Cloud Infrastructure Bundle

Skills to manage, configure, and secure cloud infrastructure and services.

Browse all skill bundles

Included Skills (100)

  1. Nemo Automodel Launcher Config — Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
  2. Vercel Token Manager — This tool enables developers to deploy and manage Vercel projects seamlessly by automating authentication through environment-based access tokens instead of interactive logins.
  3. Jetson Customize Nvpmodel — Use when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target. Triggers: edit power mode, tune frequency caps.
  4. Tilegym Converting Cutile To Triton — Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.
  5. Tao Run On Slurm — Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed
  6. Gke Workload Security — Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (`audit_cluster.sh`), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (`gVisor`), enforcing Pod Security Standards (`restricted` labeling) and pod securityContext, and mounting Secret Manager secrets via CSI (`SecretProviderClass`). Use when auditing workload security posture, isolating namespaces, applying pod security standards, or configuring network policies and secret volume mounts. Don't use for Workload Identity (use gke-workload-identity), cluster-wide control plane security, RBAC hardening, Binary Authorization, Shielded Nodes, or enabling platform-level GKE add-ons (use gke-platform-security instead).
  7. SageMaker Container Selector — This tool identifies the optimal HuggingFace-curated SageMaker serving container and retrieves the correct image URI to ensure reliable, region-specific model deployments for developers.
  8. Gke Service Networking — The Gke Service Networking skill configures edge networking, traffic routing, load balancing, and private service endpoints for GKE clusters. It is used when setting up Gateway API manifests, standard Ingress, Cloud Armor WAF policies, Container‑Native Load Balancing, Private Service Connect, or Google‑managed SSL certificates, and it helps troubleshoot 502/5xx errors, backend health‑check failures, connection draining, and TLS/SSL policy enforcement. The skill is not intended for core cluster IP planning, Dataplane V2 network policies, or node NAT egress.
  9. AWS Infrastructure Explorer — This tool enables developers to query AWS resource configurations and metadata using natural language while strictly maintaining a read-only safety posture.
  10. Jetson Promote Image — Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.
  11. Azure Cost Optimizer — This tool analyzes Azure infrastructure and IaC files to identify savings opportunities, automatically tracking them through GitHub issues for efficient cost management.
  12. Nemo Relay Plugin Build — Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed `rust_dynamic` native or `worker` gRPC plugin, with deterministic validation and rollback-safe registration.
  13. Doca Gpunetio Ib Write Lat — Use this skill when the user characterizes RDMA WRITE round-trip time posted from a CUDA kernel via GPUNetIO — compiling `gpunetio_ib_write_lat` under `doca/tools/`, verifying GPU–NIC affinity, and interpreting the half-iteration / full-iteration / nanosecond columns for median / p99 / tail-jitter analysis of a real-time control loop. Also load it for implied asks like "p99 WRITE time on H100 + ConnectX", "tail delay versus batching", or "device-originated versus upstream ib_write_lat". Refuse and route to the proper owner for throughput runs (doca-gpunetio-ib-write-bw), the GPI channel API (doca-gpi), GPUNetIO API work (doca-gpunetio), or SDK setup.
  14. Doca Gpunetio Ib Write Bw — Use this skill when the user is building or interpreting the doca/tools/gpunetio_ib_write_bw tool pair — a CUDA kernel posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE BW on a GPU+IB-device pair. Trigger even without the tool name — typical phrasings: "measure WRITE BW when the GPU posts the WRs", "BW swings run to run on the same flags", "is the NIC saturated or am I bound on the CUDA kernel", "meson compile fails for the GPUNetIO bw tool", "nvidia_peermem isn't picking up my GPU buffer", or "GPU-posted WRITE BW vs the CPU path". Refuse and route elsewhere for general doca-gpunetio library work, DOCA setup, the GPU-posted WRITE latency analog, CPU-posted RDMA benchmarking (doca-perftest), and app-level end-to-end rates.
