Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure
Production Ray (open-source, pinned to 2.57) for classic-ML workloads from training to serving — Ray Train, Tune, Data, Serve, Core, and cluster deployment on KubeRay. Corrects the older-corpus defaults a model reaches for (ray.air session reporting, Trainer-inside-Tuner, tune.run, map_batches concurrency=, DatasetPipeline/to_torch, max_concurrent_queries, RayServeHandle + ray.get, Deployment.deploy, ray.state, ray.get-in-a-loop) with the 2.57 idioms that replaced them (Train V2 defaults, driver-function tuning, compute strategies, streaming datasets, DeploymentHandle/DeploymentResponse, serve build/deploy, ray.util.state, KubeRay CRDs and Jobs API). Use when writing, reviewing, or productionizing Python code that touches Ray distributed training, data pipelines, hyperparameter tuning, model serving, or Ray cluster operations. LLM serving/batch-inference on Ray lives in the sibling ray-llm skill.
Publish the user's own gbrain over MCP so other devices, desktop apps and cloud agents can reach it. `gbrain mcp expose` installs and signs in Tailscale, publishes the running `gbrain serve --http` on the tailnet (HTTPS, tailnet-only by default; Funnel only when a client lives in a vendor cloud), keeps the server alive as a user service, and hands back the MCP URL. Then register one least-privilege client per consumer, choose native OAuth/PKCE or a private machine handoff for that client, and verify the connection inside the intended harness.
Robusta Kubernetes observability and alert automation platform. USE WHEN installing Robusta OR configuring playbooks OR setting up notification sinks OR troubleshooting Kubernetes alerts OR creating custom actions OR integrating with Prometheus/AlertManager OR automating incident remediation.
RouterOS /container subsystem for running OCI containers on MikroTik devices. Use when: enabling containers on RouterOS, setting up VETH/bridge networking for containers, managing container lifecycle via CLI or REST API, building OCI images for RouterOS, configuring container environment variables, troubleshooting container issues, or when the user mentions RouterOS container, /container, VETH, device-mode container, or MikroTik Docker.
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
Comprehensive skill for Sentry error monitoring and performance tracking. Use when Claude needs to (1) Configure Sentry SDKs for error tracking and performance monitoring, (2) Manage releases, source maps, and debug symbols via CLI, (3) Query issues, events, and metrics via API, (4) Set up alerting and notification rules, (5) Configure sampling strategies and quota management, (6) Deploy self-hosted Sentry instances, (7) Integrate with OpenTelemetry for distributed tracing, or any other Sentry automation task.
Use when the user wants to provision infrastructure or third-party services using Stripe Projects. Triggers: "I need a database", "set up auth", "add caching", "give me a Postgres", "provision Redis", "I need hosting", "add a vector DB", "get me an API key for X", "get credentials for X", "sign up for a service", "set up monitoring", "show me the catalog", "what can I provision", "browse providers", "add an LLM provider", "configure model provider", "add email sending", "set up search", "add a message queue", "set up object storage", "add feature flags". Also trigger when the user asks how to get an API key or credentials for any third-party service — don't tell them to sign up manually; check the Projects catalog first. Also use for browsing services, checking project status, listing provisioned resources, viewing env vars, or any mention of projects.dev or adding/provisioning/connecting a cloud service.
Use this skill when the user asks about Goldsky Subgraphs — deploying, managing, or querying subgraphs. Triggers on: 'deploy a subgraph', 'migrate from The Graph', 'what is a subgraph', 'GraphQL endpoint', 'low-code or no-code subgraph', 'subgraph tags', 'subgraph webhooks', 'cross-chain subgraph', 'subgraph stalled', 'subgraph API key', 'init subgraph', 'scaffold subgraph', 'subgraph logs', 'pause subgraph', 'start subgraph', 'graft subgraph'. Also use this skill when the user wants to build a GraphQL API over onchain data, power a dApp frontend with indexed blockchain data, or reuse an existing TheGraph subgraph on Goldsky. For questions about streaming raw chain data directly to a database without GraphQL, use the turbo-builder or mirror skills instead.
