Dev & Engineering ✓ NVIDIA · Official catheter-navigationfluoroscopyxpbd-physicsmedical-simulationisaac-for-healthcareinteractive-viewport

Catheter Navigation Fluoroscopy Viewport

Launch an interactive fluoroscopy viewport with real-time catheter physics and navigation controls.

FollowSkills review · FSRS-2.0
Not recommended
50/ 100 5-point scale 2.5 / 5
Trust15 / 25 · 3.0/5

The evidence shows commands that locate the workflow, validate the cache, create a run/log directory, and launch an interactive program; no credential theft, covert exfiltration, or destructive default was found. However, it may automatically clone code from external GitHub, write workflow run state, and start a GUI without explicit user confirmation, dependency-integrity checks, clear privilege boundaries, data-flow disclosure, or rollback guidance, so points are deducted.

Reliability8 / 20 · 2.0/5

The ordered steps, missing-cache exit, log capture, and remote-display/Vulkan/Slang troubleshooting are reasonably clear. However, display/GPU preflight is not actually performed, behavior depends on tmux variable persistence, external repository contents, and unlocked dependencies, and abnormal-input and launch-failure diagnostics are limited. Static calibration also caps the score.

Adaptability9 / 15 · 3.0/5

The trigger conditions, interactive scenarios, controls, X11 requirement, GPU requirement, and headless-CI non-fit boundary are fairly clear. Chinese-language support and mainland-China reachability of the GitHub-dependent workflow are not addressed, and evidence for adaptation to existing caches, displays, and GPUs is limited, so points are deducted.

Convention8 / 15 · 2.7/5

The documentation is readable and includes purpose, ordered execution, controls, prerequisites, limitations, troubleshooting, version, Apache-2.0 license, author, and an evaluation report. However, the static validation report identifies incorrect root-level version placement and missing recommended Instructions and Examples sections; maintenance ownership, changelog, and dependency-version governance remain incomplete.

Effectiveness6 / 15 · 2.0/5

The skill provides directly usable launch commands, key flags, log location, and keyboard mappings, while the benchmark report records an overall PASS and positive uplift. However, that report is committed static material with only four tasks and one attempt each, lacks independently verifiable representative execution results, and the outcome still depends on a local GUI, cache, GPU, and external workflow, so the score is limited.

Verifiability4 / 10 · 2.0/5

Versioned skill documentation, evaluation tasks, behavioral expectations, and a committed benchmark report provide some auditability. However, there is no skill-specific real CI, committed test suite, or independently reproducible third-party execution evidence; coverage is thin and the reported results cannot be independently confirmed from this static review, so points are deducted.

Evidence confidence:Low Reviewed Jul 29, 2026 Reviewed revision ce70ca7f1966
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Before execution, obtain confirmation for cloning an external GitHub workflow, creating run state, and launching the GUI; lock and verify dependency and commit versions.
  • The skill depends on X11, keyboard focus, a GPU, and a digital-twin cache and is unsuitable for headless environments; preflight checks and diagnosable failure reporting should be added.
  • Mainland-China network reachability and Chinese-language support are unspecified; the core function may be unavailable if the external repository cannot be reached.
  • Do not place real patient data or sensitive imaging in logs, prompts, or output; add explicit data-handling, permission, and cleanup guidance.
See the full review method →

What does this skill do, and when should you use it?

This skill launches the Isaac for Healthcare interactive fluoroscopy viewport with XPBD catheter physics, DSA, C-arm presets, and centerline-guided insertion. It depends on completed setup steps and a digital-twin cache, and requires an X11-capable display plus a GPU with at least 8 GB of VRAM. The workflow locates or clones the i4h-workflows repository, creates a run directory and log, and starts the interactive viewport. It is intended for keyboard-driven catheter-navigation demos or testing, not headless CI.

Locates or clones the i4h-workflows repository; checks that CACHE contains mu_volume.npy; creates a timestamped viewport run directory, logs directory, and .latest link; launches catheter_navigation interactive_viewport with the CT cache; enables the real vessel source, centerline insertion axis, 1024 detector size, 0.6 mm pixel spacing, and DSA; and exposes controls for advancing, retracting, rotating, overlays, DSA, C-arm presets, pausing, resetting, and quitting.

  1. A medical-simulation developer starts an interactive catheter-navigation viewport after preparing a digital-twin cache.
  2. An interventional-navigation researcher observes catheter motion with centerline-guided insertion and XPBD physics.
  3. A user demonstrates AP, LAO-45, Lateral, and RAO-30 C-arm views.
  4. A user runs the viewport through remote X11 or VNC and needs guidance for Qt display settings or keyboard focus.

What are this skill's strengths and limitations?

Pros
  • Provides a documented workflow for launching an interactive fluoroscopy viewport.
  • Includes XPBD catheter physics, DSA, C-arm presets, and centerline-guided insertion.
  • Creates run directories and records viewport.log.
  • Includes troubleshooting guidance for remote X11 control and missing cache errors.
Limitations
  • Requires a digital-twin cache containing mu_volume.npy.
  • Needs a graphical display and keyboard focus, so it is unsuitable for headless CI.
  • Requires a GPU with at least 8 GB of VRAM; 16 GB is recommended.
  • The SKILL.md does not document a test suite, specific supported GPU models, or a complete deployment matrix.

