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.

66

Quality

81%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A well-structured router skill body: highly actionable routing tables and executable fetch/verification recipes, clear sequenced workflows with validation, and clean progressive disclosure into six real reference files. The only soft spot is mild repetition of the difix/teardown routing across several sections.

DimensionReasoningScore

Conciseness

Mostly efficient with terse tables and no basic-concept padding; not a 5 because some routing (difix vs nurec-fixer, teardown) is restated across the picker table, Hard Rules, Limitations, and Troubleshooting and could be tightened.

4 / 5

Actionability

Provides copy-paste-ready bash (clone/refresh block, secret-verification checks), specific container URIs, env vars, file paths, and CLI flags, plus a decisive picker table — fully executable guidance covering the common routing cases.

5 / 5

Workflow Clarity

Sequences multi-step workflows (data -> conversion -> train -> render -> cleanup) with arrows, six labeled A-F workflows, and explicit validation/checkpoints (verify secrets, `test -f` after clone, 'read upstream before mutating'), reinforced by an error->cause->fix troubleshooting table.

5 / 5

Progressive Disclosure

Clear overview body with well-signaled one-level-deep references; all six referenced files (workflows, mix-ups, secrets-handling, teardown, upstream-fetch, maintenance) exist as real, single-topic files, giving easy navigation.

5 / 5

Total

19

/

20

Passed

Description

70%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 tightly scoped, third-person router description with concrete capability tags and good conflict-avoidance guidance. Its main gap is the absence of an explicit positive 'Use when...' trigger clause, which leaves the 'when' only weakly implied via the negative boundary.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user mentions NuRec, neural reconstruction, NRE, USDZ rendering, or NCore conversion') to lift completeness above 3.

Fold one or two user-natural synonyms from the body (e.g., 'neural reconstruction', '3D Gaussian Splatting') into the description to raise trigger-term coverage toward 5.

Expand abbreviated tags into verb-led actions (e.g., 'renders USDZ scenes, converts recordings to NCore V4') for more comprehensive specificity.

DimensionReasoningScore

Specificity

Names several concrete capabilities ('USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets') with only minor coverage gaps; not a 5 because actions are abbreviated jargon rather than comprehensive verb-led descriptions.

4 / 5

Completeness

Has a clear 'what' ('Router for NVIDIA NuRec/NRE...') but no explicit positive 'Use when...' trigger clause — only a negative boundary ('Do NOT use for SimReady or infra setup'), which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms a user would say (NuRec, NRE, USDZ, NCore, 3DGS, gRPC, PhysicalAI) plus anti-triggers (SimReady, infra); not a 5 because synonyms and the natural phrase 'neural reconstruction' live in the body rather than the description field.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear NVIDIA NuRec/NRE niche with explicit conflict-avoidance ('Do NOT use for SimReady or infra setup'), giving distinct triggers and minimal overlap risk.

5 / 5

Total

16

/

20

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.