Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nvidia/i4h-catheter-navigation-setup
Verify host/GPU requirements and PYTHONPATH for the catheter navigation workflow.
Passed 14 of 17 test cases with the skill, and 3 of 17 without it.
and 19 more in the full report
15 fixed4 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to verify that catheter navigation is recognized by the i4h CLI tool. Instead of using `pytest` or `i4h list`, what exact CLI command should I run from the repository root?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the command ./i4h modes catheter_navigation | Missed | Passed |
The instructions your model reads when the skill loads.
Verify host and GPU requirements, confirm the ./i4h CLI sees the workflow, and run CPU smoke tests. Use when asked to set up catheter navigation or when hitting missing imports, GPU, or slangpy errors.
These steps drive the i4h-workflows base code (the workflows/catheter_navigation/ tree). To reuse an existing checkout, set I4H_WORKFLOWS to its path (no clone happens). Otherwise this resolves the current repo, or clones to ~/i4h-workflows - pick that default without prompting. Run every command below from the resolved root:
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"
workflows/catheter_navigation/metadata.json and runs through ./i4h run catheter_navigation <mode>.render_drr uses installed fluorosim (python -m fluorosim.examples.render_drr), while interactive_viewport is launched from the local workflow script path in metadata.json.workflows/catheter_navigation/docker/Dockerfile (drop --local on ./i4h run to use it).command -v python3
command -v git
nvidia-smi
df -h .
Required: Linux x86_64 (Ubuntu 22.04/24.04 tested), NVIDIA GPU (CC >= 7.0), driver compatible with CUDA 12.8, >= 16 GB RAM, >= 20 GB disk.
Run the steps below in order. Each step is a separate bash call; variables persist in the local agent's tmux session.
test cases passed, vs 3 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.