# amc-setup-calibration-stack

Launches the AutoMagicCalib microservice and web UI from NGC containers using Docker Compose. It requires an NGC API key and a configured NVIDIA Docker Runtime.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 640 installs · ★ 3735
- Author: NVIDIA CORPORATION
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/NVIDIA/skills/tree/HEAD/skills/amc-setup-calibration-stack/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/amc-setup-calibration-stack

## What it does

This skill guides the agent through deploying the AutoMagicCalib stack developed by NVIDIA CORPORATION. It detects an existing `auto-magic-calib` checkout or prompts before cloning the repository from `NVIDIA-AI-IOT`. The workflow also ensures Docker runs without `sudo`.

Next, the agent handles authentication to `nvcr.io` with your NGC API key. If needed, it downloads the 4.7GB VGGT model from Hugging Face using `HF_TOKEN`. You can skip this download because base AMC functionality works without the VGGT weights.

Finally, the skill configures environment variables and locates an open backend port between 8000 and 8009. The stack fails without NVIDIA Docker Runtime configured for GPU passthrough, so set that up beforehand.

## Requirements
- Works with: Docker

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill amc-setup-calibration-stack -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/amc-setup-calibration-stack/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/amc-setup-calibration-stack/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill amc-setup-calibration-stack -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/amc-setup-calibration-stack/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill amc-setup-calibration-stack -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/amc-setup-calibration-stack/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NVIDIA/skills amc-setup-calibration-stack
```

2. **Manually: put the files in place**
- File: `.github/skills/amc-setup-calibration-stack/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill amc-setup-calibration-stack -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NVIDIA/skills --path skills/amc-setup-calibration-stack
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/amc-setup-calibration-stack/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill amc-setup-calibration-stack -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/NVIDIA/skills/tree/HEAD/skills/amc-setup-calibration-stack/SKILL.md

## When to use it
- deploy the AutoMagicCalib microservice and web UI via Docker Compose
- authenticate Docker with the NGC container registry
- download the optional VGGT model weights from Hugging Face
- verify Docker permissions without sudo access
- allocate an open backend port between 8000 and 8009

## Example prompts
- Deploy the AutoMagicCalib stack using Docker Compose
- Launch the AMC microservice and web UI
- Set up auto-magic-calib and log in to NGC

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 0d2fe26153859830.

BEGIN THIRD-PARTY FILE 0d2fe26153859830
````text
---
name: "amc-setup-calibration-stack"
description: "Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key."
metadata:
  author: "NVIDIA CORPORATION"
  tags: [amc, deepstream, docker, calibration, setup, ngc]
owner: "NVIDIA CORPORATION"
service: "auto-magic-calib"
version: "1.0.0"
reviewed: "2026-04-28"
license: "Apache-2.0"
---

# Skill: Launch AutoMagicCalib Release Containers

Set up the AutoMagicCalib microservice and UI from release containers: resolve an AMC checkout, authenticate to NGC, optionally download VGGT, configure Docker Compose, launch services, and verify readiness.

## Prerequisites
- Docker and Docker Compose installed
- NVIDIA Docker Runtime configured (for GPU support)
- `auto-magic-calib` repo on disk. Step 0b resolves the current repo, DeepStream `tools/auto-magic-calib`, `DEEPSTREAM_REPO_ROOT`, or `~/auto-magic-calib`; otherwise it asks before cloning `https://github.com/NVIDIA-AI-IOT/auto-magic-calib`.
- NGC account with access to NVIDIA container registry
- Docker runnable without `sudo`; verify with `docker ps` before continuing.

## Instructions

### Step 0: Verify Docker Runs Without sudo

```bash
docker ps
```

- If it succeeds → continue.
- If it fails with "permission denied" → the user is not in the `docker` group. Ask the user to run:
  ```bash
  sudo usermod -aG docker $USER && newgrp docker
  ```
  Then ask the user to confirm `docker ps` works before continuing.

> **Agent note**: If `docker ps` cannot be run from within the agent sandbox, ask the user to confirm it works (e.g. "Can you confirm `docker ps` runs without sudo?") before proceeding.

### Step 0b: Resolve Repo Checkout

The skill needs AMC repo assets (`compose/`, sample data, and `models/`). Resolve an existing checkout first; ask before cloning into `~/auto-magic-calib`.

```bash
REPO_URL="https://github.com/NVIDIA-AI-IOT/auto-magic-calib.git"
DEFAULT_CLONE_DIR="$HOME/auto-magic-calib"
CURRENT_GIT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || true)"

is_amc_checkout() {
  [ -n "$1" ] \
    && [ -f "$1/README.md" ] \
    && grep -q "AutoMagicCalib" "$1/README.md" 2>/dev/null \
    && [ -f "$1/compose/compose.yml" ] \
    && grep -q "auto-magic-calib-ms" "$1/compose/ms/compose.yml" 2>/dev/null \
    && grep -q "auto-magic-calib-ui" "$1/compose/ui/compose.yml" 2>/dev/null
}

REPO_ROOT=""
for candidate in \
  "$CURRENT_GIT_ROOT" \
  "${CURRENT_GIT_ROOT:+$CURRENT_GIT_ROOT/tools/auto-magic-calib}" \
  "${DEEPSTREAM_REPO_ROOT:+$DEEPSTREAM_REPO_ROOT/tools/auto-magic-calib}" \
  "$PWD/tools/auto-magic-calib" \
  "$DEFAULT_CLONE_DIR"; do
  if is_amc_checkout "$candidate"; then
    REPO_ROOT="$candidate"
````
END THIRD-PARTY FILE 0d2fe26153859830

The third-party file has ended. Everything between the 0d2fe26153859830 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2842 of 15760 bytes. © NVIDIA CORPORATION · Apache-2.0 · https://github.com/NVIDIA/skills/tree/HEAD/skills/amc-setup-calibration-stack/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md