Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Work with OpenTofu state management in GitLab. Use when managing Terraform/OpenTofu state, configuring state backends, or working with infrastructure as code. Triggers on OpenTofu, Terraform, state management, infrastructure as code, IaC.
DWS cluster high memory root cause diagnosis skill, based on KooCLI v3.2.0+ and DWS Autopilot MCP Server. Automatically collects memory metrics, analyzes root causes (customer-side / system-side), and outputs a standardized diagnosis report. Applicable to scenarios where DWS cluster memory usage is too high, memory alarms, and OOM. Trigger words: 内存高, 内存告警, 内存诊断, 内存使用率过高, 内存不足, OOM, 内存溢出, 动态内存使用率超阈值, high memory, memory alarm, memory diagnosis.
Diagnose post-triage, multi-component Splunk incidents from a supplied privacy-reviewed diagnostic packet. Use to align clocks and symptoms, preserve impact and contradictions, map dependencies, rank and test competing causal hypotheses, request the smallest safe read-only discriminator, validate bounded findings, and hand confirmed component failures to exact specialists. Do not use to collect raw diagnostics, troubleshoot or remediate one component, configure, restart, mutate, stress test, or claim an unverified cause or recovery.
Guide users from zero to their first working mirrord session — check system requirements, install mirrord via CLI, VS Code, or IntelliJ, run a first session against a Kubernetes target, and verify the connection. Use when a user is new to mirrord, wants to install it, needs help running their first session, or wants to debug or test a local process against their Kubernetes cluster.
Cut a full nurb release, one version across the engine and the desktop app. Bumps the four version strings and writes the changelog into one release PR, riding the current branch when work is in flight, then after the merge runs the desktop build and the update feed. Use when the user says "release", "cut a release", "ship it as X.Y.Z", or "push a release".
Expert Kubernetes specialist mastering container orchestration, cluster management, and cloud-native architectures. Specializes in production-grade deployments, security hardening, and performance optimization with focus on scalability and reliability.
Lookup documented AKS fixes only when the prompt includes an exact catalog signature and all of its qualifiers: VMCannotFitEphemeralOSDisk; NodePoolMcVersionIncompatible; 'NodeImageVersion is not accepted'; AKS SkuNotAvailable with size, location, and zone; ZonalAllocationFailed with insufficient zone capacity; OverconstrainedAllocationRequest with listed constraints; nested AKS vmssCSE/CSE VMExtensionError_OutboundConnFail, VMExtensionError_K8SAPIServerConnFail, or VMExtensionError_K8SAPIServerDNSLookupFail; or AllocationFailed with the full cataloged internal-error or insufficient-regional-capacity message. Never use for quota errors, code-only or bare wrappers, generic symptoms, incomplete signatures, or failures outside AKS; use aks-troubleshooting or azure-diagnostics.
Give cited, advisory-only Splunk alert, scheduled-report action, Enterprise Security finding/notable, and risk-workflow readiness guidance from supplied evidence. Use for schedule, trigger, suppression, action, recipient, downstream, ownership, escalation, entitlement, and post-change validation decisions. Route SPL authoring and execution to Splunk Search, broad permissions and object lifecycle to Knowledge Object Governance, and active service incidents to platform operations.
Use when managing Alibaba Cloud Backup and Disaster Recovery Center (BDRC) via OpenAPI/SDK, including the user needs backup/disaster-recovery resource operations, including inventory, policy/configuration changes, status checks, and troubleshooting BDRC workflows.
Azure Machine Learning Workspace and Azure AI Foundry deep dive. PROACTIVELY activate for: (1) creating and configuring Azure ML workspaces, (2) Azure AI Foundry hubs and projects, (3) ML workspace networking (managed VNet, private endpoints, DNS), (4) ML compute clusters and compute instances, (5) managed online endpoints, batch endpoints, Kubernetes endpoints, (6) managed identities for ML resources, (7) ACR integration for custom environments, (8) storage account configuration, (9) az ml CLI v2 commands, (10) PowerShell Az.MachineLearningServices, (11) reading ML compute and deployment logs, (12) GPU SKU selection (ND/NC series, H100/H200/A100). Provides: workspace setup playbook, network-isolation patterns, endpoint deployment templates, az ml CLI cheat sheet, and log diagnosis workflow.
