What does this skill do, and when should you use it?
This skill guides developers using the Azure AI Text Translation SDK for Python. It covers text translation, transliteration, language detection, dictionary lookup, sentence-boundary detection, and supported-language discovery. The examples include synchronous and asynchronous clients, with DefaultAzureCredential and deterministic resource cleanup recommended. It fits Python developers building applications that already use Azure Translator or need multilingual text operations.
Installs and uses the azure-ai-translation-text package, creates a TextTranslationClient, and calls translate, transliterate, lookup_dictionary_entries, lookup_dictionary_examples, get_supported_languages, and find_sentence_boundaries. It translates text into one or more target languages, reports detected languages, converts between scripts, returns dictionary definitions and examples, and supports HTML input, profanity handling, word alignment, and sentence-length information.
- A Python developer needs to translate application or user-interface text into one or more languages in real time.
- A multilingual application needs to identify the input language and inspect its confidence score.
- A text-processing application needs to convert content from one writing script to another.
- A learning, search, or content tool needs alternate translations, parts of speech, or dictionary usage examples.
- A high-throughput service needs to process batched text with the asynchronous client.
How do you install this skill?
- The main document and references use inconsistent SDK signatures and input models; verify them against the official API for this revision and the installed package version before adoption.
- Examples do not cover exceptions, throttling, timeouts, retries, sensitive-text handling, log redaction, or cost controls.
- Translation content is sent to a remote Azure service; the supplied material does not establish retention, regional compliance, or mainland-China network reachability.
- The method table lists detect without an implementation example, while several operations are documented only in references.
- Shell / CLI
- Network access
Pythonazure-ai-translation-textazure-identityazure-core
In an Agent Skills-compatible client, run npx skills add microsoft/skills and select azure-ai-translation-text-py in the installation wizard. The README does not document a standalone installation command for this individual skill. Install the SDK with pip install azure-ai-translation-text.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/.github/plugins/azure-sdk-python/skills/azure-ai-translation-text-py" ~/.claude/skills/
rm -rf "$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 TextTranslationClient to translate text into Spanish
- Use Azure Translator to transliterate Latin text into Japanese script.
Give the coding agent a request containing a documented trigger, such as “Use TextTranslationClient to translate text into Spanish” or “Use Azure Translator to transliterate Latin text into Japanese script.” Configure AZURE_TRANSLATOR_ENDPOINT and prefer DefaultAzureCredential; for production, AZURE_TOKEN_CREDENTIALS=prod may be set. For API-key authentication, configure AZURE_TRANSLATOR_KEY and, when using the global endpoint, AZURE_TRANSLATOR_REGION.
What are this skill's strengths and limitations?
- Covers translation, transliteration, language detection, and dictionary operations.
- Includes both synchronous and asynchronous client examples.
- Clearly recommends Entra ID credentials and context managers.
- Documents batching, HTML input, profanity handling, alignment, and sentence boundaries.
- Token-credential authentication requires a custom-subdomain endpoint; the global endpoint commonly requires an API key and region.
- The source does not specify a Python version, service pricing, or quotas.
- The skill is an instruction document, not a complete runnable project or standalone test suite.
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 Text Translation for Python this page ✓ Microsoft · Official | 50 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure Translation for TypeScript ✓ 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 Vision Image Analysis ✓ Microsoft · Official | 55 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure AI Content Safety for Python ✓ Microsoft · Official | 53 · Use with care | ★ 2.7k | 3mo ago | MIT |
The skill positions DefaultAzureCredential as the preferred approach for new code while retaining API-key authentication for existing deployments. Token credentials use a custom-subdomain endpoint; the common API-key setup for the global endpoint requires a region.
How did FollowSkills review this skill?
The documentation prefers DefaultAzureCredential, explains legacy API-key use, environment variables, and deterministic client cleanup; no malicious behavior or overbroad operation is evident. It does not explain sensitive-text handling, data residency or retention, user confirmation, service-side logging, or rollback, so trust is materially below full marks.
Installation and sync/async lifecycle guidance are reasonably detailed, but the main document and references conflict on request parameters and models: the main examples use string bodies and to, while references use InputTextItem and to_language. The method table lists detect without an example. Static evidence is insufficient, so the score stays below the 10-point static ceiling and is reduced for potentially unrunnable paths.
Triggers, SDK identity, and core translation/transliteration/language-operation scenarios are clear, with both sync and async coverage. However, non-fit boundaries, invalid-input constraints, quota/rate-limit behavior, regional availability, and Chinese-language guidance are missing. The core function depends on Azure's remote service, and mainland-China reachability is not established, so points are deducted.
The skill has a name, description, MIT license, author, version metadata, layered main/reference documentation, and several examples plus a capability index. It lacks a skill-specific changelog, explicit maintenance owner or update path, dependency version constraints, FAQ, and systematic troubleshooting; inconsistencies between the main and reference files also reduce maintainability.
The skill covers common text translation and several advanced operations, and most examples are directly usable as starting points. Conflicting API parameters, input models, and method coverage, plus missing production error handling, retry guidance, privacy handling, and verified outputs, mean substantial manual correction may be required. The score therefore remains below the static 7-point ceiling and is reduced further.
Concrete code, environment variables, a capability index, and repository-level CI/evaluation workflows provide some auditability. The supplied material contains no skill-specific committed tests, execution results, or third-party corroboration, and the CI evidence does not establish coverage of this skill's key paths, so only limited static evidence is credited.
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 →