Physical AI Neural Reconstruction

Locate and fetch the upstream skills

Try the local disk first, in this order — a sibling skill already installed in the runtime is preferable to a network fetch. This applies to the nurec-skills-hosted siblings; asset-harvester is fetched from its own repo (see references/upstream-fetch.md):

1. .agents/skills/<name>/SKILL.md (Cursor, Codex, NemoClaw)
2. .claude/skills/<name>/SKILL.md (Claude Code)
3. .cursor/skills/<name>/SKILL.md (project-scoped)
4. ~/.cursor/skills/<name>/SKILL.md (personal skills)
5. An existing nurec-skills clone under the shared upstream root.

This order covers the nurec-skills-hosted siblings only. asset-harvester is not among them — see references/upstream-fetch.md.

Only if none of those exist, ask the user for explicit consent before cloning. A git clone is a network fetch of an external repository plus a write to the local filesystem; it can violate org network policy and carries supply-chain risk. Show the user what you intend to run and wait for a yes.

Quick recipe (full version, including the pinned-commit layout, in references/upstream-fetch.md):

UPSTREAM_ROOT="${NUREC_SKILLS_UPSTREAM_ROOT:-${PHYSICAL_AI_SKILL_HUB_UPSTREAM_ROOT:-$HOME/.physical-ai-skill-hub/upstreams}}"
mkdir -p "$UPSTREAM_ROOT"
if [ -d "$UPSTREAM_ROOT/nurec-skills/.git" ]; then
  git -C "$UPSTREAM_ROOT/nurec-skills" fetch --tags
  git -C "$UPSTREAM_ROOT/nurec-skills" checkout main
  git -C "$UPSTREAM_ROOT/nurec-skills" pull --ff-only
else
  # Only after the user has agreed. Prefer --branch <tag-or-sha> over HEAD.
  git clone --depth 1 https://github.com/NVIDIA/nurec-skills.git \
    "$UPSTREAM_ROOT/nurec-skills"
fi
test -f "$UPSTREAM_ROOT/nurec-skills/skills/nurec-index/SKILL.md"

The upstream tree is rooted at skills/<name>/SKILL.md; .agents/skills is a symlink onto skills/, so either path resolves. Read the upstream skill before running any mutating command:

cat "$UPSTREAM_ROOT/nurec-skills/skills/nurec-index/SKILL.md"  # upstream router
cat "$UPSTREAM_ROOT/nurec-skills/skills/<folder>/SKILL.md"     # sibling

Companion files (references/, scripts/, assets/) ship inside the sibling's own skill directory, alongside its skill definition — not next to this router.

Hard Rules

• Router only — do not duplicate upstream NuRec recipes here. Read the upstream sibling skill body before running any mutating command.
• Refer to sibling skills by their name: (e.g. nre), not by repo path. Folder layouts can change; the name is portable.
• Never git clone the upstream without explicit user consent. For the nurec-skills siblings, exhaust the local lookup order first, show the exact command, and clone only into a path the user agreed to — never silently into /tmp. Do not scan broad developer workspaces such as ~/Codes or reuse unrelated old clones.
• Use the GA container channel: nvcr.io/nvidia/nre/nre-ga and nvcr.io/nvidia/nre/nre-tools-ga. The un-suffixed nvcr.io/nvidia/nre/nre / nre-tools names are the legacy channel — still valid for cached version pins, but not what a new workflow should pull.
• Resolve the NGC key as ${NGC_CLI_API_KEY:-${NGC_API_KEY:-}} and log in with docker login nvcr.io --username '$oauthtoken' --password-stdin. Never echo a key.
• physical-ai-datasets covers gated Hugging Face datasets. Do not bypass dataset license terms; the user must accept the PhysicalAI-* gated licenses on Hugging Face and provide a token before downloading.
• Asset Harvester runs before packaging into a USDZ. Do not call nre's export-external-assets on hand-rolled .ply files unless the user explicitly asks to skip Asset Harvester.
• For artifact cleanup, prefer the built-in --enable-difix path in nre. Route to the standalone nurec-fixer only when the user needs the public code/model card, paired evaluation, fine-tuning, or fixes on previously rendered frames.
• Do not invent NRE / NCore / DiffusionHarmonizer commands from memory. Re-read the upstream sibling skill — versions move fast (NRE 26.04 — pull nvcr.io/nvidia/nre/nre-ga:26.04.01 or :26.04; the release name release_26.04 is not a valid image tag — and NCore 2026.04 are the current pins).
• This router does not deploy infrastructure. Route AKS / OSMO / NIM Operator setup to physical-ai-infrastructure-setup-and-resilient-scaling.

Limitations

• Router only. This skill never executes mutating NuRec commands. All training, rendering, conversion, and harmonization happens in upstream sibling skills.
• Upstream-pinned. Most recipes live in https://github.com/NVIDIA/nurec-skills; asset-harvester lives in https://github.com/NVIDIA/asset-harvester, which evolves outside this repo. Stale clones can drift; always refresh the upstream before relying on a sibling skill.
• Hand-curated catalogue. A newly-added upstream sibling is not discoverable here until someone edits the tables (see references/maintenance.md).
• Gated content. nvidia/PhysicalAI-*, nvidia/Harmonizer, and nvidia/Cosmos-Predict2-0.6B-Text2Image require the user to accept license terms on Hugging Face first. For asset-harvester only its optional DINOv3, Llama Guard and SAM 3D Body models are gated. The router cannot bypass this.
• Heavy footprint. A complete NuRec workflow can leave 150 GB+ on disk. See references/teardown.md.
• NVIDIA-only stack. Requires Linux x86_64 plus an NVIDIA GPU and the NVIDIA Container Toolkit. aarch64 / AMD / Intel / Apple Silicon are not supported.
• No Omniverse / Isaac Sim integration steps. Handing a USDZ to Isaac Sim 5.1 (workflow C) is documented in the Isaac Sim docs, not in the NuRec skill family.
• Not a SimReady pipeline. NuRec produces a renderable USDZ from a recording; SimReady packaging of CAD or source meshes is a different pipeline (see omniverse-cad-to-simready).

Troubleshooting

Routing-level symptoms — a missing upstream clone, gated-asset 403s, NGC login failures, manifest unknown on an NRE image, stale cached skill names — are tabulated in the troubleshooting companion file that ships alongside this skill. Symptoms specific to a sibling's own commands belong to that sibling's skill.

Cross-skill teardown

A complete NuRec workflow can leave 150 GB+ on disk between container images, model weights, code clones, conda envs, and output directories. Each sibling skill has its own dedicated Teardown section — read them in the order documented in references/teardown.md when the user no longer needs the workflow. Do not revoke NGC_API_KEY / HF_TOKEN as part of teardown unless they were leaked.

Keeping this router up to date

Procedure for adding new sibling skills, renames, or upstream URL changes lives in references/maintenance.md. Treat the upstream nurec-index at https://github.com/NVIDIA/nurec-skills/blob/main/skills/nurec-index/SKILL.md as authoritative for the routing taxonomy and workflow ordering; this skill mirrors only the picker tables, the workflow ordering, and the upstream fetch recipe. It is not authoritative for asset-harvester, which is maintained in https://github.com/NVIDIA/asset-harvester.