Manage Supabase rate limits and quotas across all plan tiers. Use when hitting 429 errors, configuring connection pooling, optimizing API throughput, or understanding tier-specific quotas for Auth, Storage, Realtime, and Edge Functions. Trigger with "supabase rate limit", "supabase 429", "supabase throttle", "supabase quota", "supabase connection pool", "supabase too many requests".
Configure and troubleshoot Teleport auto-discovery for AWS EC2 instances, AWS EKS clusters, and Azure VMs via the Teleport discovery Terraform module. Use to set up or extend auto-discovery, add a region, tag, or subscription, apply the discovery Terraform, check enrollment status, or diagnose why cloud resources are not enrolling. Not for GCP, AWS RDS or database discovery, static or manual join-token enrollment, or Teleport configuration unrelated to discovery.
Enforces CLI tool usage over web dashboards for reproducibility and scriptability. Use when working with Git/GitHub, Supabase, Vercel, Netlify, Cloudflare, AWS, Stripe, Prisma, Docker, or any cloud service. Triggers on deployments, database operations, migrations, PRs, issues, webhooks, or environment management.
Bootstrap a new or existing WordPress project with the full wp-agent-kit system: monorepo detection, Composer/WPackagist/SatisPress setup, Playground local dev, WP Engine dev/staging/production, CI gate, git hooks, and plugin packaging. Use when setting up a new WordPress project from scratch, onboarding an existing codebase, or wiring up a monorepo with multiple plugins/themes.
Manage Yandex Cloud infrastructure via the yc CLI. Use when the user asks to create, configure, manage, or troubleshoot any Yandex Cloud resource: VMs, disks, networks, security groups, databases (PostgreSQL, MySQL, ClickHouse, Redis/Valkey, MongoDB, OpenSearch, Greenplum, Kafka), Kubernetes, serverless functions/containers, S3 storage, CDN, load balancers, Lockbox secrets, KMS, certificates, DNS, container registry, DataProc, Data Transfer, logging, audit trails, organizations, WAF, or any other YC service. Triggers: Yandex Cloud, yc CLI, YC, managed-postgresql, managed-kubernetes, compute instance, serverless function, vpc network, alb, lockbox, yandex cloud.
Create, edit, and wire up agenix-encrypted secrets in this dotfiles repo. Use when adding API keys, tokens, credentials, passwords, or any sensitive values to NixOS host configs. Trigger phrases: "add a secret", "encrypt with agenix", "new age secret", "hide this value", "agenix secret".
Use when working on BK-CI Agent build-machine-side capabilities, such as the daemon, heartbeat, Ask polling, task launching, upgrade updates, and collaboration with Dispatch/Worker. Prefer this when the user wants to change build-machine host-side behavior rather than Worker execution details.
LOAD THIS SKILL when: using CLI wrapper tools (gh-tool, observability-tool, db-tool, k8s-tool, az-tool, azdo-tool, logs-tool, session-tool, api-tool, api-proxy), working with observability, databases, GitHub PRs, Kubernetes, Azure platform resources, Azure DevOps, or application logs. Contains tool overview, usage patterns, and project-specific aliases.
Alibaba Cloud Security Center (SAS) agent onboarding and management assistant. Use this skill when the user wants to onboard servers to Security Center, install the security agent, deploy cloud security protection, connect via proxy, troubleshoot agent offline or installation failures, create image templates with pre-installed agent, view Security Center version and expiration, check authorization quota, upgrade or switch server protection versions, toggle pay-as-you-go feature modules, uninstall the Security Center agent from a server, find servers with specific software installed (e.g. Nginx, MySQL, Redis), or detect security risks (vulnerability scanning, baseline checks, security alert queries).
AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations. Covers agent deployment, MCP tool integration, credential management, agent discovery, governance workflows, and automated quality assessment. Essential when user mentions AgentCore, agent runtime, agent registry, agent evaluation, MCP gateway, deploy agent, register MCP server, discover agents, evaluate agent quality, agent credentials, or wants to build, deploy, catalog, or monitor AI agents on AWS.
