I4h Workflow Setup

NVIDIAOfficialCreated by Isaac for Healthcare TeamDistributed by NVIDIA

Skill
Workflow
Cloud and DevOps
Apache-2.0
Medium risk

From the author

Preflight and set up the root-level workflow runtime. Use for installation, missing component environments, or third-party failures; do not use for rollout validation.

— the description by Isaac for Healthcare Team

AutoGineer summary

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

The i4h-workflow-setup skill provides a standardized procedure for initializing the Isaac for Healthcare (i4h) workflow environment. It manages repository checkout, performs host-level preflight checks for system dependencies, executes the full setup process, and verifies workflow discovery and linting. This skill is designed to ensure the runtime is correctly configured before attempting to run specific healthcare-related simulation workflows.

What it does

Resolves and clones the i4h workflows repository to a specified or default directory.
Performs host preflight checks including OS, hardware, and dependency verification.
Executes the full setup script to synchronize environments and third-party components.
Verifies successful workflow discovery and runs linting across all components.
Provides a structured approach to troubleshooting environment-related installation failures.

When to use it

When initializing a new development or runtime environment for Isaac for Healthcare workflows.
When encountering missing component environments or third-party dependency failures.
To verify that the host system meets all hardware and software requirements before deployment.
To perform a clean synchronization of the workflow runtime.

Advantages

Ensures a consistent and reproducible environment setup across different machines.
Automates complex dependency checks and repository management.
Provides immediate feedback on system compatibility through preflight checks.
Validates the integrity of the installation via automated discovery and linting.

Usage examples

“Set up the i4h workflow on this machine and tell me if any host requirements are missing.”: The agent will perform host preflight checks, execute the full setup script, run discovery, and report linting results.

Install

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

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

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

Documentation by Isaac for Healthcare Team

i4h Workflow Setup

Purpose

Prepare the complete runtime, then prove dependency-light workflow discovery works.

Instructions

Resolve the base checkout.
Run every host preflight check.
Run default full setup.
Verify discovery and lint --all.

Resolve the checkout

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" "$ROOT"
fi
export I4H_WORKFLOWS="$ROOT"
cd "$ROOT"

Treat this resolver 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.

Preflight

uname -srm
command -v uv
command -v git
nvidia-smi
df -h .
./setup.sh --help

Require supported Linux on x86_64 or aarch64, uv, Git, network access for missing packages/assets, sufficient disk and model-cache space, and an NVIDIA driver compatible with the repository's Isaac Sim version. Read the exact current requirements from ./README.md; do not rely on remembered version numbers. Require Docker only when the requested local VLM or Cosmos service needs it.

Sync

Run the default full setup:

./setup.sh

The explicit equivalent is:

./setup.sh all

Use ./setup.sh clean only when the user explicitly requests a full rebuild or cleanup because it deletes generated caches, component environments, and third-party checkouts. Setup is idempotent; do not clean as a generic repair. The setup script restores pinned third-party sources and the upstream Isaac Sim skill catalog; do not copy that catalog into skills/.

Verify

./run.sh list
./run.sh lint --all
test -f ./third_party/IsaacSim-045ca8b/skills/SKILLS.md

Use run.sh show <workflow> --mode <mode> when the user named a workflow. These checks prove discovery and contracts without importing Isaac Sim. Use i4h-workflow-validate for an actual rollout.

Troubleshooting

On failure, report the first host, network, checkout, or uv-sync error and rerun full setup only after correcting that cause.

Prerequisites

Require supported Linux, network access, uv, Git, disk space, and a compatible NVIDIA GPU/driver for simulator use.

Limitations

Setup does not download every optional checkpoint or prove any rollout succeeds. clean is destructive to generated environments and third-party checkouts.

Examples

Set up the i4h workflow on this machine and tell me if any host requirements are missing. → preflight, run default full setup, then run discovery and lint --all.

Completion gate

Report every host check, synced target, first failing component if any, discovery/lint results, and the smallest next smoke command. Do not claim simulator or policy success from setup alone.

Files

ATTRIBUTION.mdAdded by AutoGineer931 B
BENCHMARK.md6.9 KiB
LICENSELicence file added by AutoGineer11.2 KiB
SKILL.md3.9 KiB
evals/evals.json938 B
skill-card.md4.0 KiB
skill.oms.sig4.5 KiB

BENCHMARK.md

Skill Benchmark: i4h-workflow-setup

✅ Overall verdict: PASS — Recommended for publication

Publication Recommendation

Recommended for publication based on the completed evaluation evidence in this report.

Evaluation Metadata

Skill: i4h-workflow-setup
Evaluation date: 2026-09-15
Evaluator version: 1.5.6
Agents: Claude Code (aws/anthropic/bedrock-claude-opus-4-8), Codex (openai/openai/gpt-5.5)
Tasks: 1 evaluation tasks (1 positive)
Dataset digest: sha256:ade31484d3ac5633cdb8008746e2b20803e31832a7c5b577d8bff9bb02a55354 (skill-evaluator-dataset-snapshot/1)
Attempts per task: 3
Environment: k8s-sandbox
Tier 2 evidence: required for publication
Tier 3 evidence: required for publication

Each task attempt ran in its own isolated sandbox pod.

What This Report Answers

The three-tier evaluation checks whether the skill:

is safe to use;
produces correct answers;
is discovered and activated when needed;
helps the agent complete the user's goal and expected workflow; and
avoids wasted skill and tool usage.

