Generated banner for I4h Workflow Create
Generated logo for I4h Workflow Create

I4h Workflow Create

NVIDIAOfficialCreated by Isaac for Healthcare TeamDistributed by NVIDIA

  • Skill
  • Workflow
  • Software development
  • Apache-2.0
  • Medium risk

From the author

Create a minimal blank Workflow scaffold with a Scene containing ground and light plus an idle run mode. Use for fast new Workflow scaffolding.
— the description by Isaac for Healthcare Team

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a standardized way to initialize a new workflow within the Isaac for Healthcare ecosystem. It creates a minimal, five-file scaffold that includes a basic scene with a ground plane and dome light, along with an idle run mode. By establishing this baseline, developers can quickly begin building out specific tasks, robot embodiments, and scene assets without manual file setup. The skill includes built-in static validation to ensure the generated structure meets project invariants.

What it does

  • Generates a standardized five-file workflow scaffold.
  • Creates a blank scene containing only a ground plane and dome light.
  • Initializes an idle run mode for immediate scene access.
  • Performs static validation of the generated workflow structure.
  • Prevents accidental overwriting of existing workflow files.
  • Supports specific product specialties including robotics for laparoscopy, ultrasound, endoluminal, and hospital automation.

When to use it

  • When starting a new development project within the Isaac for Healthcare framework.
  • When you need a clean, minimal environment to begin scene authoring.
  • When you want to ensure your new workflow adheres to standard project file structures.
  • When you need to quickly verify the structural integrity of a new workflow via static checks.

Advantages

  • Ensures consistent project structure across different workflows.
  • Reduces manual setup time for new development tasks.
  • Includes safety checks to prevent overwriting existing work.
  • Provides a ready-to-use idle mode for immediate scene visualization and editing.

Usage examples

“Create a blank hospital-automation-robotics workflow named my_workflow.”
Generates the five-file scaffold for 'my_workflow' under the hospital-automation-robotics specialty and runs static validation.
“Make a new laparoscopic-robotics workflow called training_sandbox as fast as possible. Start blank.”
Creates the 'training_sandbox' workflow structure in the laparoscopic-robotics specialty with an idle-only configuration.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/nvidia/i4h-workflow-create/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip i4h-workflow-create.zip -d .agents/skills

Documentation by Isaac for Healthcare Team

Create a Blank i4h Workflow

Purpose

Create a complete runnable blank Workflow without searching for an existing Workflow or booting Isaac Sim.

Instructions

  1. Resolve the checkout using I4H_WORKFLOWS when set; otherwise use the current git root. If neither contains workflows/i4h_workflows, use the checkout resolver from the repository AGENTS.md.

  2. Choose a lowercase snake_case Workflow id.

  3. Select exactly one approved product specialty: laparoscopic-robotics, ultrasound-robotics, endoluminal-robotics, or hospital-automation-robotics.

  4. Generate the blank Workflow and run the static validation below.

If the request does not identify a specialty, ask the user to choose one; do not infer a product category from the workflow name alone.

Run:

./scripts/create_blank_environment.py <workflow_id> --specialty <specialty>

This is the only authoring utility that generates workflow-specific source. It rejects an existing public workflow id in any specialty before dry-run output or file creation. It writes the fixed empty templates that establish the design boundary; later scene and task code is written by the coding agent. Use --dry-run to preview its output, --description TEXT to customize the scene-manifest description, and --validate to run the focused static checks after creation. Do not combine --dry-run and --validate.

The script refuses to overwrite files and creates only:

./
├── arena/i4h_arena/assets/<workflow_id>.py
├── arena/i4h_arena/scenes/<workflow_id>.py
├── arena/i4h_arena/scenes/manifest/<workflow_id>.yaml
├── workflows/i4h_workflows/<specialty>/<workflow_id>.py
└── workflows/tests/test_<workflow_id>_contract.py

The result contains a ground plane, dome light, no embodiment or declared robots, no task-specific objects or cameras, and one idle mode. Its contract test verifies durable Workflow and manifest invariants rather than asserting that the Scene stays blank, so later Scene, Task, and run-mode authoring does not require rewriting the test. Do not inspect robot assets, choose a policy, create Task manifests, load upstream Isaac Sim skills, or launch the simulator during blank creation.

