New to Claude Skills? Learn how to install them →

nvidia on GitHub

i4h Workflow Replay

OfficialFree

Replay HDF5 episodes for visual verification in Isaac Sim.

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

Free · Opens the source repo

What i4h Workflow Replay does

The i4h Workflow Replay skill allows users to replay recorded HDF5 episodes within Isaac Sim, facilitating visual verification of robotic simulations. This skill is particularly useful for developers and researchers working with robotic workflows who need to confirm the accuracy of their recorded episodes before proceeding to further stages such as training or conversion. By replaying these episodes, users can ensure that the visual outputs align with their expectations and that the simulations behave as intended.

To utilize this skill, users must set up their environment correctly and provide an absolute path to an existing HDF5 recording. The skill supports zero-based episode indexing, allowing users to easily specify which episode they wish to replay. The replay process is executed through a series of bash commands, making it straightforward for those familiar with command-line interfaces. The skill also includes error handling to guide users in resolving common issues, such as missing recordings or mismatched environment IDs.

This skill is designed for users who are already engaged with the i4h workflows ecosystem. It requires an existing setup of the i4h workflows and an HDF5 file generated from previous recordings, such as those created during teleoperation or validation sessions. By integrating this skill into their workflow, users can enhance their ability to debug and verify their robotic simulations effectively, ensuring higher fidelity in their projects.

Overall, the i4h Workflow Replay skill is an essential tool for anyone involved in the development and testing of robotic systems using Isaac Sim, providing a reliable method to validate recorded episodes visually and confirm their correctness before further processing.

When to use it

Use this skill when you need to replay and verify the visual accuracy of HDF5 recordings from Isaac Sim.

When not to use it

This skill is not suitable for modifying or expanding recordings, as it only supports playback of existing episodes.

What you can build with it

Verifying Simulation Outputs

Use the skill to replay episodes and visually confirm that the simulation outputs match your expectations.

Debugging Robotic Workflows

Replay HDF5 recordings to identify issues in robotic workflows and ensure that the simulations are functioning correctly.

Preparing for Training

Before training models, use this skill to verify that the recorded episodes are accurate and ready for further processing.

How to install i4h Workflow Replay

View source

1. Install with the skills CLI

npx skills add nvidia/skills/i4h-workflow-dataset-replay --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 Workflow — Replay Dataset

Purpose

Replay a recorded HDF5 episode inside Isaac Sim for visual verification. Use when the user asks to replay, play back, or step through an HDF5 recording.

Base Code

These steps drive the i4h-workflows base code (the workflows/agentic/ 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:

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

Basics

  • Env config (source of truth): workflows/agentic/config/environments/<env>.yaml — the <env> scene, robot, and cameras Arena replays against.
  • Replay runs arena/run.sh --replay against the env that produced the HDF5.
  • Use it to verify visual correctness before conversion or training.
  • Interpret ordinal wording as zero-based episode indices: "first episode" -> 0, "second episode" -> 1, etc.

Run

Run the steps below in order. Each step is a separate bash call; variables persist in the local agent's tmux session.

Step 1 — setup and resolve HDF5

REPO_ROOT="${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>/dev/null)}"; [ -d "$REPO_ROOT/workflows/agentic" ] || REPO_ROOT="$HOME/i4h-workflows"
ENV_ID=scissor_pick_and_place
RUNS_ROOT="${REPO_ROOT}/workflows/agentic/runs"
EPISODE_INDEX="${EPISODE_INDEX:-0}"  # For "Replay second episode", set EPISODE_INDEX=1.

# Point HDF5_PATH at a real recording (absolute path). Recordings come from teleop, mimic, or
# validate (which writes data/verify.hdf5 under each runs/eval_* dir). List candidates newest-first:
#   find "${RUNS_ROOT}" -name '*.hdf5' -printf '%TY-%Tm-%Td %TH:%TM  %p\n' | sort -r | head
HDF5_PATH="${HDF5_PATH:-}"
if [ ! -f "${HDF5_PATH}" ]; then
  echo "replay: set HDF5_PATH to an existing .hdf5 (got '${HDF5_PATH:-<unset>}'). Candidates:" >&2
  find "${RUNS_ROOT}" -name '*.hdf5' -printf '%TY-%Tm-%Td %TH:%TM  %p\n' 2>/dev/null | sort -r | head
  exit 1
fi

RUN_DIR="${RUNS_ROOT}/replay_${ENV_ID}_$(date +%Y%m%d_%H%M%S)"
mkdir -p "${RUN_DIR}/logs"
ln -sfn "${RUN_DIR}" "${RUNS_ROOT}/.latest"

Step 2 — replay

"${REPO_ROOT}/workflows/agentic/arena/run.sh" \
  --env "${ENV_ID}" \
  --replay "${HDF5_PATH}" \
  --episode-index "${EPISODE_INDEX}" \
  2>&1 | tee "${RUN_DIR}/logs/replay.log"

Notes

  • HDF5_PATH must be an absolute path to an existing recording — --replay resolves a relative path against runs/<env>/, not your cwd, so a bare/relative path silently fails to load. The block lists real candidates if it's unset or wrong.
  • Recordings come from [[i4h-workflow-dataset-teleop]], [[i4h-workflow-dataset-mimic]], or [[i4h-workflow-validate]] (validate writes data/verify.hdf5 under each runs/eval_* dir). There is no default demo.hdf5.
  • --episode-index selects the episode within the HDF5 (zero-based).
  • For "Replay second episode", use --episode-index 1.
  • Use the same env id as the env that produced the recording.

Prerequisites

  • Workflow set up via [[i4h-workflow-setup]] (the .venv must exist).
  • An existing HDF5 recording to replay.
  • The env id that produced the recording.

Limitations

  • Visual verification only; replay does not modify or expand the recording.
  • Replays one episode per invocation, selected by --episode-index.
  • Runs inside Isaac Sim; the env id must match the one that produced the HDF5.

Troubleshooting

  • Error: .venv not found / replay fails to launch - Cause: workflow not set up. Fix: run [[i4h-workflow-setup]] first.
  • Error: replay: set HDF5_PATH to an existing .hdf5 (or recording fails to load) - Cause: HDF5_PATH unset or not a real file. Fix: pick an absolute path from the printed candidates (e.g. a verify.hdf5 under runs/eval_*/data/).
  • Error: episode index out of range - Cause: --episode-index exceeds the episodes in the HDF5. Fix: use a valid zero-based index.
  • Error: mismatched/garbled playback - Cause: --env differs from the env that produced the recording. Fix: use the same env id.

Final Response

Report env, HDF5 path, episode index, launch outcome, visible mismatches.

Frequently asked questions about i4h Workflow Replay

Similar skills