New to Claude Skills? Learn how to install them →

nvidia on GitHub

i4h Catheter Navigation Smoke Tests

OfficialFree

Run CPU-only smoke tests for catheter navigation workflows.

by nvidia2.8k stars on nvidia/skills
Updated Aug 7, 2026
Get this skill

Free · Opens the source repo

What i4h Catheter Navigation Smoke Tests does

The i4h Catheter Navigation Smoke Tests skill is designed to facilitate the execution of CPU-only unit smoke tests specifically for fluorosim components and entrypoint parsers. This skill is particularly useful for developers working in continuous integration (CI) environments where GPU resources may not be available. It ensures that essential components such as imports, CT-to-mu preprocessing, and parser sanity checks are functioning correctly without the need for GPU validation.

To utilize this skill, users will set up their environment to point to the appropriate workflow directories. The skill includes a straightforward Bash script that checks for the necessary directories and sets the appropriate paths. Once the environment is prepared, users can execute tests using Python's unittest framework, which will log the results and provide immediate feedback on the status of the tests. This allows developers to quickly identify any issues in the workflow.

The skill also includes troubleshooting tips for common issues, such as import failures or unexpected test counts, making it easier for users to resolve problems without extensive debugging. However, it is important to note that this skill does not cover GPU rendering or interactive viewport checks, which are handled by a separate skill. Therefore, while it effectively ensures the basic functionality of the catheter navigation workflows, it should be complemented with GPU validation skills for comprehensive testing.

Overall, this skill is aimed at developers and QA engineers who need a reliable method for smoke testing their catheter navigation workflows in a CI context, ensuring that critical components are functioning as expected before deeper testing phases.

When to use it

Use this skill when you need to run smoke tests for catheter navigation components in a CI environment without GPU access.

When not to use it

This skill is not suitable for validating GPU rendering or interactive viewport features; use the appropriate GPU validation skill instead.

What you can build with it

Continuous Integration Testing

Use this skill in your CI pipeline to ensure that catheter navigation components are functioning correctly without GPU resources.

Basic Functionality Checks

Quickly verify that the essential imports and preprocessing steps are working as expected before deeper testing.

Troubleshooting Workflow Issues

Leverage the troubleshooting tips provided in the skill to resolve common issues encountered during smoke testing.

How to install i4h Catheter Navigation Smoke Tests

View source

1. Install with the skills CLI

npx skills add nvidia/skills/i4h-catheter-navigation-smoke --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by nvidia

i4h Catheter Navigation - Smoke Tests

Purpose

Run CPU-only unit smoke tests for fluorosim components and entrypoint parsers, safe for CI without a GPU. Exercises imports, CT->mu preprocessing, parser sanity, and conditional viewport import checks.

Base Code

ROOT="${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>/dev/null)}"
if [ ! -d "$ROOT/workflows/catheter_navigation" ]; then
  ROOT="${I4H_WORKFLOWS:-$HOME/i4h-workflows}"
  [ -d "$ROOT/workflows/catheter_navigation" ] || git clone https://github.com/isaac-for-healthcare/i4h-workflows "$ROOT"
fi
export I4H_WORKFLOWS="$ROOT"; cd "$ROOT"

Run

Step 1 - run tests

REPO_ROOT="${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>/dev/null)}"; [ -d "$REPO_ROOT/workflows/catheter_navigation" ] || REPO_ROOT="$HOME/i4h-workflows"
WF_ROOT="${REPO_ROOT}/workflows/catheter_navigation"
RUN_DIR="${WF_ROOT}/runs/smoke_$(date +%Y%m%d_%H%M%S)"
mkdir -p "${RUN_DIR}/logs"
ln -sfn "${RUN_DIR}" "${WF_ROOT}/runs/.latest"

python3 -m unittest workflows/catheter_navigation/tests/test_fluorosim_smoke.py \
  2>&1 | tee "${RUN_DIR}/logs/smoke.log"

Expected Output

Ran N tests in ...s
OK

Parser error lines on stderr from negative CLI tests are expected - not failures.

Verify

grep -E "Ran [0-9]+ tests" "${RUN_DIR}/logs/smoke.log"
grep "OK" "${RUN_DIR}/logs/smoke.log"

Prerequisites

  • Python 3 with workflow dependencies installed (for example via workflows/catheter_navigation/requirements.txt).
  • No GPU required.

Limitations

  • Does not exercise GPU Slang rendering or the interactive viewport.
  • For GPU validation, use [[i4h-catheter-navigation-render-drr]].

Troubleshooting

  • Error: import failures - Fix: run [[i4h-catheter-navigation-setup]] and ensure the active venv has catheter workflow dependencies installed.
  • Error: unexpected test count - Fix: inspect log; this can change when smoke coverage is added/removed on a branch.

Final Response

Report pass/fail, test count, and log path. If passed, note GPU stages still need separate verification.

Frequently asked questions about i4h Catheter Navigation Smoke Tests

Similar skills