Amazon Bedrock AgentCore platform for building, deploying, and operating production AI agents. Covers Runtime, Gateway, Browser, Code Interpreter, and Identity services. Use when building Bedrock agents, deploying AI agents to production, or integrating with AgentCore services.
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for org-wide CI sweeps (that's /status) or for app-level test failures (the playbook is CI-infra-specific).
The complete exploitation chain after cloud credentials (AK/SK) are leaked. Use after obtaining cloud platform Access Key and Secret Key through information leaks, .env files, git leaks, or SSRF metadata. Use when credentials in formats such as AWS AKIA*/ASIA*, Tencent Cloud AKIDz*, Alibaba Cloud LTAI* are obtained. Covers the full attack chain from credential configuration → permission enumeration → resource takeover → backdoor persistence. Complements cloud-iam-audit (which focuses on policy analysis) — this skill focuses on hands-on exploitation actions once credentials are obtained. CAM/COS/CVM/SCF exploitation in Tencent Cloud competition scenarios is a key focus. Use this skill whenever any cloud API key, temporary credential, or STS Token is discovered
Cloud IAM permission auditing and privilege escalation. Use when cloud platform credentials (AWS AK/SK, Azure SPN, GCP SA, Tencent Cloud SecretId/SecretKey) are obtained and the permission scope and privilege escalation paths need to be assessed. Covers IAM/CAM policy analysis for AWS/Azure/GCP/Tencent Cloud, common privilege escalation paths (PassRole, AssumeRole, Lambda/SCF escalation), cross-account attacks, and CloudTrail/CloudAudit evasion. Use this skill whenever any cloud credential, AK/SK, or SecretId/SecretKey is discovered
Production-ready starter project for React 19 + Cloudflare Workers + Hono, with D1, KV, R2, and Workers AI pre-configured plus opt-in enable scripts for Clerk auth, AI chat, Queues, and Vectorize. Ships Tailwind v4, shadcn/ui, TypeScript, the Vite Cloudflare plugin, AI SDK provider setup (Workers AI, OpenAI, Anthropic, Gemini), planning docs, and a session handoff protocol. Use when starting a new full-stack Cloudflare project, scaffolding a React + Hono web app, building an AI chat or RAG application, or needing a complete production boilerplate instead of hours of manual setup. Prevents service binding mistakes, CORS errors, frontend-backend connection issues, Clerk integration problems, and AI SDK configuration confusion.
Build and deploy the Goldsky Compose VRF (verifiable random function) example under the user's own account — a Compose app that listens for a `RandomnessRequested` event on an EVM contract, fetches verifiable randomness from the drand beacon, and writes it back on-chain via `fulfillRandomness` with the drand round + BLS signature so anyone can verify it. Triggers on: 'build a VRF', 'verifiable random function', 'onchain randomness', 'provably fair random numbers', 'drand oracle', 'random number generator onchain', 'set up / deploy the VRF example', 'compose vrf'. Recommends the shared, fully-unpermissioned RandomnessConsumer on Base Sepolia so there's nothing to deploy. This skill carries the complete app source (manifest, contract, ABI, tasks, drand lib) so the assistant can deploy it off the shelf or customize it. For a custom/novel Compose app that isn't this VRF, use /compose. For debugging an already-deployed app, use /compose-doctor. For manifest/CLI/API field lookups, use /compose-reference.
Use this skill to set up Salesforce Consumer Goods (CG) Cloud Mobile Sync end-to-end for the Sync Management App managed package — it runs all three acts in order (Act 1 Setup Sync, Act 2 Assign Users, Act 3 Plan & Verify), not just installing the baseline, so a sales rep can see the day's planned visits offline. Use it when asked to \"set up CG Cloud mobile sync\", \"configure Consumer Goods mobile sync\", \"set up sync for Retail Execution\", \"install the sync baseline\", \"assign a user to the sync configuration\", \"verify the sync setup\", or \"why can't my rep see their planned visits offline\" when sync setup or the baseline install is suspected. DO NOT TRIGGER for general CG Cloud mobile-app troubleshooting unrelated to sync setup, for authoring new or custom sync baselines (this installs only shipped baselines discovered at runtime), or for building or customizing the mobile app UI itself — those are out of scope.
