redis,” “add MongoDB,” or “connect to database.” Also use when the user mentions data persistence issues such as “data lost after restart,” “data not saved,” “data disappears,” “need persistent storage for data,” or “how to persist data.” Also use when integrating a database with an existing service.
Guides users through distributing Tauri applications to the iOS App Store, including Apple Developer enrollment, Xcode configuration, provisioning profiles, code signing, TestFlight beta testing, and App Store submission processes.
WARNING: Guides IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets); every mutating step is governed by doca-hardware-safety (window, rollback). BlueField-4 only: BlueField-3 bring-up uses doca-bf3-deployment. Use this skill for BlueField-4 (BF4) day-1 platform bring-up from the BMC: installing the BlueField/DOCA bundle ISO onto the DPU (Grace, the Arm complex) over UEFI HTTP Boot, PXE, or Redfish Virtual Media; the PLDM firmware-update flow (BMC, NIC firmware, SBIOS, ERoT) via the Redfish UpdateService and pldmtool; and a Grace Ubuntu image with optional cloud-init. Triggers on BlueField-4/BF4 bring-up phrasing even without “BF4”: {bring up my new BlueField-4}, {the BlueField ISO will not boot over HTTP from the BMC}, {attach BF4 virtual media via Redfish}, {BF4 firmware Task stuck at Running}, {prepare a BlueField-4 host: platform support, version alignment, safest first smoke test}. Route application launch and library API requests to other skills.
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, and counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin, or 5-tuple-to-queue questions even when “DOCA Flow” is not named. Also covers pipe validation before hardware programming, Flow/DOCA version matching, and Flow API errors. First app: follow the local bundle (doca-setup, doca-programming-guide, doca-flow, doca-public-knowledge-map). Stage 1: pull nvcr.io/nvidia/doca/doca (NGC catalog tag, never invent); Stage 2 needs a real NIC. Then ls samples inside the container; never emit main.c, a Dockerfile, or hand-typed -l flags. Route software-only host pipelines, plain DPDK `rte_flow`, kernel TC, OVS, BFB bring-up, and DPU OS installation elsewhere. DPU OS installation is destructive and always requires explicit confirmation.
Migrate workloads from Google Cloud Platform to AWS — including AI and agentic workloads regardless of cloud provider. Triggers on: migrate from GCP, GCP to AWS, move off Google Cloud, migrate Terraform to AWS, migrate Cloud SQL to RDS, migrate GKE to EKS, migrate Cloud Run to Fargate, migrate App Engine to Elastic Beanstalk, Google Cloud migration, migrate from OpenAI to Bedrock, move off OpenAI, switch from ChatGPT API to AWS, migrate from Gemini to Bedrock, migrate LangChain to Bedrock, migrate LangGraph to AWS, migrate agentic workloads to AWS, move AI workloads to AWS, migrate my AI app to AWS. Runs a 6-phase process: discover GCP resources from Terraform files, app code, or billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. Clarify must finish before Design, Estimate, or Generate. Includes AI provider migration guidance (for example, OpenAI to Amazon Bedrock) by selecting closest-fit Bedrock model families for required modality, latency/quality targets, context windows, and cost constraints. Model mapping is compatibility-guided, not 1:1 parity; validate prompts, tool-calling behavior, and eval metrics before cutover. Do not use for: Azure migrations to AWS (see azure-to-aws), on-premises migrations to AWS, AWS-to-GCP reverse migration, general AWS architecture advice without migration intent, GCP-to-GCP refactoring, or multi-cloud deployments that do not involve migrating off GCP.
Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, read and patch its code, start and stop its sandbox, poll status, list versions, delete, and share the app with humans via its PostHog URL. Use when asked to "create a streamlit app", "deploy a data app", "ship a dashboard app", "restart/stop my app", "why is my app not running", or "give me a link to the app".
Used to start, reset, or troubleshoot the XGENT portal Docker one-box local integration environment in the App's own repository; no need to clone or modify the portal source code. Handles image pulling, registration, ports, health checks, and integration troubleshooting.
Upload files to the cloud and get shareable public URLs using stableupload.dev (x402 micropayments). USE FOR: - Uploading files to get public URLs - Sharing files via download links - Hosting images, documents, or any file type - Making files publicly accessible for 7 days or 6 months - Hosting static websites with custom domains TRIGGERS: - "upload this", "share this file", "get me a link" - "host this file", "make this downloadable" - "public URL", "download link", "put online" - "share file", "file hosting", "upload file" - "host site", "deploy site", "static site" ALWAYS use `npx agentcash@latest fetch` for stableupload.dev endpoints — never curl or WebFetch for the purchase step.
ClickHouse cluster migration planner. Use when planning data migration between ClickHouse clusters, including cross-cluster migrations, horizontal scaling, disk downgrade, availability zone changes, or migration from self-built or non-Alibaba Cloud ClickHouse to Alibaba Cloud ClickHouse (Community or Enterprise Edition). Helps analyze migration conditions, select appropriate migration methods, and generate detailed migration plans
Alibaba Cloud EBS Disk Monitoring and Metric Analysis Skill. Query and analyze monitoring metrics for single or multiple cloud disks, supporting time-series aggregation and cross-disk analysis. Triggers: “EBS monitoring”, “disk metrics”, “cloud disk performance”, “IOPS analysis”, “BPS analysis”, “disk monitoring data”, “metric aggregation”.
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.