CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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-engineered skill body: lean procedural directives with explicit validation and error-recovery loops, and clean progressive disclosure to real, condition-signaled bundle files. The single minor gap is the absence of any inline code snippet, with executable detail delegated to the template asset and references.

DimensionReasoningScore

Conciseness

The body is entirely lean, imperative directives with zero concept explanations or padding — no 'what is the Translator API' prose, just what to do, check, and stop on. Every line adds non-obvious, project-specific guidance, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Guidance is highly concrete — exact method names ('Translator.availability()', 'create()', 'translateStreaming()', 'measureInputUsage()'), options ('monitor', 'signal'), 'AbortController' usage, named DOMException types, and an executable command ('node scripts/find-translator-targets.mjs .'). It falls short of 5 only because the body contains no inline code snippet; execution details are delegated to assets/translator-session.template.ts and the reference files, which is acceptable for an instruction-oriented skill but leaves minor gaps.

4 / 5

Workflow Clarity

Five clearly sequenced steps with a dedicated validation phase (Step 5) that includes explicit checkpoints — re-run the inventory script, test create()+translate() flows, test streaming abort, verify measureInputUsage, run build/typecheck/tests — plus a per-error recovery section ('If create() throws NotAllowedError, check permissions-policy constraints...'). This matches the anchor with feedback loops and error-recovery guidance.

5 / 5

Progressive Disclosure

The body is a concise overview and each bundle file is signaled with an explicit condition for when to read it ('Read references/examples.md when the feature needs a session wrapper...'; 'Read references/troubleshooting.md when support checks... fail'). All referenced paths exist on disk and references are one level deep, matching the well-signaled one-level-deep anchor.

5 / 5

Total

19

/

20

Passed

Description

92%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.

An excellent description: specific, third-person, with an explicit 'Use when' trigger clause and a negative boundary that cleanly separates it from server-side translation tooling. The only minor gap is a few missing natural synonyms a user might say (e.g., 'local translation').

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Translator support checks', 'language-pair availability flows', 'model download UX', 'session creation', 'translate() or translateStreaming() calls', 'input-usage measurement', 'permissions-policy handling' — giving comprehensive coverage in third-person voice. It is not level 4 because no meaningful capability of the skill's scope is left uncovered.

5 / 5

Completeness

It explicitly answers both 'what' ('Implements and debugs browser Translator API integrations in JavaScript or TypeScript web apps') and 'when' ('Use when adding...') with concrete trigger phrases, and adds a 'Don't use for...' exclusion. This matches the level-5 anchor exactly.

5 / 5

Trigger Term Quality

Good natural-term coverage ('on-device translation', 'model download', 'streaming', 'session') but a few common user phrasings are missing. It is not 5 because synonyms like 'local translation' or 'browser built-in translation' are absent; not 3 because most terms a user would naturally say when requesting this work are present.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct (browser on-device Translator API) and the explicit negative boundary ('Don't use for server-side translation SDKs, cloud translation services, or generic multilingual content pipelines') minimizes overlap with cloud/translation-pipeline skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
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.