What does this skill do, and when should you use it?
This skill provides implementation patterns for Azure Translation’s TypeScript REST-style clients. It covers text translation, transliteration, language detection, supported-language lookup, and both single and batch document translation. The examples show API-key, regional, and Azure identity authentication. It fits TypeScript teams using Azure Translator who want coding agents to generate code aligned with the documented SDK patterns.
Installs and configures Azure Translation TypeScript packages, reads Translator endpoint, subscription key, and region environment variables, creates text or document translation clients, calls the /translate, /languages, /transliterate, /detect, /document:translate, /document/batches, status, and formats endpoints, checks responses with isUnexpected, and produces translated text, language confidence scores, batch status, document status, or supported-format output. Batch document examples also use Azure Blob Storage container SAS URLs and extract an operation ID from the response headers.
- A TypeScript developer needs to translate English text into Spanish, French, or other target languages.
- An application must detect the source language when users do not provide one.
- A service needs transliteration between scripts, such as converting Simplified Chinese into Latin characters.
- A backend team needs document translation using Azure identity credentials or an API key.
- A workflow must start and monitor batch document translation using Blob Storage SAS URLs.
How do you install this skill?
- Do not log subscription keys or translation content; use secret management and confirm data-residency, compliance, and third-party processing requirements.
- The batch example grants source-container read and target-container read/write access through SAS URLs; constrain permissions, lifetime, and network scope, and confirm upload/write effects before proceeding.
- The material does not document Azure endpoint reachability in mainland China, regional service differences, quotas, costs, or API-version compatibility.
- Add guidance for retries, timeouts, cancellation, missing operation-location headers, partial success, and rollback of output files.
- Shell / CLI
- Network access
- Local filesystem
Node.js@azure-rest/ai-translation-text@azure-rest/ai-translation-document@azure/identity@azure/storage-blob
Run npx skills add microsoft/skills in the project and select azure-ai-translation-ts in the installation wizard. The documented SDK dependencies are @azure-rest/ai-translation-text, @azure-rest/ai-translation-document, @azure/identity, and @azure/storage-blob for the batch-document example. Install by feature: npm install @azure-rest/ai-translation-text @azure/identity for text translation, or npm install @azure-rest/ai-translation-document @azure/identity for document translation.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/.github/plugins/azure-sdk-typescript/skills/azure-ai-translation-ts" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Use the Azure Translation TypeScript SDK to implement text translation, language detection, and batch document translation with isUnexpected error handling.
After installing the skill in the selected coding agent’s skills directory, trigger it for a TypeScript translation task such as: "Use the Azure Translation TypeScript SDK to implement text translation, language detection, and batch document translation with isUnexpected error handling." Set TRANSLATOR_ENDPOINT, TRANSLATOR_SUBSCRIPTION_KEY, and TRANSLATOR_REGION; when using DefaultAzureCredential, also set AZURE_TOKEN_CREDENTIALS. Then create the appropriate client, call the required endpoint, and validate the response.
What are this skill's strengths and limitations?
- Covers clearly defined text, transliteration, language-detection, and document-translation workflows.
- Includes API-key, regional-credential, DefaultAzureCredential, and managed-identity patterns.
- Shows error checking, pagination, SAS URLs, and batch-operation monitoring.
- Examples map directly to Azure REST client packages and are useful for generating TypeScript code.
- Requires an Azure Translator endpoint and credentials; batch document translation also requires Blob Storage SAS URLs.
- The source provides SDK usage patterns but no pricing, quota, or deployment guidance.
- No standalone test results or complete project template are provided for this individual skill.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Azure Translation for TypeScript this page ✓ Microsoft · Official | 50 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure Text Translation for Python ✓ Microsoft · Official | 50 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure Document Translation for Python ✓ Microsoft · Official | 52 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure AI Content Safety for TypeScript ✓ Microsoft · Official | 50 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure Document Intelligence for TypeScript ✓ Microsoft · Official | 50 · Use with care | ★ 2.7k | 3mo ago | MIT |
How did FollowSkills review this skill?
The document exposes API-key, regional, managed-identity, and time-limited SAS patterns, and recommends bounded SAS permissions, so the main authentication and data-flow choices are visible. Points are deducted because it does not require confirmation for external translation, cloud upload, or target-container writes, and it omits sensitive-text handling, secret logging, SAS leakage, revocation, and rollback guidance.
It provides examples for translation, language detection, transliteration, document submission, polling, pagination, and isUnexpected checks. Points are deducted because the skill itself contains no executable tests, pinned compatibility versions, input boundaries, retry/timeout guidance, or diagnostics for missing headers, malformed responses, and other abnormal cases; static calibration also limits the score.
The name and description clearly target TypeScript/JavaScript Azure Translation applications and cover text, transliteration, detection, and single/batch document translation. Points are deducted because non-fit cases, input/output contracts, regional reachability, cost constraints, and mainland-China network or endpoint availability are not stated.
It has installation notes, environment variables, authentication alternatives, progressive topical examples, key types, and best practices; MIT licensing, author, and version metadata are present. Points are deducted for missing changelog, maintenance/update path, compatible SDK versions, FAQ, troubleshooting, and known limitations; installation notes also omit the storage dependency needed for the batch example.
The examples address the main translation workflows and include reusable client calls, error checks, pagination, and SAS permission setup, so they can support the core development task. Points are deducted because there is no complete runnable project, full configuration context, verified output, or comparison with alternatives, and some snippets rely on client state established elsewhere; static calibration caps this at 7.
The skill gives concrete package names, environment variables, API paths, code patterns, and error checks, while the repository materials show general evaluation workflows and harness tests. Points are deducted because the supplied material does not show skill-specific committed tests, real execution results, independent corroboration, or revision-pinned API verification, so only limited static auditability is supported.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →