translator-api

Implements and debugs browser Translator API integrations in JavaScript or TypeScript web apps. Use when adding Translator support checks, language-pair availability flows, model download UX, session creation, translate() or translateStreaming() calls, input-usage measurement, or permissions-policy handling for on-device translation. Don't use for server-side translation SDKs, cloud translation services, or generic multilingual content pipelines.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

62%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 content is well-sequenced with strong validation checkpoints and error-handling feedback loops, but it leans instructive rather than executable and is undermined by progressive-disclosure references to bundle files that are absent from the package.

Suggestions

Ship the referenced bundle (references/translator-reference.md, examples.md, compatibility.md, troubleshooting.md, scripts/find-translator-targets.mjs, assets/translator-session.template.ts) or remove the references — broken paths defeat progressive disclosure.

Inline at least one minimal, executable Translator.create() + translate() code block so the skill is copy-paste ready without the missing template asset.

Trim inferable API caveats (e.g. the availability() capability-vs-guarantee note) to tighten the token budget and respect Claude's existing knowledge.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded — e.g. 'Treat availability() as a capability check, not a guarantee...' explains nuance Claude can infer, and the procedures repeat familiar API caveats rather than trusting Claude's knowledge.	2 / 3
Actionability	Guidance is concrete and directive but largely instructs behavior rather than providing copy-paste code — no executable session-wrapping example is inlined, only an asset template reference that does not exist in the bundle.	2 / 3
Workflow Clarity	A clear 5-step sequence with explicit validation checkpoints (Step 5 'Validate behavior', re-run inventory, secure-context checks, build/typecheck/test) and a dedicated Error Handling section with feedback loops.	3 / 3
Progressive Disclosure	The body references references/.md, scripts/.mjs, and assets/*.ts files, but no references/, scripts/, or assets/ directories exist — the navigation points at missing material, leaving a monolithic SKILL.md with broken one-level-deep references.	1 / 3
	Total	8 / 12 Passed

Description

100%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.

A precise, well-scoped description that covers the API surface comprehensively with natural trigger terms and an explicit negative-scope clause. It cleanly answers both what and when with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'support checks, language-pair availability flows, model download UX, session creation, translate() or translateStreaming() calls, input-usage measurement' — covering the full API surface comprehensively.	3 / 3
Completeness	Explicitly answers both what ('Implements and debugs browser Translator API integrations...') and when ('Use when adding Translator support checks... Don't use for server-side translation SDKs...'), with explicit positive triggers and a negative-scope exclusion clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'Translator API', 'language-pair availability', 'model download', 'translate()', 'translateStreaming()' — with strong coverage of both natural and technical phrasings.	3 / 3
Distinctiveness Conflict Risk	Clear niche — on-device browser Translator API — and the 'Don't use for...' exclusion clause distinguishes it from cloud/server translation skills, making misfires unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	15 / 16 Passed

Repository: webmaxru/web-ai-agent-skills
Path: skills/translator-api/SKILL.md
Commit: f4c5a23

Reviewed: 13 days 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.