Utility

CommandPurposeArguments
./scripts/create_blank_environment.pyCreate the complete overwrite-safe blank Workflow<workflow_id> --specialty <specialty> [--description TEXT] [--dry-run] [--validate]

Validate

Run only fast static checks:

./scripts/create_blank_environment.py <workflow_id> --specialty <specialty> --validate

When the Workflow already exists because it was created without --validate, run the equivalent checks directly:

cd "$(git rev-parse --show-toplevel)"
./run.sh show <workflow_id> --mode idle
./run.sh lint <workflow_id> --mode idle
./run.sh lint --all
workflows/.venv/bin/python -m pytest workflows/tests/test_<workflow_id>_contract.py -q
arena/.venv/bin/python -m pytest arena/tests/test_scene.py -q

--validate requires the workflow and Arena environments; run ./setup.sh first if either is missing. It verifies the generated contract and the shared zero-DOF blank-scene runtime adapter without launching Isaac Sim. If a component virtual environment is elsewhere, use that component's Python for its direct test command. Do not run visible or dynamic validation unless the user explicitly requests it.

Troubleshooting

  • If the checkout cannot be resolved, set I4H_WORKFLOWS to the existing repository root or use the resolver in AGENTS.md.

  • If generation reports that the workflow id already exists, report its specialty source and ask whether to edit it or use a different id; never overwrite, relocate, or duplicate it.

  • If --validate reports a missing component environment, run ./setup.sh and repeat the same validation.

Prerequisites

Require a writable root-level i4h-workflows checkout and Python 3.11 or newer. Static --validate also requires the workflow and Arena component environments.

Limitations

This skill creates only the five-file idle scaffold. It does not add an embodiment, task behavior, policy, cameras, or task-specific assets, and it does not visibly validate the Scene.

Continue

Treat creation as the first stage of an incremental workflow:

  1. Create the blank Workflow scaffold with this skill: blank Scene, scene manifest, and idle-only Workflow.

  2. Use i4h-workflow-scene-edit to add and visibly verify assets, robots, cameras, layout, and physics, then bake the confirmed Scene.

  3. Define behavior only after the user provides a concrete goal and success condition. Reuse compatible Tasks; create a focused Task only when the behavior is new. Do not create an empty placeholder Task.

  4. Add rule-based, teleop, replay, or policy modes only when requested and only when their Task and action contracts are runnable.

  5. Validate every newly enabled mode with the owning stage skill.

The blank Workflow is intentionally useful before behavior exists: its shared idle Task opens the Scene for authoring, so a blank task manifest or implementation would add no capability.

Examples

  • Create a blank hospital-automation-robotics workflow named my_workflow. → generate my_workflow in the hospital automation specialty and run static validation.

  • Make a new laparoscopic-robotics workflow called training_sandbox as fast as possible. Start blank. → generate the same five-file idle-only scaffold under training_sandbox in the laparoscopic specialty.

Completion gate

Report the created id, five files, idle-only status, and static validation results. Do not commit unless explicitly asked.

Files

ATTRIBUTION.md

Attribution

This folder is an unmodified copy of the Agent Skill "i4h-workflow-create", distributed by AutoGineer (https://autogineer.com/agent-skills).

The skill's own files are unmodified copies. AutoGineer is not affiliated with or endorsed by the author or the publisher.

Files added by AutoGineer

  • ATTRIBUTION.md: this file, written by AutoGineer

  • LICENSE: copied from LICENSE-APACHE

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

Security

What our scanner noticed· Medium risk

  • Large base64-encoded blobs

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Isaac for Healthcare Team
Publisher
NVIDIA (Official)
Distributed by
NVIDIA
Source
NVIDIA/skills · skills/i4h-workflow-create · commit fce3cca
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE-APACHE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Isaac for Healthcare Team or NVIDIA.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download i4h-workflow-create.zip