I4h Workflow Validate

NVIDIAOfficialCreated by Isaac for Healthcare TeamDistributed by NVIDIA

Skill
Workflow
Software development
Apache-2.0
Medium risk

From the author

Run the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation, checkpoints, or local controllers; do not use for replay or dataset annotation.

— 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 procedure for validating Isaac for Healthcare (i4h) workflows. It guides the user through resolving the correct repository, identifying supported run modes, executing the unified launcher in the foreground, and verifying the resulting simulation data. It includes specific protocols for pre-flight checkpoint inspection, handling remote versus in-process tasks, and performing post-rollout data inspection to ensure structural and behavioral integrity.

What it does

Resolves and verifies the local i4h workflow repository checkout.
Lists and selects supported workflow modes using the unified launcher.
Executes simulation rollouts in the foreground with configurable episode counts.
Performs pre-flight validation of checkpoints against task manifests.
Inspects HDF5 recording artifacts to confirm episode success and data integrity.
Validates collision-excluding success rules through force-matrix analysis.

When to use it

When evaluating learned policies or rule-based controllers for i4h tasks.
Before deploying a new checkpoint or workflow configuration.
To verify that a specific simulation scene and task contract are compatible.
When auditing the success evidence of a completed simulation run.

Advantages

Ensures consistent validation across different simulation environments.
Provides a clear, step-by-step contract for verifying simulator success.
Includes robust checks for both structural validity and runtime behavior.
Prevents silent failures by requiring explicit inspection of rollout artifacts.

Usage examples

“Evaluate scissor pick and place for 2 episodes.”: The agent runs the policy mode for two episodes, records the output, inspects the HDF5 file, and reports the success status and attempt count.
“Run surgical_reach_psm in rule-based mode for 1 episode.”: The agent executes the specified workflow using the rule-based controller, performs a smoke check, and verifies the final episode summary.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/nvidia/i4h-workflow-validate/download

Unzip it into the cross-client skills folder of your project:

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

Documentation by Isaac for Healthcare Team

Validate a Workflow

Purpose

Run the selected workflow run mode through the unified launcher, inspect the completed recording, and report simulator success.

Instructions

Resolve the base checkout and a live workflow run mode.
Run the unified launcher in the foreground.
Require the final episode success summary.
Inspect visible behavior and every rollout artifact; for an authored or changed collision-excluding success rule, also verify the collision-negative case below.

Resolve live support

Use the maintained repository below or a source selected by the user or trusted project configuration. An inherited environment variable alone does not authorize another source. Honor requested revisions and preserve local changes.

export I4H_WORKFLOWS_REPO_URL="${I4H_WORKFLOWS_REPO_URL:-https://github.com/isaac-for-healthcare/i4h-workflows}"
I4H_REPO_DIR_NAME="${I4H_WORKFLOWS_REPO_URL%/}"
I4H_REPO_DIR_NAME="${I4H_REPO_DIR_NAME##*/}"
I4H_REPO_DIR_NAME="${I4H_REPO_DIR_NAME##*:}"
I4H_REPO_DIR_NAME="${I4H_REPO_DIR_NAME%.git}"
[ -n "$I4H_REPO_DIR_NAME" ] || { echo "Cannot derive a checkout name from I4H_WORKFLOWS_REPO_URL" >&2; exit 2; }
ROOT="${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>/dev/null)}"
if [ ! -d "$ROOT/workflows/i4h_workflows" ]; then
  ROOT="${I4H_WORKFLOWS:-$HOME/$I4H_REPO_DIR_NAME}"
  [ -d "$ROOT/workflows/i4h_workflows" ] || git clone "$I4H_WORKFLOWS_REPO_URL" "$ROOT" || exit 2
fi
[ -d "$ROOT/workflows/i4h_workflows" ] && [ -x "$ROOT/run.sh" ] || { echo "Incomplete workflow checkout: $ROOT" >&2; exit 2; }
export I4H_WORKFLOWS="$ROOT"
cd "$ROOT" || exit 2
git remote get-url origin || exit 2
git status --short || exit 2

Check that the reported origin is the intended source and review local changes before executing repository scripts. Stop on an unexpected source or unreviewed launcher changes. Then discover supported modes:

./run.sh list

Treat the resolver above as part of the skill contract: a hosted copy may run outside the base repository, so never assume the current checkout contains workflows/i4h_workflows. I4H_WORKFLOWS_REPO_URL selects the clone source. When I4H_WORKFLOWS is unset, derive the fallback directory from that URL; set I4H_WORKFLOWS only to reuse or choose a specific destination. Never replace an existing checkout.