  15. Jetson Link Docs — Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading.
  16. Doca Gpunetio — Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.
  17. Macos Menubar Tuist App — The skill builds and maintains a macOS menu bar application using Tuist, generating a SwiftUI MenuBarExtra project without a Dock icon. It configures menu or panel presentation, state handling, quit and settings items, launch-at-login, and dependency management with automated rebuild and relaunch from the terminal. This service is ideal for developers who need a lightweight status bar utility that integrates seamlessly with Tuist and SwiftUI.
  18. Foundationpose Setup — Install or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines. Use for SAM3/TAO dependency conflicts, CUDA library failures, and depth-engine shape or precision decisions.
  19. AWS Cloudfront — Configure Amazon CloudFront for global content delivery. Set up distributions with S3 and ALB origins, define cache behaviors and TTLs, invalidate cached content, and use Lambda@Edge for request/response manipulation at the edge.
  20. Azure AI Translation Ts — Text and document translation with REST-style clients.
  21. Vercel Infrastructure Manager — Streamline Vercel platform operations including deployments, domains, and environment variables for developers using the Rube MCP integration for automated cloud management.
  22. Industrial Control Threat Detection — This skill identifies sophisticated cyber-physical attacks by monitoring PLC logic integrity and process anomalies to protect critical infrastructure from nation-state level threats.
  23. Tracking Threat Actor Infrastructure — Discovers and maps adversary-controlled infrastructure (C2 servers,
  24. Zed — High-Performance Code Editor — Zed is a high‑performance, GPU‑accelerated code editor written in Rust that delivers AI‑powered editing and real‑time collaboration, enabling developers to configure language‑specific formatters, connect AI providers such as Anthropic or Ollama, and share projects with teammates while extending functionality with WebAssembly modules. It is ideal for teams that need a fast, extensible editor that seamlessly integrates AI assistance and collaborative workflows.
  25. Implementing Cloud Security Posture Management — Continuously monitor multi-cloud environments (AWS, Azure, GCP) for
  26. Sentry Workflow Automator — This tool streamlines Sentry error tracking and project monitoring for developers by automating issue triage, alert configuration, and release management tasks via Rube MCP.
  27. AWS VPC Designer — Designs and implements secure VPC networking for AWS infrastructure, helping DevOps engineers.
  28. Cloud SQL Manager — Provisions and manages Cloud SQL instances on Google Cloud, simplifying relational database administration for developers and database administrators.
  29. Azure Mgmt Apimanagement Dotnet — Azure Resource Manager SDK for API Management in .NET.
  30. S3 Exfiltration Detector — This tool identifies unauthorized bulk data transfers and suspicious access patterns in AWS S3 buckets to help security teams mitigate potential data breaches.
  31. Alarm Resistor Calculator — Calculates and validates end-of-line resistor loops for intrusion alarm systems with wire gauge compensation.
  32. Performing Power Grid Cybersecurity Assessment — Conduct cybersecurity assessments of power grid infrastructure spanning generation, transmission substations, distribution, and EMS control centers, covering NERC CIP compliance verification, IEC 61850 (GOOSE/MMS) substation protocol analysis, and synchrophasor (PMU) network security against threats like Industroyer/CrashOverride. Use for periodic NERC CIP assessments, substation automation or EMS/SCADA security reviews, or regional entity compliance audits; not for non-BES systems or generic OT assessments without power grid specifics.
  33. DNS Configuration — Helps DevOps engineers configure and manage DNS zones, records, and security policies.
  34. Performing S7comm Protocol Security Analysis — Perform security analysis of Siemens S7comm and S7CommPlus protocols
  35. Cdn Setup — Configure CDNs for content delivery. Set up CloudFront, Cloudflare, and
  36. Azure EventGrid Client — This .NET library enables developers to publish and consume events within Azure Event Grid, facilitating robust event-driven architectures and pub/sub messaging workflows.
  37. Azure Document Translator — This tool enables developers to perform large-scale batch document translation while preserving original formatting across various file types using Azure AI services.
