CtrlK
BlogDocsLog inGet started
Tessl Logo

physical-ai-neural-reconstruction

Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.

63

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/nvidia/skills/physical-ai-neural-reconstruction/SKILL.md

The canonical home for this skill is physical-ai-neural-reconstruction in NVIDIA/skills

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a well-organized, actionable router with strong progressive disclosure and clear workflow sequencing; its main weakness is minor repetition across sections that slightly hurts token efficiency.

Suggestions

Consolidate the SimReady exclusion so it lives in one canonical place (e.g., the Limitations section) and is referenced rather than restated in Purpose and Hard Rules.

Avoid restating the full prerequisite list in the body since the frontmatter compatibility field already captures it; link to it instead.

DimensionReasoningScore

Conciseness

Mostly efficient and well-structured, but there is repetition that could be tightened: the SimReady caveat appears in Purpose, Hard Rules, and Limitations, and the Prerequisites section duplicates the frontmatter compatibility block.

2 / 3

Actionability

Provides copy-paste executable bash (the upstream clone/refresh block, secret-verification checks) and a concrete goal-to-skill picker table with explicit ordering arrows — fully actionable routing guidance.

3 / 3

Workflow Clarity

Multi-step NuRec workflows are explicitly sequenced (data -> conversion -> train -> render -> cleanup) with ordering arrows in the picker table, and the fetch recipe includes an explicit validation checkpoint (`test -f .../SKILL.md`) plus a 'read upstream before mutating' rule.

3 / 3

Progressive Disclosure

Clear overview body with well-signaled, one-level-deep references to real bundle files (workflows.md, mix-ups.md, teardown.md, upstream-fetch.md, secrets-handling.md, maintenance.md), all of which exist in ./references/; content is appropriately split for easy navigation.

3 / 3

Total

11

/

12

Passed

Description

67%Weight 40%Scale 1-3

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

The description is specific and well-bounded with clear negative scope, but it omits an explicit "Use when..." trigger clause and its keywords lean technical, capping trigger quality and completeness at 2.

Suggestions

Add an explicit "Use when..." clause listing natural-language triggers a user would say (e.g., 'Use when a user asks about neural reconstruction, training or rendering a NuRec scene, or converting recordings to NCore').

Soften purely technical tokens with at least one plain-language variation (e.g., '3D Gaussian Splatting (3DGS)') so non-expert phrasing still matches.

DimensionReasoningScore

Specificity

Lists multiple concrete capability domains — "USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets" — matching the anchor for several specific actions rather than vague language.

3 / 3

Completeness

Clearly states what the skill does (router for NuRec/NRE) but provides no explicit "Use when..." trigger clause; the rubric caps completeness at 2 when trigger guidance is only implied via a negative "Do NOT use for..." clause.

2 / 3

Trigger Term Quality

Includes relevant niche terms ("NuRec/NRE", "USDZ", "NCore", "3DGS", "gRPC sensor sim") but these lean technical and lack common natural-language variations a user might phrase; no explicit "Use when..." trigger phrasing.

2 / 3

Distinctiveness Conflict Risk

The narrow NVIDIA NuRec/NRE niche plus the explicit negative boundary ("Do NOT use for SimReady or infra setup") makes it clearly distinguishable and unlikely to trigger for the wrong skill.

3 / 3

Total

10

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
openai/plugins
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.