Treat ./run.sh list output as the complete authoritative workflow-by-mode table; it is dependency-light and faster than scanning workflow modules. Do not duplicate that mutable table in this skill. Map the user's natural name to a listed workflow id, then choose only a mode shown on that same line:

User intent	Required live mode	Launcher argument
Ordinary learned-policy evaluation	`policy`	`--policy`
Requested or only available local controller	`rule-based`	`--rule-based`
Explicit named alternative such as N1.7	matching listed mode such as `policy_n17`	`--mode <name>`

Inspect ./run.sh show <workflow> --mode <mode>, the workflow module, Scene manifest, and selected Task manifest when model, prompt, checkpoint, goal, or step-cap behavior matters.

Use precise readiness language:

Structurally valid: show, per-mode lint, and lint --all pass.
Launchable: the selected simulator mode starts and every required backend/checkpoint preloads.
Rollout-validated: the requested episodes complete and the recorded success evidence passes inspection.

Do not report “validated” without stating which level was actually reached.

Foreground execution rule

Keep run.sh as this agent's foreground tool call. Do not use a subagent, monitor task, shell backgrounding, nohup, tmux, or a detached process. Poll a yielded session until exit and inspect the final episode summary before responding. When the selected Task is remote, the policy backend subprocess internally owned by run.sh is expected; a simulator-compatible exported RSL-RL Task runs in-process.

Run visibly by default. If the user explicitly requests headless execution, or a documented environment constraint makes it necessary, say so before launch and include --headless; never switch to headless silently.

Use the requested episode count; if omitted, state that this is a one-episode smoke check and set N=1. Keep the launcher's per-episode --attempts 3 budget distinct from the bounded whole-run recovery below.

Policy:

./run.sh <workflow> --policy \
  --episodes <N> --attempts 3 \
  --record verify.hdf5

Rule-based:

./run.sh <workflow> --rule-based \
  --episodes <N> --attempts 3 \
  --record verify.hdf5

The launcher creates a unique canonical run directory and anchors the relative verify.hdf5 inside it. Resolve RUN_DIR from the ==> run dir ... line or machine-readable run.json; do not recreate the launcher's timestamp. Use --run-dir "$RUN_DIR" only when a caller-selected location must be shared with another stage; the launcher creates it. Absolute recording paths remain supported.

For another declared mode, use --mode <name>. For “300 timesteps,” pass --episode-steps 300.

Supplied-checkpoint preflight

Resolve the supplied checkpoint to an existing absolute path and pass that same path with --checkpoint. Run ./run.sh show <workflow> --mode <mode> to identify the selected policy Task. Read its manifest and loader under tasks/<project>/i4h_tasks/<project>/ and compare the checkpoint's model/export metadata with the required model, format, observation ordering/dimensions, and action mapping. Stop if the path or contract is unresolved; do not infer compatibility from a filename.

For a remote Task, use its declared backend's --preload-only option to load the checkpoint and exit before starting a simulator. For example, the gr00t_n15/assemble_trocar Task uses:

uv run --project tasks/gr00t_n15 python -m i4h_tasks.gr00t_n15.server \
  --namespace assemble_trocar --preload gr00t_n15/assemble_trocar \
  --checkpoint /absolute/path/to/checkpoint --preload-only

For another Task, resolve its own backend project, server entrypoint, and Task id from the live declarations; do not reuse the example's model family. Require exit status 0 and no loader error. During the normal foreground rollout, also require ready for specs in the run directory's backend log and successful runtime observation/action contract checks. Successful loading alone does not establish Scene compatibility.