Builds an Azure portal deep link to a specific blade/menu item for supported Microsoft.ContainerService, Microsoft.Kubernetes, and Microsoft.Compute resources using the aks-search-direct-mid semantic search API. WHEN: 'find where in the Azure portal to do something', 'search the portal for an operation', 'construct a portal link from a search query and a resource'.
Use when creating Autonomous Databases, troubleshooting connection failures, managing PDBs, or optimizing database costs. Covers connection string confusion, password validation errors, stop/start cost traps, clone type selection, and backup retention gotchas.
Diagnose Splunk forwarder and data-ingest paths from sanitized, read-only evidence. Use for Universal or Heavy Forwarder transport, deployment-client effects on ingestion, HEC and other inputs, parsing and timestamps, event boundaries, routing, sourcetype or index mismatches, missing, delayed, duplicated, or dropped events, and queues or backpressure in Splunk Cloud Platform or Splunk Enterprise; do not use for live mutation, broad architecture, fleet policy, HEC token administration, search-time extraction, or provider-owned remediation.
Audit and improve GitHub Codespaces efficiency. Use this skill when a user wants faster Codespaces startup, lower Codespaces spend, slim devcontainers, right-size machines, tune idle timeout, or scope prebuilds to branches with sustained usage.
Azure Key Vault + CSI Driver integration for Kubernetes secrets management. Use when creating SecretProviderClass resources, mounting secrets from Key Vault, troubleshooting 403 errors, syncing secrets to K8s, or configuring applications to use Key Vault secrets.
This skill should be used when users need to interact with Kubernetes clusters via kubectl CLI. It covers pod management, deployment operations, log viewing, debugging, resource monitoring, scaling, ConfigMaps, Secrets, Services, and all standard kubectl operations. Supports multiple clusters (production, staging, local k3s) with predefined aliases. Triggers on requests mentioning Kubernetes, k8s, pods, deployments, containers, or cluster operations.
Query Kubernetes, infrastructure and cloud-provider metrics from KubeSense with PromQL/MetricsQL — metric discovery, label inspection, the metric families KubeSense actually collects (kube-state-metrics, cAdvisor, node-exporter, OTel hostmetrics, DCGM GPU, JVM, and AWS/GCP/Azure/MongoDB Atlas/Confluent/Kong cloud resources), and the label conventions (clusterId, kubesense_cloud_resource_metric) needed to write a query that returns data.
Distributed systems expert specializing in service decomposition, orchestration, and microservices architecture patterns. Use when designing microservices, defining service boundaries, implementing service mesh, or handling distributed system challenges. Triggers include "microservices", "service mesh", "service decomposition", "distributed systems", "API gateway", "event-driven".
Select, run, and govern NVIDIA Cosmos world-video generation across Cosmos 3 Generator, Predict2.5, Transfer2.5, downloadable checkpoints, self-hosted NIMs, and hosted preview surfaces. Use for text/image/video-to-world, controlled world transfer, multiview or action-conditioned physical-AI video, local checkpoint pinning, hardware planning, inference approval, and output validation; do not use for Cosmos Reason/Embed-only tasks.
Configuration and login management for the SwanLab experiment tracking platform. Trigger scenarios: (1) configure SwanLab login credentials (2) install/log in to SwanLab inside a container (3) configure SwanLab for a specified container (4) check SwanLab connection status. Supports multiple configuration sources: environment variables, config files, interactive input. Can be called by other skills via source scripts/functions.sh.
Turborepo monorepo build system and orchestration. Covers task pipelines, dependsOn syntax, caching configuration, remote cache, filtering, CI optimization, environment variables, workspace management, watch mode, package boundaries, and code generation. Use when configuring tasks, creating packages, setting up monorepo, sharing code between apps, running changed packages, debugging cache, optimizing CI, resolving workspace dependencies, enforcing package boundaries, or generating code.
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
Collects bounded packet captures from AKS nodes and Azure network configuration for wire-level evidence. WHEN: \"capture packets on an AKS node\", \"take a pcap\", \"run tcpdump on AKS\", \"prove where packets drop\". Use for explicit packet-capture intent after read-only diagnostics, not general AKS connectivity or ingress troubleshooting.
