Official agent skill

I4h Workflow

by NVIDIA in NVIDIA/skills

Orient users to the i4h workflow runtime and route them to the correct stage skill.

OfficialApache-2.0Auto-check passed

Install I4h Workflow

skills CLI
$ npx skills add NVIDIA/skills --skill i4h-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NVIDIA/skills i4h-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/i4h-workflow .claude/skills/i4h-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
i4h-workflow
GitHub stars
3.5k
Used in
1 other repo
Token cost
~1.3k tokens
SKILL.md length
513 words
Files
6 (incl. references)
Skills in repo
380
Repo updated
First seen
Licence
Apache-2.0

At a glance

Orient users to the i4h workflow runtime and route them to the correct stage skill.

  • Works in 4 steps: Run the base-checkout resolver. → Read live support and DESIGN.md. → Use only current architecture facts in… → …
  • Where-to-start questions
  • SKILL.md covers Purpose, Instructions, Resolve the checkout and Inspect before answering, plus 7 more sections
  • Calls git; reaches github.com

What it does

I4h Workflow is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `BENCHMARK.md`, `evals/evals.json` and `references/repo-map.md`).

The repository describes itself as: Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The licence is Apache-2.0.

When your agent uses it

  • Where-to-start questions
  • Do not execute a known stage

Example prompts

  • “/i4h-workflow”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Run the base-checkout resolver.
  2. Read live support and DESIGN.md.
  3. Use only current architecture facts in the answer.
  4. Use the narrowest stage skill for execution.

What it can do on your machine

Read from SKILL.md and the folder at commit 67a13c0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

I4h Workflow loads about 1.3k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 513 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/skills at commit 67a13c0, republished under its Apache-2.0 licence (© NVIDIA). 513 words, ~1,301 tokens.

Download SKILL.mdSave it as .claude/skills/i4h-workflow/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
i4h-workflow
description
Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.
license
Apache-2.0
metadata.author
Isaac for Healthcare Team <isaac-for-healthcare-support@nvidia.com>
metadata.version
0.8.0
metadata.verification-request
2026-09-15
metadata.tags
isaac-for-healthcare, i4h, robotics, onboarding

i4h Workflows

Purpose

Orient the user from live repository facts, then hand execution to the narrowest stage skill.

Instructions

  1. Run the base-checkout resolver.
  2. Read live support and DESIGN.md.
  3. Use only current architecture facts in the answer.
  4. Use the narrowest stage skill for execution.

Resolve the checkout

bash
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.

Inspect before answering

Read ./DESIGN.md for architecture and skills/i4h-workflow/references/repo-map.md for ownership. Discover current support instead of copying a static table:

bash
./run.sh list

If discovery fails because setup is incomplete, report that limitation and route to i4h-workflow-setup.

Explain the design

Keep the summary precise:

  • A Scene owns the simulated world, assets, embodiment, cameras, randomization, adapters, and reset hooks.
  • A Task owns one reusable capability. It reads ctx.scene, writes ctx.act, and never advances the simulator.
  • A Workflow selects one Scene, exposes run-mode-specific TaskGraph builders, and owns goal semantics. A run mode answers how that workflow should run; code and CLI use the shorter term mode.
  • The Engine schedules graph nodes; the shared SimulationRunner alone resets, steps, renders, records, retries whole episodes, and prints run summaries.
  • Online RL is a separate training lifecycle: its trainer owns vectorized stepping and returns a checkpoint to the normal policy Task and SimulationRunner validation path.
  • Simulator-compatible exported RSL-RL actors may run as in-process Tasks; incompatible foundation-model policy stacks remain remote.
  • Remote policy stacks run out of process and communicate over Zenoh; offline dataset tools remain independent of the simulator.
  • Python owns behavior. Manifests carry facts across dependency boundaries.

Do not describe retired environment YAMLs, per-mode runners, or separate policy/Arena launchers.

Show full SKILL.md (205 more words)Show less

Route the next action

GoalSkill
Install, sync, or repair dependenciesi4h-workflow-setup
Create a new workflow/environmenti4h-workflow-create
Edit an existing scene, camera, task, or success rulei4h-workflow-scene-edit
Record demonstrationsi4h-workflow-dataset-teleop
Replay HDF5i4h-workflow-dataset-replay
Augment HDF5i4h-workflow-dataset-mimic
Grade/filter HDF5 with a VLMi4h-workflow-dataset-annotate
Convert HDF5 to LeRoboti4h-workflow-dataset-convert
Inspect LeRobot in a browseri4h-lerobot-viz
Fine-tune a manifest-backed policy taski4h-workflow-finetune
RL post-train a supported policy in simulationi4h-workflow-train-rl
Run policy or rule-based rolloutsi4h-workflow-validate
Run the maintained complete pipelinei4h-workflow-e2e

For Stop all, do not load a stage skill. Run ./stop.sh all from the repository root and report the stopped process count.

Troubleshooting

If discovery fails, verify the resolved checkout and run setup. If a mode is absent, report it as unsupported.

Prerequisites

Require a readable base checkout or network access to clone it.

