CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tao-train-nvpanoptix3d

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-style head and 3D frustum reconstruction. Use when training, evaluating, exporting, or running inference for a TAO NVPanoptix3D model. Trigger phrases include "train NVPanoptix3D", "panoptic 3D reconstruction", "3D scene segmentation", "occupancy completion".

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is exceptionally actionable — exact commands, complete spec overrides, parameter defaults, and error-fix pairs — but suffers from duplicated content (repeated description, PRQ guidance in two sections), an fsdp support contradiction across three sections, and dependencies on a schemas/ directory that is not packaged. Fixing the contradiction, the padding, and the missing schemas would raise workflow clarity and progressive disclosure.

Suggestions

Resolve the fsdp contradiction: 'Important Parameters' lists 'train.distributed_strategy: Options: ddp, fsdp' and Hardware says 'FSDP for multi-node', while the Multi-GPU section says fsdp is NOT supported — pick one truth and state it consistently (and remove the duplicated --shm-size=8g line in DOCKER_COMMON).

Package the schemas/ directory the body gates on (schemas/train.schema.json, schemas/<action>.schema.json, schemas/manifest.json) or rewrite the AutoML routing and Dataclass Schemas sections so they do not depend on files absent from the bundle.

Cut duplication to improve token efficiency: drop the verbatim repeat of the frontmatter description in the intro, and consolidate the PRQ metric guidance stated in both 'Train Action Policy' and 'Training Requirements' into one section; also make the checkpoint handoff explicit (which checkpoint file evaluate/inference/export should consume after train/AutoML).

DimensionReasoningScore

Conciseness

Mostly efficient — nearly every line carries model-specific operational detail Claude would not know — but there is real padding: the intro repeats the frontmatter description verbatim, PRQ metric guidance is stated in both 'Train Action Policy' and 'Training Requirements', and the Train Action Policy prose could be tightened. Not a 4 because these duplications are more than minor trimming instances.

3 / 5

Actionability

Fully executable guidance: exact docker run commands with the full module entrypoint, complete Python spec-override dicts per action, parameter tables with defaults/enums, and error patterns paired with specific fixes (e.g. 'ValueError: Only fp32 precision is supported' → 'train.precision: fp32'). Copy-paste ready and covers the common cases.

5 / 5

Workflow Clarity

Per-action commands are unambiguous, but there is an internal incoherence: 'Important Parameters' and 'Hardware' present fsdp as a supported option ('FSDP for multi-node') while the Multi-GPU section states 'fsdp is NOT supported', and checkpoint selection for evaluate/inference/export is left implicit ('<selected train/AutoML checkpoint>'). Validation checkpoints exist only in the AutoML promotion path, not for the direct train→evaluate handoff. This fits the anchor of steps present but checkpoints missing or implicit, with contradictions preventing a 4.

3 / 5

Progressive Disclosure

References to references/skill_info.yaml and references/spec_template_<action>.yaml resolve in the bundle, but the body repeatedly depends on schemas/<action>.schema.json and schemas/manifest.json ('Generated TAO Core schemas are packaged in schemas/...'), and no schemas/ directory exists in this bundle — a referenced path the AutoML routing policy explicitly gates on. Combined with ~300 lines of dense reference material inlined in SKILL.md, this is the 'structure present but referenced paths not fully reliable / content that could be separate is inline' level rather than a 4.

3 / 5

Total

14

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities and outputs, gives an explicit 'Use when' clause naming all four actions, and lists specific trigger phrases anchored to a uniquely named model. The only weakness is slightly incomplete synonym coverage among trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('training, evaluating, exporting, or running inference') plus concrete outputs ('semantic, instance, and panoptic masks', 'occupancy completion'), giving comprehensive coverage of the model's capabilities. Not a level below because coverage of the four actions with specific outputs matches the comprehensive anchor rather than having minor gaps.

5 / 5

Completeness

Explicitly answers both 'what' ('Produces 3D panoptic segmentation ... with occupancy completion') and 'when' ('Use when training, evaluating, exporting, or running inference for a TAO NVPanoptix3D model'), with concrete trigger phrases listed. This matches the anchor that clearly answers both what AND when with concrete triggers.

5 / 5

Trigger Term Quality

Trigger phrases ('train NVPanoptix3D', 'panoptic 3D reconstruction', '3D scene segmentation', 'occupancy completion') are natural terms for this domain, but a few natural variations users might say are missing (e.g. 'semantic segmentation', 'instance segmentation', '3D reconstruction from images'). Not a 5 because synonym coverage is incomplete; not a 3 because the included phrases are specific and match how users would phrase requests rather than generic keywords.

4 / 5

Distinctiveness Conflict Risk

Clear niche: a named TAO model (NVPanoptix3D) with model-specific triggers like 'train NVPanoptix3D' — minimal overlap risk with other skills. Not lower because the triggers are anchored to a unique model name rather than broad phrases.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

NVIDIA/skills

Path

skills/tao-train-nvpanoptix3d/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.