  38. Microsoft Teams — Build bots, automate workflows, and manage Microsoft Teams programmatically via Microsoft Graph API. Use when someone asks to "build a Teams bot", "automate Teams messages", "create Teams channels", "integrate with Teams", "Teams webhook", "send Teams notifications", "manage Teams meetings", or "Teams app development". Covers Graph API for messaging, channels, meetings, bots with Bot Framework, incoming webhooks, and Power Automate integration.
  39. Hono Web Framework — This skill enables developers to build high-performance, type-safe web APIs and full-stack applications that run seamlessly across all modern edge and server runtimes.
  40. Industrial Anomaly Detector — This tool deploys machine learning to analyze OT network traffic and process models, helping security engineers identify deviations and rogue devices in industrial environments.
  41. Gke AI Troubleshooting Tpu Dynamic Slices Monitoring — 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).
  42. Edge Function Deployer — Builds and deploys serverless functions to Cloudflare's global edge network for developers.
  43. Gke Networking — Plans, configures, and manages core GKE cluster networking. Covers private clusters, VPC-native configurations, DNS, node egress, Dataplane V2, and IP planning. Use when designing GKE networking layouts, configuring private clusters, setting up Dataplane V2, planning GKE IP ranges, or managing VPC- native cluster modes. Don't use for application ingress, load balancing, or service networking (use gke-service-networking instead).
  44. Gpu Kubernetes Operations — Operate GPU-backed Kubernetes clusters for AI inference and training
  45. Gke AI Troubleshooting Tpu Vbar Oom — Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbar_control_agent crashes, memory cgroup OOMs in serial console logs, tpu-device-plugin metrics checksum corruption errors, or custom TPU metrics collection conflicts on GKE TPU v6e nodes. Don't use for general non-TPU container OOM troubleshooting or standard GKE node lifecycle operations.
  46. Cloudformation — Deploy AWS resources with CloudFormation templates. Create stacks, use
  47. AWS Rds — Provision and manage RDS databases. Configure backups, replication, and
  48. Render — Deploys web apps, APIs, static sites, workers, cron jobs and Postgres on Render, the cloud platform configured through a render.yaml Blueprint. Use when a user asks to host an app on Render, write or fix render.yaml, wire environment variables between services, set up auto-deploy from Git, autoscale, add a custom domain, or trigger deploys with the Render API or CLI.
  49. LeCun Debate Persona — This skill adopts Yann LeCun's persona to provide technical critiques of LLMs and analyze his intellectual debates regarding AI safety and development.
  50. Hardening Linux Endpoint With Cis Benchmark — Hardens Linux endpoints using CIS Benchmark recommendations for Ubuntu,
  51. Implementing Attack Surface Management — Implements external attack surface management (EASM) using Shodan, Censys,
  52. Nemo Rl Auto Research — Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
  53. AWS CDK Initializer — This skill provides developers with a comprehensive guide to configuring environments, initializing projects, and deploying infrastructure using AWS CDK with Python.
  54. AWS Cost Optimizer — This tool analyzes AWS infrastructure and IaC files to identify savings opportunities, automatically generating GitHub issues to streamline cloud cost reduction efforts.
  55. AWS RDS Manager — This skill manages Amazon RDS databases, automating provisioning, backups, and scaling for developers and database administrators.
  56. Namecheap — Manage DNS records for domains registered with Namecheap via their API. List domains, view/add/update/remove DNS host entries (A, AAAA, CNAME, MX, TXT, etc.), and guide users through API setup including public IP detection and credential configuration. Use when the user mentions Namecheap, DNS records, domain management, or wants to add/change/remove A records, CNAME records, MX records, or TXT records for their domains.
  57. MCP Server Creator — Generates a complete Python MCP server with typed tools and tests for AI clients.
  58. Tao Mine Nearest Neighbors — Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files. Use when a workflow needs to mine source samples closest to target samples.
  59. Azure Identity Authenticator — This tool assists Rust developers in implementing secure Microsoft Entra ID authentication for Azure SDK clients using official library credentials.