An in-process RSL-RL Task instead requires the exported TorchScript policy.pt. Pass it to the selected foreground policy command above; the Task loads it with torch.jit.load on entry and checks its output shape on the first policy step. Require successful loading and a valid first policy step before reporting it launchable, then complete the requested episodes. Do not pass a native trainer checkpoint to this runtime Task.

show, lint, and --dry-run are structural checks: they do not load policy checkpoints. If the loader/runtime check cannot run, report only the structural checks actually completed, not checkpoint compatibility or rollout validation.

Never raise the Scene manifest's cap. --episode-steps may only lower it. Remote inference waits do not consume simulation steps. Use a unique --namespace when another run of the same workflow is active.

Verify

Require exit status 0 and final N/N episodes succeeded. A failed attempt followed by a successful retry counts as a successful requested episode; report attempts and retries.

RUN_DIR="<absolute run_dir from run.json or launcher output>"
uv run --project tools/dataset i4h-dataset inspect "$RUN_DIR/verify.hdf5" --segments

Check episode metadata, action/state widths, declared cameras, executed-node segments, and success flags against the Scene/Task contracts and final summary. Missing, corrupt, or inconsistent data blocks rollout validation; report the failed check. For visible runs, observe Scene/camera behavior and final task outcome. On failure, use the first actionable backend, contract, graph, or simulator error; never switch modes or increase the cap silently. After a crash, stop the retained foreground session and verify its child processes exit. ./stop.sh all affects every run in this checkout; use it only when all those runs are within the requested cleanup scope.

After authoring or changing a collision-excluding success rule, use the Scene's contact setup to test the configured body pair. Require non-zero filtered force, rejected success, and cleared collision history after reset. Record sensor names, force-matrix shape, maximum force, and outcome in the saved evidence. Initialization or zero force alone is insufficient. If the test cannot run, report the validation gap.

Troubleshooting

Correct the first actionable error within scope, then retry the whole run once with the same mode, cap, and episode count. If it recurs or cannot be fixed, stop and report it with the run directory. Per-episode attempts do not reset this whole-run retry budget.

Prerequisites

Require synced simulator assets and any backend/checkpoint declared by the selected run mode.

Limitations

Only modes from run.sh list are supported, and a runtime step override may lower but never raise the validated Scene cap.

Examples

Evaluate scissor pick and place for 2 episodes. → run policy mode for two successful episodes, record, inspect, and report attempts plus visible outcome.
Run surgical_reach_psm in rule-based mode for 1 episode. → use only the declared local-controller mode.

Completion gate

Report workflow, mode, model/checkpoint source, requested successes, attempts/retries, completion steps, visible outcome, HDF5 path and inspection, collision-negative/reset evidence when applicable, final exit status, and first unresolved failure if any.

Files

ATTRIBUTION.mdAdded by AutoGineer940 B
BENCHMARK.md11.1 KiB
LICENSELicence file added by AutoGineer11.2 KiB
SKILL.md10.1 KiB
evals/evals.json13.0 KiB
skill-card.md4.0 KiB
skill.oms.sig4.5 KiB

