CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nvidia-skill-finder

Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, RAPIDS/cuDF, cuPyNumeric, cuOpt, Dynamo, Holoscan, TensorRT, DeepStream, VSS, TAO, NGC/NVCF. Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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, highly actionable instruction-only router skill with executable commands, clear sequencing, guardrails against fabrication, and a properly signaled one-level-deep reference. Its main weaknesses are redundancy — catalog sources listed twice and taxonomy content duplicated between the body and the reference — plus an unspecified step for checking whether a skill is already installed.

Suggestions

Deduplicate the catalog source list: state the four sources once and reference that list from the fallback instruction instead of repeating all four URLs verbatim.

Move the catalog-lane enumeration and distinctive-phrase lists out of the body into references/taxonomy-routing.md (which already contains them), keeping only a pointer plus a few examples in SKILL.md.

Specify how to perform step 1 (e.g., check available skills or in-context skill names for an installed NVIDIA skill before querying the catalog).

DimensionReasoningScore

Conciseness

The four catalog sources are listed twice verbatim (the 'Catalog check means one of' bullets and again as 'Use the fallback catalog sources' bullets), and the product/lane enumerations repeat the description and duplicate references/taxonomy-routing.md. It is mostly purposeful with no explanations of concepts Claude already knows, matching anchor 3 ('could be tightened') rather than 2, but the duplicated passages keep it below 4.

3 / 5

Actionability

Fully executable, copy-paste-ready guidance covering the common cases: 'npx skills add nvidia/skills --list' with three concrete fallback URLs, per-agent install commands ('--agent codex', '--agent claude-code', and omitting --agent when unknown), a literal recommendation-format template, and a defined failure path ('say the catalog could not be checked and do not name a concrete slug'). Matches anchor 5.

5 / 5

Workflow Clarity

A clear numbered 5-step discovery sequence (check installed → query live catalog → match → recommend at most three → ask before installing) with error-recovery paths: fallback sources when the CLI fails and anti-fabrication handling when lookup fails. Minor validation gaps — how to check whether a skill is 'already installed or already in context' is unspecified and there is no post-install verification — place it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

One reference file (references/taxonomy-routing.md, which exists in the bundle) is clearly signaled with a conditional load instruction ('Read ... only when the request is taxonomy-only, ambiguous') and is one level deep. However, the body inlines roughly 25 lines of catalog-lane and distinctive-phrase lists that duplicate the reference's 'Stable Catalog Lanes' content, so content is not fully split — anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

81%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 trigger-oriented description with excellent natural keyword coverage, synonym clusters, and explicit negative boundary guidance that minimizes mis-activation. Its main weakness is that the skill's concrete capability (discovering and recommending NVIDIA catalog skills) is only implied, never explicitly stated.

Suggestions

State the concrete action explicitly, e.g. 'Finds and recommends NVIDIA skills from the live catalog, with install commands' before the trigger list, so the 'what' is as explicit as the 'when'.

Trim or compress the long product enumeration slightly (e.g. group related names) — the synonym coverage can be preserved without listing every variant in the description, since the body repeats the list.

DimensionReasoningScore

Specificity

The domain is named with exceptional concreteness ('Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, RAPIDS/cuDF...'), but the only action framing is the generic 'Use for NVIDIA-related requests where an NVIDIA skill might help' — no concrete capability verbs like finds, recommends, or installs. This sits between anchor 2 (actions minimal or generic) and anchor 3 (1-2 concrete actions): the routing action is present but vague, while scope naming exceeds the anchor examples.

3 / 5

Completeness

The 'when' is exceptionally explicit ('Trigger on NVIDIA products...' plus the negative 'Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks'), and a 'what' is present but weak ('where an NVIDIA skill might help' implies skill routing without stating the discovery/recommendation capability). Both are present with one improvable, matching anchor 4 rather than 5, where the what would be explicitly stated.

4 / 5

Trigger Term Quality

Comprehensive coverage of natural terms with synonym clusters users actually say: 'Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup', 'Omniverse/OpenUSD/SimReady', 'RAPIDS/cuDF', 'cuPyNumeric', 'TensorRT, DeepStream, VSS, TAO, NGC/NVCF'. This matches the anchor-5 pattern of full synonym coverage; no common NVIDIA phrasings are materially missing, so it does not fall to 4.

5 / 5

Distinctiveness Conflict Risk

Clear niche (NVIDIA skill catalog routing) with distinct product-name triggers and explicit negative triggers that suppress activation on generic 'route, optimize, deploy, AI, video, data, or infrastructure' wording. Minimal conflict risk with other skills, matching anchor 5.

5 / 5

Total

17

/

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

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

openai/plugins

Path

plugins/nvidia/skills/nvidia-skill-finder/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.