Skip to content
cccskills
FreePublished on GitHub

i4h-workflow-dataset-replay

Replay an episode stored in HDF5, a structured data file, using its original workflow Scene. Check the full recorded motion visually, inspect segment boundaries and camera views, and report agreement or the first mismatch.

OriginalShow the original description

Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.

See how to install

Good for

  • Visually verify a recorded motion trajectory
  • Replay a specific episode from an HDF5 recording
  • Inspect camera views and segment boundaries
  • Locate the first mismatch during replay

Files included (5)

  • SKILL.md3.8 KB
  • BENCHMARK.md6.8 KB
  • evals/evals.json1.1 KB
  • skill-card.md3.9 KB
  • skill.oms.sig4.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Replay a Workflow Recording

Purpose

Replay the exact recorded action sequence through the matching workflow and inspect it visibly.

Instructions

  1. Run the checkout resolver and select the exact HDF5.
  2. Read the original workflow and requested episode.
  3. Inspect action-contract compatibility.
  4. Run the replay visibly in the foreground through completion.

Resolve the recording

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"
find runs -name '*.hdf5' -type f -printf '%T@ %p\n' | sort -nr | head

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.

Use an explicit or current-chain recording first. Otherwise select the newest plausible HDF5 and state that choice. Never substitute an older file after a failed recording.

Interpret natural ordinals as zero-based indices: first is 0, second is 1.

Inspect before launch

HDF5_PATH=/absolute/path/to/recording.hdf5
uv run --project tools/dataset i4h-dataset inspect "$HDF5_PATH" --segments

Resolve the original workflow from recording metadata and conversation context. Confirm the requested episode exists and its action width matches the workflow's replay Scene contract.

Replay

./run.sh <workflow> --replay "$HDF5_PATH" --episode <zero-based-index>

Keep the visible simulator and command in the foreground. Poll yielded execution until run.sh exits; do not detach or return while replay is still running.

Verify

Observe the complete trajectory, relevant objects, camera views, segment boundaries, and final status. If motion diverges, report the first mismatching segment or action-contract error. Do not change workflow, episode, or recording silently.

Troubleshooting

On launch failure, verify workflow metadata, episode existence, and action width. On divergence, report the first mismatching segment.

Prerequisites

Require the original workflow assets and a readable episode whose action width matches replay mode.

Limitations

Replay verifies stored actions in one Scene; it does not evaluate a learned policy or guarantee transfer to another Scene.

Examples

  • Replay the second episode. → select the current recording, map “second” to index 1, and observe the visible replay.

Completion gate

Report workflow, HDF5 path, episode index, frame/segment count, action width, exit/final status, and visible agreement or first mismatch.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Move pandas-style table processing to NVIDIA GPUs using cuDF. Choose minimal-change acceleration or explicit GPU code, handle joins and aggregations, compare results with pandas, and use dask-cuDF when data exceeds GPU memory.

  • Accelerate existing pandas processing with minimal changes
  • Move joins and aggregations to GPU code
  • Compare missing values and ordering with pandas
NVIDIA/skills3.7KUpdated Oct 22, 2026

Customize NVIDIA Nemotron Voice Agent’s Generic Pipecat example for appointment scheduling, five-field patient intake, or a custom healthcare conversation. Build prompts and tool handlers without a separate backend, then validate conversation behavior, services, and voice interaction.

  • Build an appointment-scheduling voice agent
  • Collect five patient-intake fields through conversation
  • Design a custom healthcare conversation with tool calls
NVIDIA/skills3.7KUpdated Oct 22, 2026

Calibrate live cameras by recording their RTSP video streams through VIOS and processing the clips with AutoMagicCalib. The workflow imports settings and alignment files, checks readiness, tracks calibration progress, and retrieves results.

  • Calibrate cameras from live RTSP streams
  • Import settings and alignment files for a camera scene
  • Retrieve evaluation statistics using ground truth data
NVIDIA/skills3.7KUpdated Oct 22, 2026

Test a running AMC service with the bundled four-camera warehouse dataset. Run camera calibration from upload to completion, then check distance and image projection errors against ground-truth data to verify the installation.

  • Verify a newly installed AMC service
  • Check the sample's calibration errors against ground truth
  • Walk through the sample workflow in Swagger UI
NVIDIA/skills3.7KUpdated Oct 22, 2026

Calibrate multiple cameras from recorded MP4 files through the AutoMagicCalib REST API. The skill handles project creation, uploads, input verification, progress checks, and evaluation when reference data is supplied, with optional VGGT refinement.

  • Calibrating cameras from synchronized MP4 recordings
  • Uploading local settings and alignment files
  • Evaluating calibration against ground-truth data
NVIDIA/skills3.7KUpdated Oct 22, 2026

Set up AutoMagicCalib from NGC release containers using Docker Compose. The skill handles registry authentication, port and path configuration, optional VGGT model download, service startup, and readiness checks for the backend and web interface.

  • Launching the AutoMagicCalib backend and web interface
  • Configuring service ports and network access
  • Adding the optional VGGT model during setup
NVIDIA/skills3.7KUpdated Oct 22, 2026

See all skills by NVIDIA

Report a problem with this skill