Results at a Glance

Measure	Claude Code (Baseline → Skill Uplift)	Codex (Baseline → Skill Uplift)
Overall	88.8% — baseline ran, but no comparable score was available; uplift unavailable	65.7% — baseline ran, but no comparable score was available; uplift unavailable
Security	100.0% → 100.0% (±0.0 points)	0.0% → 0.0% (±0.0 points)
Correctness	80.0% → 100.0% (+20.0 points)	100.0% → 100.0% (±0.0 points)
Discoverability	95.0% — baseline ran, but no comparable score was available; uplift unavailable	75.0% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness	39.3% → 71.1% (+31.8 points)	85.7% → 95.0% (+9.3 points)
Efficiency	77.9% — baseline ran, but no comparable score was available; uplift unavailable	58.7% — baseline ran, but no comparable score was available; uplift unavailable

How to read this table: baseline is the same task attempted without the target skill. Scores are rounded to one decimal; threshold-adjacent values use additional precision so their displayed band matches the verdict. Uplift is derived from those displayed scores and shown in percentage points.

Example: 47.0% → 92.0% (+45.0 points) means the skill-assisted run scored 92.0%, 45.0 percentage points above its 47.0% no-skill baseline.

Token Usage

Actual Tier 3 execution usage is reported for every observed agent/case pair and both conditions.

Agent	Dataset case	With skill	Without skill	Delta	Change	Coverage
claude-code	All cases	303,304	398,810	-95,506	-23.95%	skill 1/1; base 1/1
claude-code	i4h-workflow-setup-readme-quick-setup	303,304	398,810	-95,506	-23.95%	skill 1/1; base 1/1
codex	All cases	823,880	1,369,599	-545,719	-39.85%	skill 1/1; base 1/1
codex	i4h-workflow-setup-readme-quick-setup	823,880	1,369,599	-545,719	-39.85%	skill 1/1; base 1/1
ALL AGENTS	Dataset aggregate	1,127,184	1,768,409	-641,225	-36.26%	skill 2/2; base 2/2

Prompt tokens include cached reads, so total tokens are prompt + completion (cached is not added twice). The Efficiency score uses (prompt - cached) + completion. N/A means the relevant trajectory counters were not available; coverage is never estimated.

Tier Status

Tier	Purpose	Status	Evidence
Tier 1	Static validation	PASSED	11 validator(s); 0 finding(s)
Tier 2	Semantic deduplication	PASSED	2 validator(s); 0 finding(s)
Tier 3	Live agent evaluation	PASS	2 agent(s); 1 task(s)

Findings and Observations

<details> <summary>Show detailed findings and successful checks</summary>

Schema & Repository Governance: Found skill manifest: SKILL.md
Semantic Version Validation: Valid semantic version: 0.8.0
Security Scan: No security vulnerabilities detected (secrets, API keys, credentials)
PII Scan: Scanning 1 files for PII
Code Integrity & Hygiene: Checking 1 markdown files for dead links
Unicode Smuggling Detection: No invisible Unicode characters detected in 1 file(s)
QUALITY: Score: 100.0/100 (Grade: A)
SCRIPT_LINT: No scripts/ directory found
Context Deduplication: Collected 1 file(s)
Inter-Skill Deduplication: Parsed skill 'i4h-workflow-setup': 167 char description
AGENT_EVAL: Tier 3 evaluation complete: verdict PASS; best agent claude-code

</details>

Scoring Methodology

<details> <summary>Show dimension definitions, source signals, and thresholds</summary>

Dimension	Question	Scored signals
Security	Is it safe to use?	`security` (100%)
Correctness	Is the answer correct?	`accuracy` (100%)
Discoverability	Was the right skill loaded when needed?	`skill_execution` (100%)
Effectiveness	Did the skill help complete the task?	`goal_accuracy` (50%) + `behavior_check` (50%)
Efficiency	Did it avoid wasted tool calls and token usage?	`skill_efficiency` (50%) + `token_efficiency` (50%)

Dimension bands: PASS at 50% or above; NEUTRAL from 40% to below 50%; FAIL below 40%.
Overall Tier 3 lift: PASS at +5 points or more; FAIL at -10 points or less; values between those bands are NEUTRAL.
Overall verdict: PASS only when every configured dimension passes for at least one supported agent. Lift is reported as diagnostic evidence and does not override this gate.
The 50% attempt pass threshold is a separate per-task gate; it is not the dimension pass threshold.
Effectiveness is the equal-weight mean of goal completion (goal_accuracy) and expected workflow adherence (behavior_check).
Efficiency is 50% tool-call productivity (the backward-compatible skill_efficiency wire id) and 50% token_efficiency. Positive-case skill routing is scored under Discoverability, not Efficiency; a negative case without a routing target is N/A. N/A sources are omitted, remaining weights are renormalized, and the dimension is marked partial.

Signals present in this run:

security (Security): unsafe operations, secret leakage, and unauthorized access.
skill_execution (Skill Execution): whether the expected skill was selected, decoys were avoided, and the workflow executed.
skill_efficiency (Tool Productivity): tool-call productivity (legacy wire id; routing is scored under Discoverability).
accuracy (Accuracy): final-answer correctness against the reference answer.
goal_accuracy (Goal Accuracy): whether the user's goal was achieved.
behavior_check (Behavior Check): whether the expected workflow behavior was followed.
token_efficiency (Token Efficiency): actual uncached prompt plus completion usage (50% of Efficiency).

</details>

Freshness

Regenerate this benchmark when the skill, evaluation dataset, target agent/model, evaluator version, environment, or scoring policy changes.

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.

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-setup · 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-setup.zip