I4h Workflow Dataset Replay

What it does

When your agent uses it

• Visual trajectory and recording verification
• Do not use for policy evaluation

Example prompts

• “/i4h-workflow-dataset-replay”

Workflow steps

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

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

What it can do on your machine

Read from SKILL.md and the folder at commit 14a98ae. 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
  • uv

  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 Dataset Replay loads about 972 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 333 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~48

When it runs · the whole SKILL.md, loaded when a task matches

~972

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

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 14a98ae, republished under its Apache-2.0 licence (© NVIDIA). 333 words, ~972 tokens.

name

i4h-workflow-dataset-replay

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.

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, dataset, replay, hdf5

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

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

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

© 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 4 other files in skills/i4h-workflow-dataset-replay of NVIDIA/skills.

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

Open the folder on GitHubat commit 14a98ae

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.

• isaac-for-healthcare/i4h-workflowsskills/i4h-workflow-dataset-replay