Deployment & Release Agent Skills

Install and verify cuPyNumeric for Python using conda or pip, including GPU usage checks.

Rebuild kernel-side artifacts (DTBs, OOT modules, kernel Image) from source changes under bsp_sources/ and produce a manifest for staging into a BSP image.

Downloads NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Used for Auto Setup; does not extract or edit profiles.

Collects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes for model serving with GPU support.

Plan and apply safe, reversible headless-mode changes on Jetson devices to reclaim memory from the GUI and non-essential daemons.

Copies overlay files and built artifacts into a staged BSP image for NVIDIA Jetson platforms, preparing it for flashing without modifying the workspace.

Start or patch Dynamo router modes and run router endpoint smoke checks for round-robin, KV-aware, least-loaded, or device-aware routing.

Configure Jetson UPHY lane allocation on Orin/Thor custom carriers by editing ODMDATA tokens and dispatching per-controller kernel-DT overlay skills.

Install the Holoscan SDK Python wheel via pip into a virtual environment and verify with example scripts.

Reclaim DRAM on NVIDIA Jetson devices by disabling unused display, camera, and DMA subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB layers for headless or no-camera deployments.

Install the Holoscan SDK C++ runtime and headers on Ubuntu using NVIDIA's apt repository, with automatic CUDA variant detection and verification via bundled examples.

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.

Lock, cap, or customize CPU, GPU, and EMC clock behavior on NVIDIA Jetson devices by editing BPMP DTB and nvpower.sh before flashing.

Validates that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after deploying a disagg or multi-node recipe to confirm KV transport is correct, or use troubleshoot for already-failed pods.

Recommends an inference runtime and memory-related launch flags for LLM/VLM workloads on NVIDIA Jetson devices, based on a live memory audit snapshot.

Start, query, and stop a TAO inference microservice for a specific network architecture by delegating container execution to the appropriate platform skill.

Deploy and operate the VSS 3.2 GA RT-Embed Video Embedding microservice using Docker Compose, covering GPU prerequisites, REST API usage for file uploads, text/video embeddings, live RTSP streams, Redis/Kafka/OTel integration, and troubleshooting.

Deploy a standalone RT-VLM dense-captioning microservice and exercise its REST API endpoints for file upload, caption generation, streaming, chat completions, and Kafka integration.

Import object detection models from HuggingFace or NVIDIA NGC into a DeepStream pipeline with automated ONNX download, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report generation.

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

Runs AutoMagicCalib calibration on local MP4s, RTSP streams, or a bundled sample dataset, and deploys the AMC microservice when needed.

Deploy, debug, and operate the RTVI-CV 2D detection/tracking microservice and call its REST API for stream management, health checks, and metrics.

Deploy and operate the RTVI-CV-3D microservice for multi-camera 3D detection and tracking, supporting sample datasets, custom videos, and RTSP streams.

Deploy serverless browser automation as cloud functions using Browserbase. Run browser automation on a schedule, create webhook endpoints, or run automation in the cloud instead of locally.

Manage an Uncloud cluster — deploy services, configure Caddy ingress, add static proxy routes for non-cluster devices, publish ports, scale, inspect logs, and manage machines and volumes with the `uc` CLI.

Classifies ECC components (skills, commands, rules, hooks) into DAILY and LIBRARY buckets based on evidence from the actual codebase, producing an install plan and verification report.

Manage GitHub repositories: triage issues, review PRs, debug CI/CD, prepare releases, and monitor security alerts using the gh CLI.

Monitors a deployed URL for regressions after releases by checking HTTP status, console errors, network failures, performance metrics, content integrity, API health, static assets, and SSE streams.

Configure Celery with Django for background task processing, including task design, scheduling, retries, canvas workflows, monitoring, and testing.

Orchestrate multi-agent coding tasks by dispatching parallel agents in isolated worktrees, monitoring progress, and reading structured reports.

Audits local code for production readiness, identifying risks in security, data integrity, payments, operations, and UX before shipping.

Provides deployment strategies, CI/CD pipeline patterns, Docker containerization best practices, health checks, and production readiness guidance for web applications.

Runs a multi-phase verification pipeline for Laravel projects including environment checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

Enforces safety gates, evidence-based debugging, anti-slack detection, and verification hooks when AI modifies files, configs, or deployments.

Build serverless background jobs, event-driven workflows, and durable execution with Inngest, without managing queues or workers.