evals/evals.json

[
  {
    "id": "i4h-workflow-validate-readme-quick-scissor-two",
    "question": "Evaluate scissor pick and place in policy mode and record 2 successful episodes.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README Quick Run prompt routes to validation for scissor_pick_and_place and keeps policy mode while recording two successful rollout episodes.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the natural env name to scissor_pick_and_place",
      "sets EPISODES to 2",
      "uses policy mode and does not switch to rule-based because the prompt says successful",
      "uses the workflow's remote-task manifest unless a checkpoint is provided",
      "keeps the unified launcher in the foreground until the final episode summary",
      "records verification episodes to HDF5"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-ultrasound",
    "question": "Evaluate ultrasound_liver_scan in policy mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README Quick Run prompt routes to validation for env ultrasound_liver_scan with one episode.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "uses the explicit ultrasound_liver_scan workflow ID",
      "sets EPISODES to 1",
      "uses the openpi policy task declared by the workflow"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-trocar",
    "question": "Evaluate trocar assembly in policy mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README Quick Run prompt routes to validation for env assemble_trocar with one remote GR00T policy episode, using either its configured checkpoint or an explicitly exported RLinf checkpoint.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps trocar assembly to assemble_trocar",
      "sets EPISODES to 1",
      "uses the remote GR00T N1.5 Task and accepts a compatible exported RLinf checkpoint when supplied"
    ]
  },
  {
    "id": "i4h-workflow-validate-ultrasound-probe-reach",
    "question": "Validate ultrasound_probe_reach in policy mode and report its simulator success rate.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README RL-authoring prompt validates the exported TorchScript actor through the rsl_rl/ultrasound_probe_reach in-process Task and normal Workflow SimulationRunner.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "resolves the ultrasound_probe_reach policy mode and rsl_rl/ultrasound_probe_reach Task",
      "requires the exact exported policy.pt checkpoint",
      "runs the requested episodes through the normal SimulationRunner",
      "reports episode attempts, visible torso-target behavior, and simulator success rate"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-locomanip-tray",
    "question": "Evaluate locomanip tray pick and place in policy mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README Quick Run prompt routes to validation for env locomanip_tray_pick_and_place with one episode.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the prompt to locomanip_tray_pick_and_place",
      "sets EPISODES to 1",
      "uses the GR00T N1.6 locomanip policy stack"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-locomanip-cart",
    "question": "Evaluate locomanip push cart in policy mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README Quick Run prompt routes to validation for env locomanip_push_cart with one episode.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the prompt to locomanip_push_cart",
      "sets EPISODES to 1",
      "uses the GR00T N1.6 locomanip policy stack"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-surgical-reach-rule-based",
    "question": "Run surgical_reach_psm in rule-based mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README Quick Run prompt routes to the surgical_reach_psm rule-based mode for one episode.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the workflow to surgical_reach_psm",
      "sets the requested episodes to 1",
      "runs the unified launcher with --rule-based",
      "does not request an unavailable surgical policy"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-surgical-reach-newton",
    "question": "Run surgical_reach_psm in rule-based mode for 1 episode with Newton physics.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README prompt runs one surgical_reach_psm rule-based rollout with the explicitly requested Newton physics preset.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the workflow to surgical_reach_psm",
      "sets the requested episodes to 1",
      "runs the unified launcher with --rule-based and --presets newton",
      "does not silently use the default PhysX backend",
      "requires the final episode success summary"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-surgical-lift-needle-rule-based",
    "question": "Run surgical_lift_needle in rule-based mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README Quick Run prompt routes to the surgical_lift_needle rule-based mode for one episode.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the workflow to surgical_lift_needle",
      "sets the requested episodes to 1",
      "runs the unified launcher with --rule-based",
      "does not request an unavailable surgical policy"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-quick-new-checkpoint",
    "question": "Evaluate the new checkpoint.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README continuation validates the newly produced my_workflow checkpoint with the workflow's normal episode cap.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "resolves the latest/new checkpoint and passes --checkpoint explicitly",
      "uses the my_workflow policy mode and does not invent a timestep override",
      "records rollout verification output"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-new-env-rule-based-record",
    "question": "Run and record 5 successful rule-based episodes for my_workflow.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README authoring prompt records five successful demonstrations from the newly created workflow's rule-based G1 reach-table mode.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "resolves my_workflow and requires its declared rule-based mode",
      "runs the unified launcher in rule-based mode for five successful episodes",