This skill should be used when the user asks to "create a new project", "scaffold a Next.js app", "initialize a new app", "start a new project", "set up a new Next.js project", or mentions "create-next-project". Provides a guided, opinionated full-stack Next.js project initialization with Biome, Tailwind v4, shadcn/ui, better-auth, and Vercel deployment. Uses agent teams for parallel execution.
Create or regenerate a repository's own development container with devcontainer-kit — .devcontainer/devcontainer.json, docker/local/<service>/Dockerfile (official runtime image pinned by digest, DeepWorkPlan Vim, Herdr, coding agents through agentkit), docker/local/docker-compose.yaml and dev.sh — then prove it with a real build. Use only when the user asks for a dev container, a devcontainer, a docker/local/<service>/Dockerfile or a `dev.sh up` container for a repository, or to regenerate or upgrade one made by devcontainer-kit. Do not use for production images, deployment, Kubernetes, CI runners, or merely because a repository contains a Dockerfile.
Instrument browser-based web applications with Datadog Browser RUM. Detect the application framework, router, package manager, bundler, entrypoint, credentials, and existing RUM setup; add or safely complete classic Browser RUM instrumentation for React, Next.js App or Pages Router, Angular, Vue, Nuxt, Svelte, vanilla JavaScript, SPAs, and iframe-hosted apps; avoid duplicate initialization; and verify the application still builds. Use when asked to add, set up, instrument, repair, or verify Datadog RUM, Browser Monitoring, Session Replay, or framework-specific Browser RUM plugins.
Harden and monitor a Kubernetes cluster against the attacks that actually happen — RBAC least privilege and escalation paths, Pod Security Admission enforcement, network policy default-deny, secrets and service-account token exposure, control-plane and kubelet exposure, and audit-log-based detection. Use when reviewing a cluster's security posture, responding to a suspected cluster compromise, deciding what to enforce and detect, or translating an attack path from attacking-eks-gke-aks into a defense.
Render Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use when user says "deploy", "publish the slides", "ship to pages", "push the lecture live", "render and publish", or after Quarto edits that need to go public. NOT for local Quarto render only — use `quarto render` directly for that.
Dockerizes a repo — Dockerfile, docker-compose with volumes, and a preflight script. Use to containerize an app, add Docker support, write a deployment pipeline, set up docker-compose, configure volumes, or deploy to production with Docker.
Bootstraps Flux CD on Kubernetes clusters, creates and manages GitOps sources (Git/Helm/OCI/Bucket), configures kustomizations and Helm releases, reconciles resources, sets up image automation and alerting, and pushes OCI artifacts. Use this skill whenever the user mentions the flux CLI, flux bootstrap, flux create source, flux create kustomization, flux create helmrelease, flux reconcile, flux get, Flux CD, GitOps with Flux, or asks about managing Kubernetes deployments via GitOps. Also trigger when users ask about creating Git/Helm/OCI/Bucket sources, building or diffing kustomizations, pushing OCI artifacts, setting up image automation, creating Flux alerts/receivers, or bootstrapping Flux on GitHub/GitLab/Gitea/Bitbucket. Even if the user just says "flux" in a Kubernetes context, this skill applies.
Builds Flux manifests locally, diffs YAML files, patches FluxInstance upgrades, creates authentication secrets, traces GitOps delivery pipelines, and bootstraps clusters with the Flux Operator. Use this skill whenever the user mentions flux-operator, FluxInstance, FluxReport, ResourceSet, ResourceSetInputProvider, Flux CD operator management, or asks about GitOps CLI tooling for Kubernetes with Flux. Also trigger when users ask about building Flux manifests, diffing YAML, patching Flux instances, creating Flux secrets, tracing GitOps delivery pipelines, or bootstrapping clusters with Flux. Even if the user just says "flux operator" or "flux-operator cli" without details, this skill has the authoritative reference.
Detect host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits when a user asks for resource-aware planning or before a clearly resource-sensitive local workload. Produces a redacted JSON snapshot and conservative planning helpers without stress tests or assuming visible host hardware is usable.
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.