webnn

Implements and debugs browser Web Neural Network API integrations in JavaScript or TypeScript web apps. Use when adding navigator.ml checks, MLContext creation, MLGraphBuilder flows, device selection, tensor dispatch and readback, or explicit fallback paths to ONNX Runtime Web or other local runtimes. Don't use for model training, server-side ML inference, or cloud AI APIs.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%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 content is a well-structured, lean procedural skill that defers detail to one-level-deep bundle files, gives concrete executable guidance, and embeds validation checkpoints and explicit stop conditions throughout. It is an exemplar of high-quality skill content.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no padding or explanations of concepts Claude already knows; every step earns its place by prescribing a specific action or decision.	5 / 5
Actionability	Provides concrete executable commands ('node scripts/find-webnn-targets.mjs .'), specific API call sequences ('context.writeTensor()', 'context.dispatch()', 'await context.readTensor()'), explicit device-intent values, and a template file to adapt.	5 / 5
Workflow Clarity	A clear five-step sequence with explicit validation in Step 5 (smoke test, device-setting tests, build/typecheck), explicit stop conditions, and an Error Handling section providing feedback loops for recovery.	5 / 5
Progressive Disclosure	The body is an overview with well-signaled, one-level-deep references ('Read references/webnn-reference.md before writing code', 'Read references/examples.md when...'), and all referenced files (references/, scripts/, assets/*) exist and are organized by purpose.	5 / 5
	Total	20 / 20 Passed

Description

100%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.

The description is precise, comprehensive, and well-bounded: it names concrete WebNN actions, provides natural trigger terms, answers both what and when explicitly, and scopes out adjacent domains. It is an exemplar of a high-quality skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('navigator.ml checks, MLContext creation, MLGraphBuilder flows, device selection, tensor dispatch and readback, explicit fallback paths to ONNX Runtime Web') with comprehensive coverage of the WebNN integration domain.	5 / 5
Completeness	Explicitly answers both 'what' ('Implements and debugs browser Web Neural Network API integrations') and 'when' ('Use when adding...') with concrete trigger phrases and explicit exclusion boundaries.	5 / 5
Trigger Term Quality	Covers natural user-facing terms including 'Web Neural Network API', 'navigator.ml', 'MLContext', 'MLGraphBuilder', 'ONNX Runtime Web', plus negative triggers ('model training', 'server-side ML inference', 'cloud AI APIs').	5 / 5
Distinctiveness Conflict Risk	A clear niche (browser WebNN API in JS/TS web apps) with explicit negative scope ('Don't use for model training, server-side ML inference, or cloud AI APIs') minimizes overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webmaxru/web-ai-agent-skills
Path: skills/webnn/SKILL.md
Commit: 89fee4a

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.