  60. Omniverse Realtime Viewer — Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.
  61. Jetson Video Recipe — Use when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.
  62. OneDrive File Automator — Streamline OneDrive file management, folder operations, and permission settings for users by leveraging the Rube MCP toolkit for efficient cloud storage control.
  63. Cloud Storage Specialist — This expert assistant helps developers implement secure, high-performance file upload systems using presigned URLs, multipart streaming, and robust server-side validation techniques.
  64. Odoo Backup Strategy — Complete Odoo backup and restore strategy: database dumps, filestore backup, automated scheduling, cloud storage upload, and tested restore procedures.
  65. N8n Workflow Orchestrator — This router streamlines n8n MCP workflow development, testing, and debugging by directing tasks to specialized guidance for developers and automation engineers.
  66. LinkedIn Growth Assistant — This tool helps professionals expand their LinkedIn reach by generating strategic comment rosters and crafting personalized outreach messages while strictly adhering to platform safety limits.
  67. Universal Server Builder — Build server-side applications deployable to multiple platforms with Nitro, ideal for developers creating APIs or full-stack applications.
  68. Celery Task Manager — Executes asynchronous tasks using Celery, assisting Python developers with background processing, task scheduling, and queue management for improved application performance.
  69. Cloudflare CLI — A command-line interface for managing Cloudflare resources and deploying Workers projects.
  70. File Upload Processor — When the user needs to build file upload functionality for a web application. Use when the user mentions "file upload," "image upload," "upload endpoint," "multipart upload," "presigned URL," "S3 upload," "file validation," "upload to cloud storage," or "accept user files." Handles upload endpoints, file validation (type, size, magic bytes), cloud storage integration, and upload status tracking. For bucket setup and presigned URLs in depth, see s3-storage.
  71. Multi Source Search — Cross-validate web research and produce an offline-checkable evidence ledger with explicit source diversity, confidence, conflicts, and gaps.
  72. Deed Page — Publish an HTML file or static folder to a permanent public https://<slug>.deed.page/ URL with one curl request. No account; the first publish returns a token for updates.
  73. Multiplayer — Multiplayer game development principles. Architecture, networking, synchronization.
  74. Using Neon — Neon is a serverless Postgres platform that separates compute and storage to offer autoscaling, branching, instant restore, and scale-to-zero. It's fully compatible with Postgres and works with any language, framework, or ORM that supports Postgres.
  75. MacOS Container Manager — This tool enables developers to build and manage OCI-compliant containers as lightweight virtual machines on Apple Silicon without requiring a Docker daemon.
  76. Experiment Design Assistant — This skill helps product teams design, prioritize, and analyze A/B tests with statistical rigor for data-driven decisions.
  77. K8s Cost Optimizer — Analyzes Kubernetes resource usage to identify waste and generate right-sizing recommendations for administrators.
  78. Go gRPC Architect — This skill assists Go developers in designing and implementing secure, high-performance gRPC microservices with standardized Protobuf contracts and robust observability.
  79. Hashcat — GPU-accelerated password hash recovery with hashcat. Use when a user asks to crack NTLM/bcrypt/MD5/SHA/WPA hashes, run mask or rule-based attacks, convert a PCAP to a crackable hash, or benchmark hash cracking throughput on their own hardware.
  80. Cloudflare D1 Database — This skill helps developers build serverless applications using Cloudflare D1, a serverless SQLite database at the edge.
  81. AWS Cost Optimizer — Comprehensive AWS cost analysis and optimization recommendations using AWS CLI and Cost Explorer
  82. Cloudflare Workers — Cloudflare Workers is an edge computing platform for running JavaScript, TypeScript, and WebAssembly close to users worldwide with sub-millisecond cold starts. Use when working with the Workers runtime, the Wrangler CLI, KV, D1, R2, Durable Objects, Queues, or Hyperdrive, or when a user asks to build and deploy an edge function.