Limitations

This router does not install, author, simulate, process data, train, or evaluate.

Examples

  • What does the i4h workflow include, and where should I start? → inspect live support, summarize DESIGN.md, and recommend one stage skill.

Completion gate

Answer with the live workflow/mode list, a short architecture summary, and one concrete next skill. If the requested workflow or mode is absent from run.sh list, say it is unsupported instead of inventing a command.

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/i4h-workflow of NVIDIA/skills.

  • SKILL.md
  • BENCHMARK.md
  • evals/evals.json
  • references/repo-map.md
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 67a13c0

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in NVIDIA/skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

I4h Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

I4h Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
I4h Workflow this skillNVIDIA/skills3.5k1 repos~1.3kAutomated safety check: PassApache-2.0
Orientationthedaviddias/Front-End-Checklist74k—~625Automated safety check: PassMIT
OmniRoute Routing CLIdiegosouzapw/OmniRoute74k1 repos~342Automated safety check: PassMIT
OmniRoute Combo Routingdiegosouzapw/OmniRoute74k—~2.1kAutomated safety check: PassMIT
Intelligence Routeruvnet/ruflo74k—~874Automated safety check: NotesMIT
OrientDrCatHicks/learning-opportunities2.5k—~3.1kAutomated safety check: NotesCC-BY-4.0

Similar skills

  • Orientation

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing mobile-first layouts, tablet experiences, fullscreen flows, forms, dashboards, or media interfaces.

    74k GitHub stars~625 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • OmniRoute Routing CLI

    diegosouzapw/OmniRoute

    Creates, switches, and inspects OmniRoute model-routing combos, plus a suggestion command with cost and latency constraints.

    74k GitHub starsUsed in 1 repo~342 tokens
    AI & LLM EngineeringAuto-check passed
  • OmniRoute Combo Routing

    diegosouzapw/OmniRoute

    Manages OmniRoute routing combos through its REST API: create and update combos, choose from 19 strategies, set fallback chains, test outcomes and read metrics.

    74k GitHub stars~2.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Intelligence Route

    ruvnet/ruflo

    Route tasks via the 3-tier model selector and learned patterns; emits a routing rationale via hooksexplain

    74k GitHub stars~874 tokensUpdated today
    DevelopmentAuto-check: notes
  • Orient

    DrCatHicks/learning-opportunities

    Generates a repo-specific orientation.md resource for the learning-opportunities skill.

    2.5k GitHub stars~3.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Explains LobeHub's split between src/routes page segments and src/features domain code, and where router config, redirects and platform adapters belong.

    83k GitHub stars~3.2k tokensUpdated today
    Frontend & DesignAuto-check passed

More from NVIDIA/skills

All 380 skills in this repo
  • Official

    A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.

    3.5k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed
  • Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.5k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • Official

    Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.

    3.5k GitHub stars~4.8k tokensUpdated yesterday
    Auto-check passed
  • Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

    3.5k GitHub stars~5k tokensUpdated yesterday
    Auto-check: notes
  • Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

    3.5k GitHub stars~4.7k tokensUpdated yesterday
    Auto-check: notes
  • Official

    Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

    3.5k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check: notes

Questions about I4h Workflow

What does I4h Workflow do?

Orient users to the i4h workflow runtime and route them to the correct stage skill. I4h Workflow is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Orient users to the i4h workflow runtime and route them to the correct stage skill.

When should I use I4h Workflow?

I4h Workflow fits situations like: where-to-start questions; do not execute a known stage.

How do I install I4h Workflow in Claude Code?

Run `npx skills add NVIDIA/skills --skill i4h-workflow -a claude-code`. Or copy the skill folder (skills/i4h-workflow in NVIDIA/skills) into .claude/skills/i4h-workflow in your project. Claude Code loads it when a task matches its description.

How do I install I4h Workflow in Codex?

Run `npx skills add NVIDIA/skills --skill i4h-workflow -a codex`. Or copy the skill folder (skills/i4h-workflow in NVIDIA/skills) into .agents/skills/i4h-workflow in your project. Codex loads it when a task matches its description.

Can I use I4h Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill i4h-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/i4h-workflow, .gemini/skills/i4h-workflow, .github/skills/i4h-workflow and .opencode/skills/i4h-workflow in your project.

What does I4h Workflow need to run?

Going by SKILL.md and its folder, I4h Workflow needs the command-line tools its instructions call (git). Our summary lists: Python 3.

Does I4h Workflow access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is I4h Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does I4h Workflow use?

I4h Workflow is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does I4h Workflow use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 903 tokens, read only when the agent opens those files.

What are the alternatives to I4h Workflow?

Skills that share tags, products or a category with I4h Workflow: Orientation (thedaviddias/Front-End-Checklist, 74k stars), OmniRoute Routing CLI (diegosouzapw/OmniRoute, 74k stars), OmniRoute Combo Routing (diegosouzapw/OmniRoute, 74k stars) and Intelligence Route (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains I4h Workflow?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,539 GitHub stars. The repository holds 380 skills in this directory. The repository was last updated on October 7, 2026.

Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.