How do you install this skill?

Install the skill through the NVIDIA/skills skills CLI: npx skills add nvidia/skills --skill i4h-catheter-navigation-viewport --yes. The README does not specify the exact installation directory; the CLI handles the destination. Running the skill also requires completing i4h-catheter-navigation-setup and i4h-catheter-navigation-digital-twin and preparing i4h-workflows.

How do you use this skill?

Ask the agent, for example, “Open the interactive catheter-navigation fluoroscopy viewport” or “Demo fluoro catheter navigation.” Before running, set CACHE to a digital-twin directory containing mu_volume.npy. The entry command is: ./i4h run catheter_navigation interactive_viewport. For remote display, QT_QPA_PLATFORM=xcb can be set; the viewport uses --vessel-source real, --insertion-axis centerline, and --dsa in the documented launch command. See workflows/catheter_navigation/README.md for the full key map.

FAQ

Can this skill run on a headless server or in CI?
It is not suitable for that use. The skill requires a display and explicitly states that the interactive GUI is not suitable for headless CI.
What must be prepared before running it?
Complete i4h-catheter-navigation-setup and i4h-catheter-navigation-digital-twin, have i4h-workflows available, and point CACHE to a directory containing mu_volume.npy.
What should I do if keyboard controls do not work over remote X11?
Set QT_QPA_PLATFORM=xcb and place the pointer over the fluoroscopy window so it has keyboard focus.
Does the source state a cost or commercial licensing policy?
The supplied material does not state a cost. The skill SKILL.md lists Apache-2.0; the repository README states that the catalog project is dual-licensed under Apache 2.0 and CC BY 4.0.

More skills from this repository

All from NVIDIA/skills

Dev & Engineering ✓ NVIDIA · Official

i4h Catheter Navigation Workflow Guide

Orients agents to the right stage of NVIDIA’s endovascular catheter navigation workflow.

Dev & Engineering ✓ NVIDIA · Official

Catheter Navigation Setup Verification

Checks host, GPU, and Python path readiness for catheter navigation.

Dev & Engineering ✓ NVIDIA · Official

Catheter Navigation E2E Smoke Test

Runs the Isaac for Healthcare v0.7 catheter workflow from setup verification through digital-twin DRR rendering and unit tests.

Dev & Engineering ✓ NVIDIA · Official

Catheter Navigation DRR Renderer

Generate a single digitally reconstructed radiograph from CT data or a synthetic phantom for fluoroscopy previews and renderer smoke tests.

Dev & Engineering ✓ NVIDIA · Official

Catheter Navigation Fluoroscopy Smoke Tests

Validate core catheter-navigation workflow behavior on CPU-only CI environments.

Dev & Engineering ✓ NVIDIA · Official

Isaac for Healthcare Dataset Replay

Replay HDF5 episodes in Isaac Sim to verify recorded robot behavior visually.

Automation & Ops ✓ NVIDIA · Official

Isaac for Healthcare E2E Workflow

Run the Isaac for Healthcare pipeline from recording through validation.

Data & Analysis ✓ NVIDIA · Official

I4H Mimic Dataset Augmentation

Augment an existing HDF5 recording by cloning trajectories with action and state noise.

Dev & Engineering ✓ NVIDIA · Official

I4H Scene Editing Workflow

Edit existing Isaac for Healthcare scenes live through a controlled bridge session.

Dev & Engineering ✓ NVIDIA · Official

Isaac for Healthcare Workflow Validator

Run policy or state-machine rollouts and record verification episodes to HDF5.

Dev & Engineering ✓ NVIDIA · Official

I4H Workflow Environment Creator

Scaffold a runnable Isaac for Healthcare environment by forking a proven existing environment.

Data & Analysis ✓ NVIDIA · Official

LeRobot Dataset Visualizer

Inspect converted LeRobot datasets in a local browser.

Data & Analysis ✓ NVIDIA · Official

Catheter Navigation Vascular Digital Twin

Turn CT angiography data into a patient-specific vascular digital twin for catheter-navigation workflows.

Data & Analysis ✓ NVIDIA · Official

I4H Teleoperation Dataset Recorder

Record human demonstrations from keyboard, SO-ARM leader, or VR teleoperation into HDF5.

Dev & Engineering ✓ NVIDIA · Official

I4H Policy Fine-Tuning

Fine-tune GR00T or openpi PI0 policies on recorded LeRobot demonstrations.

Data & Analysis ✓ NVIDIA · Official

i4H Dataset Annotation Workflow

Use a vision-language model to verify task success and filter episodes for fine-tuning.

Data & Analysis ✓ NVIDIA · Official

I4H Dataset Converter

Convert Isaac for Healthcare HDF5 recordings into training-ready LeRobot datasets.

Data & Analysis ✓ NVIDIA · Official

DICOM Series Preflight

Header-only validation for one DICOM series before conversion or inference.

Data & Analysis ✓ NVIDIA · Official

NV-Segment-CT Medical Imaging Segmentation Skill

Run VISTA3D on CT NIfTI volumes and produce verifiable label-map evidence.

Dev & Engineering ✓ NVIDIA · Official

Jetson BSP Info Check

Verify Jetson BSP version, board configs, and rootfs state before flashing.

Related skills