  83. Perplexity API — Perplexity API gives LLM answers grounded in live web search, with cited sources. Use when you need up-to-date information in AI responses, research assistants, fact-checking, current events coverage, or any task requiring knowledge beyond an LLM's training cutoff. Returns cited sources alongside answers.
  84. OpenClaw Security Hardener — Secures self-hosted OpenClaw environments with hardened host controls and network policies.
  85. Kamal Deployment Manager — Deploys containerized web applications to any server with zero downtime, simplifying deployments for developers and system administrators.
  86. Jetson Customize Camera — Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY lane allocation or ODMDATA edits.
  87. Jetson Video Benchmark — Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and user media, or producing a clearly labeled documentation-derived planning estimate when representative media is absent. Also use for a video request limited to PSNR or SSIM, to apply the terminal scope response.
  88. Arduino Azure Integration — This skill assists developers in connecting Arduino devices to Azure IoT Hub and Edge, ensuring secure telemetry, command handling, and robust production deployment.
  89. Cross Eval — /c-level-agents:cross-eval [memo] — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation. Use when a high-stakes memo needs an independent sanity check before the boardroom — e.g. a bet-the-company pivot or fundraise terms.
  90. Cloud Environment Provisioner — This skill establishes isolated, version-controlled Python environments for AWS and SageMaker developers to prevent dependency conflicts and ensure reliable cloud automation execution.
  91. ImageMagick Automation Expert — Assists developers in automating image processing pipelines using ImageMagick for tasks like resizing, conversion, and compositing.
  92. Boardroom — /c-level-agents:boardroom [brief] — 6-phase multi-role deliberation across the C-suite with Phase 2 isolation, critic pre-screen, and synthesis. Outputs a board memo. Use when a decision spans multiple executive domains — e.g. a pricing change touching finance, positioning, and product, or a raise-vs-cut runway call.
  93. Cloud Architect — Expert cloud architect specializing in multi-cloud infrastructure design, IaC, and cost optimization.
  94. Subject Line Psychologist — Crafts email subject lines and notification copy using psychological triggers to boost open rates.
  95. Implementing Hipaa Security Rule Safeguards — Implement the HIPAA Security Rule (45 CFR Part 164 Subpart C) to protect electronic protected health information (ePHI): conduct the required risk analysis, deploy the administrative, physical, and technical safeguards, handle required vs addressable implementation specifications, execute Business Associate Agreements, and stand up breach-notification readiness. Use when an organization is a HIPAA covered entity or business associate, when protecting ePHI, when preparing for an OCR audit or responding to a breach, when performing a HIPAA Security Risk Analysis, when drafting or reviewing a BAA, or when mapping security controls to the §164.308/310/312/314/316 safeguards. Notes the 2025 NPRM proposed changes (not yet final). Keywords: HIPAA, HIPAA Security Rule, ePHI, PHI, 45 CFR 164, risk analysis, administrative safeguards, physical safeguards, technical safeguards, addressable, required, Business Associate Agreement, BAA, OCR, breach notification, HITECH, covered entity, business associate.
  96. Okta SAML Integration — This skill assists developers and security engineers in implementing and troubleshooting secure SAML 2.0 Single Sign-On authentication flows using Okta as the identity provider.
  97. Copywriting Psychologist — Engineer belief and action in conversion copy by applying psychological mechanisms to audience motivations.
  98. Cloudflare Workers Expert — Expert in Cloudflare Workers and the Edge Computing ecosystem. Covers Wrangler, KV, D1, Durable Objects, and R2 storage.
  99. Batch Script Progress — Design and verify runtime output when creating or modifying Python, PowerShell, or Node.js scripts that process multiple files, records, or API requests. Use for batch scripts, bulk operations, silent long-running loops, progress reporting, per-item failures, final counts, stdout separation, or exit-status consistency. Not for UI progress bars, monitoring infrastructure, or progress updates in the AI conversation.
  100. Cloudformation Best Practices — CloudFormation template optimization, nested stacks, drift detection, and production-ready patterns. Use when writing or reviewing CF templates.

Opening your workspace…