      "keeps the rollout in the foreground and visibly verifies G1 reaches the table",
      "does not silently switch the rollout to headless mode",
      "records the episodes to HDF5 and inspects segments, actions, cameras, and success flags",
      "distinguishes structural validity, launchability, and rollout validation in the report",
      "reports the recording path for conversion and training"
    ]
  },
  {
    "id": "i4h-workflow-validate-table-scissor-three",
    "question": "Evaluate scissor pick and place with 3 episodes.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README skill-table prompt routes to validation for scissor_pick_and_place with three episodes.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the prompt to scissor_pick_and_place",
      "sets EPISODES to 3",
      "does not run annotation unless separately requested"
    ]
  },
  {
    "id": "i4h-workflow-validate-readme-robotic-instrument-reach",
    "question": "Validate robotic_instrument_reach in policy mode and report its simulator success rate.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This README RL-authoring prompt validates the exported RoboticInstrumentReach TorchScript policy through its reusable in-process Task and the normal Workflow runner.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "resolves robotic_instrument_reach policy mode and the rsl_rl/robotic_instrument_reach Task",
      "passes the exact exported policy.pt checkpoint",
      "runs requested episodes visibly through the unified launcher in the foreground",
      "records and inspects HDF5 actions, camera frames, node segments, and success flags",
      "reports requested successes, attempts, completion steps, checkpoint source, and simulator success rate"
    ]
  },
  {
    "id": "i4h-workflow-validate-specialty-surgical-dual-psm",
    "question": "Run surgical_reach_dual_psm in rule-based mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This laparoscopic specialty prompt validates one surgical_reach_dual_psm episode with its declared rule-based controller.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "uses surgical_reach_dual_psm in rule-based mode",
      "requests one successful episode",
      "records and inspects the rollout artifacts"
    ]
  },
  {
    "id": "i4h-workflow-validate-specialty-surgical-star",
    "question": "Run surgical_reach_star in rule-based mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This laparoscopic specialty prompt validates one surgical_reach_star episode with its declared rule-based controller.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "uses surgical_reach_star in rule-based mode",
      "requests one successful episode",
      "records and inspects the rollout artifacts"
    ]
  },
  {
    "id": "i4h-workflow-validate-specialty-surgical-lift-block",
    "question": "Run surgical_lift_block in rule-based mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This laparoscopic specialty prompt validates one surgical_lift_block episode with its declared rule-based controller.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "uses surgical_lift_block in rule-based mode",
      "requests one successful episode",
      "records and inspects the rollout artifacts"
    ]
  },
  {
    "id": "i4h-workflow-validate-specialty-surgical-lift-needle-organs",
    "question": "Run surgical_lift_needle_organs in rule-based mode for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This laparoscopic specialty prompt validates one surgical_lift_needle_organs episode with its declared rule-based controller.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "uses surgical_lift_needle_organs in rule-based mode",
      "requests one successful episode",
      "records and inspects the rollout artifacts"
    ]
  },
  {
    "id": "i4h-workflow-validate-specialty-endoluminal-demo",
    "question": "Run endoluminal_navigation in demo mode for 1 episode without patient CT data.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This endoluminal specialty prompt validates one procedural endoluminal_navigation demo episode without a patient-twin manifest.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "uses the declared endoluminal_navigation demo mode",
      "does not require or invent a patient CT path",
      "requests one successful episode and inspects its artifacts"
    ]
  },
  {
    "id": "i4h-workflow-validate-specialty-scissor-policy",
    "question": "Evaluate scissor pick and place for 1 episode.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This hospital-automation specialty prompt validates one scissor_pick_and_place episode using its ordinary policy mode.",
    "expected_behavior": [
      "routes to i4h-workflow-validate",
      "maps the natural workflow name to scissor_pick_and_place",
      "uses ordinary policy mode for one successful episode",
      "records and inspects the rollout artifacts"
    ]
  },
  {
    "id": "i4h-workflow-validate-specialty-endoluminal-total-segmentator",
    "question": "Download TotalSegmentator sample s0011 and prepare it as a patient twin.\nRun endoluminal_navigation in demo mode with it and verify fluoroscopy.",
    "expected_skill": "i4h-workflow-validate",
    "ground_truth": "This endoluminal specialty prompt downloads the public TotalSegmentator small sample, converts subject s0011 with the patient-twin tool, and validates endoluminal_navigation demo mode using the generated manifest.",
    "expected_behavior": [
      "routes the final rollout to i4h-workflow-validate",
      "downloads the documented public TotalSegmentator small dataset only when it is not already available",
      "prepares subject s0011 with tools/patient_twin/run.sh",
      "passes the generated patient_twin.yaml to endoluminal_navigation demo mode",
      "runs the unified launcher in the foreground",
      "verifies the completed episode and visible fluoroscopy result"
    ]
  }
]

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 a command-line tool, Needs Python, Needs Node.js

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-validate · commit fce3cca

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE-APACHE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

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-validate.zip