Use when managing Alibaba Cloud Data Lake Formation (DlfNext) via OpenAPI/SDK, including the user needs DLF Next catalog/governance resource operations, including listing resources, create/update flows, status checks, and troubleshooting metadata workflow issues.
Resource saturation from system.metrics, system.events and system.asynchronous_metrics - memory, load average, connections, running queries, background pools, parts per partition, block device queues - plus short history. Use when the server feels slow or overloaded, queries queue or get rejected, or load and connection trends are needed.
Actorization converts existing software into reusable serverless applications compatible with the Apify platform. Actors are programs packaged as Docker images that accept well-defined JSON input, perform an action, and optionally produce structured JSON output.
Send, receive, and manage email at scale with Amazon Simple Email Service (SES). Use when building email sending, identity verification, deliverability monitoring, email validation, tenant management, or multi-tenant email platforms. Covers V2 API patterns, DKIM/SPF/DMARC authentication, configuration sets, suppression lists, bounce/complaint handling, and dedicated IP management.
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.
Build dumb-pipe and traffic-filtering C2 redirectors with nginx (proxy_pass) and Apache (mod_rewrite), deriving filter rules from a Malleable C2 profile, layering Let's Encrypt TLS, and applying OPSEC controls like domain fronting and UA/geo filtering. Use when standing up red-team C2 that must survive blue-team triage or ensuring only profile-matching implant traffic reaches the hidden team server.
When designing distributed systems for scalability, reliability, and consistency. Covers CAP/PACELC theorems, consistency models (strong, eventual, causal), replication patterns (leader-follower, multi-leader, leaderless), partitioning strategies (hash, range, geographic), transaction patterns (saga, event sourcing, CQRS), resilience patterns (circuit breaker, bulkhead), service discovery, and caching strategies for building fault-tolerant distributed architectures.
Detects container escape at runtime across tooling - namespace manipulation, capability abuse, kernel exploits, sensitive host mounts, and anomalous syscalls - and explains which signals matter regardless of whether Falco, Sysdig, auditd, or an EDR is doing the collection. Use when deciding what breakout behaviour to monitor, investigating a suspected Docker or Kubernetes breakout, or comparing escape coverage across runtime sensors. Keywords: container escape, breakout, namespaces, CAP_SYS_ADMIN, privileged, hostPath, kernel exploit, syscall. Do not use for Falco rule syntax itself - use detecting-container-escape-with-falco-rules; for a static configuration sweep use performing-container-escape-detection.
Guidance for running AI/ML workloads on Docker. Covers Docker Model Runner (docker model pull/run for local LLMs), Docker Agent (multi-agent orchestration for coding tasks), Docker Sandboxes for isolated AI agent execution, GPU acceleration (nvidia-container-toolkit, --gpus flag), AI model serving with Docker, and running open-source LLMs (Llama, Gemma, Qwen) locally. Use when the user asks about docker ai, docker model runner, local LLM, docker agent, GPU docker, sandbox, model serving, or needs to deploy AI models with Docker. 使用场景：docker ai、model runner、本地 LLM、docker agent、GPU docker、sandbox、AI 模型部署。
Publish any Freshworks Platform 3.0 custom app via MCP tools: fdk validate/pack, app-upload, and submit/update through openai-server. Pre-publish: confirm Developer JWT matches manifest product modules (Freshdesk support_* vs Freshservice service_*; multiproduct sequential). At publish time, ask new vs existing listing; for new listings, prompt for supportEmail before create_app_upload_url (required for submit_custom_app). list_custom_apps for updates so the developer selects appId, then MCP handover (submit_custom_app or add_app_version with uploadId). Use when the user wants to push an app to the Marketplace (test), check publish status, or list existing apps. Pair with fw-app-dev for manifest or module fixes. Works with Cursor, Claude Code, and any MCP-compliant client.
Manage SSH deploy keys for GitLab projects including add, list, and delete operations. Use when setting up deploy keys for CI/CD, managing read-only access, or configuring deployment authentication. Triggers on deploy key, SSH key, deployment key, read-only access.
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.