Deployment & Release Agent Skills

Generate operational runbooks from a service name — deployment, incident response, maintenance, and rollback workflows. Templated structure customizable per environment.

Plan and execute zero-downtime migrations for databases, services, and infrastructure with automated compatibility validation and rollback strategy generation.

Provides a structured pre-launch checklist, staged rollout plan, monitoring setup, and rollback strategy for safe production deployments.

Containerizes applications and deploys them to Google Kubernetes Engine (GKE) with Dockerfiles, manifests, and best practices.

Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints.

Sets up Google's agents-cli toolkit and guides through the full agent development lifecycle: scaffold, build, evaluate, deploy, publish, and monitor on Gemini Enterprise Agent Platform.

Manages Agent Platform serving endpoints: create, list, describe, update, delete, and troubleshoot permission, quota, and resource busy errors.

Create, deploy, and debug machine learning applications on Hugging Face Spaces using Gradio, Docker, or Static SDKs, with support for ZeroGPU and dedicated hardware.

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Build and deploy web servers anywhere using Nitro's filesystem routing, caching, tasks, WebSockets, and deployment presets for Node.js, Bun, Deno, Cloudflare, Vercel, and more.

Execute Azure deployments for already-prepared applications using azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery and verification.

Generate infrastructure code (Bicep/Terraform), azure.yaml, and Dockerfiles for Azure deployment, with a mandatory planning workflow.

Run pre-deployment validation checks for Azure readiness, including configuration, infrastructure (Bicep or Terraform), RBAC role assignments, and managed identity permissions.

Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda to Functions, Beanstalk/Heroku/App Engine to App Service, Fargate/Kubernetes/Cloud Run/Spring Boot to Container Apps.

Deploys Python web apps (Flask, Django, FastAPI) to Azure App Service Linux with automatic resource creation and framework detection.

Install or update the M365 Agents Toolkit (ATK) CLI and VS Code extension using npx and the VS Code CLI.

Builds, tests, and deploys Microsoft 365 apps and agents for Teams and Copilot using the ATK CLI, with sub-skills for project creation, local testing, cloud deployment, troubleshooting, and Slack-to-Teams migration.

Creates Azure OpenAI model deployments with intelligent intent-based routing, supporting quick presets, full customization, and capacity discovery across regions and projects.

Create, build, deploy, and localize declarative agents for M365 Copilot and Teams, including scaffolding, editing manifests, adding capabilities, and localization.

Discovers available Azure OpenAI model capacity across regions and projects, analyzes quota limits, and recommends optimal deployment locations.

Guides through interactive deployment of Azure OpenAI models with full control over version, SKU, capacity, content filtering, and advanced options.

Deploy and manage Docker containers on AWS ECS with Fargate or EC2, including task definitions, services, auto scaling, and troubleshooting.

Create, configure, and manage AWS Lambda serverless functions for event-driven compute, including triggers, debugging, cold start optimization, and layers.

Discover, select, and run Holoscan Sensor Bridge example applications on a connected devkit over SSH, filtering by platform, board type, and sensors.

Flash FPGA firmware on HSB Lattice boards and Leopard Imaging VB1940 cameras connected to NVIDIA devkits, with safety checks and multi-step upgrade/downgrade procedures.

Set up the Holoscan Sensor Bridge demo environment end-to-end: clone the repo, configure the host per platform, build and run the demo container, and verify connectivity to the sensor board.

Installs, deploys, runs, validates, troubleshoots, and stops NVIDIA AI-Q Blueprint infrastructure for local or self-hosted servers.

Inspects the host system, assesses platform compatibility, and recommends the correct Holoscan SDK installation method, then delegates to a method-specific install skill.

Extract Jetson Linux BSP and sample-rootfs tarballs, run apply_binaries.sh with the correct GPU stack flag, and record the image metadata in the active target profile.

Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles — use jetson-init-target instead.

Flash a promoted BSP image to a Jetson device in RCM mode using NVIDIA's flash.sh or l4t_initrd_flash.sh toolchain.

Bootstraps a BSP customization workspace for NVIDIA Jetson, including the Linux_for_Tegra overlay tracker, bsp_sources mono-tree, and Crosstool-NG toolchain.

Creates a new Jetson target-platform profile YAML by selecting a reference devkit and optional custom carrier, then updates the active target pointer.

Launch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.

Selects, configures, deploys, verifies, debugs, or tears down a VSS profile (base, search, lvs, warehouse, edge) for NVIDIA's video search and summarization stack.