azure-ai-translation-ts
Text and document translation with REST-style clients.
43
43%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/azure-ai-translation-ts/SKILL.mdQuality
Discovery
22%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too terse and vague to effectively guide skill selection. It lacks concrete actions, explicit trigger conditions, and natural user-facing keywords. The mention of 'REST-style clients' adds some distinctiveness but is insufficient without a clear 'Use when...' clause and specific capability listing.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user asks to translate text or documents between languages, or needs to call a translation API.'
List specific concrete actions such as 'Translates text between languages, translates document files, detects source language, supports batch translation via REST API calls.'
Include natural trigger terms users would say, such as 'translate', 'language', 'localization', 'i18n', 'multilingual', and specific API names if applicable.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'translation' and 'REST-style clients' but does not list any concrete actions (e.g., translate documents, detect language, batch translate). It remains vague about what specific operations are performed. | 1 / 3 |
Completeness | The 'what' is only weakly stated (translation with REST clients) and there is no 'when' clause or explicit trigger guidance at all. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'translation', 'text', 'document', and 'REST' that users might mention, but misses common variations like 'translate', 'language', 'localization', 'i18n', or specific API names. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'translation' and 'REST-style clients' provides some specificity, but 'text and document' is broad enough to overlap with general document processing or generic REST API skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid API reference skill with excellent actionability — all code examples are concrete, executable, and cover the major use cases. However, it reads more like comprehensive documentation than a lean skill file; the batch translation workflow lacks explicit sequencing and validation steps, and the entire content could benefit from splitting detailed examples into referenced files while keeping the main skill as a concise overview.
Suggestions
Add an explicit numbered workflow for batch document translation with validation checkpoints (e.g., verify SAS URL validity, poll with backoff, handle partial failures).
Split detailed code examples into a separate REFERENCE.md or EXAMPLES.md file and keep SKILL.md as a concise overview with quick-start examples and links to details.
Remove the boilerplate 'When to Use' and 'Limitations' sections which add no skill-specific value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but includes some unnecessary sections like 'When to Use' and 'Limitations' that are boilerplate filler. The 'Best Practices' section contains some tips Claude would already know (e.g., 'handle errors'). The overall length (~200 lines) is substantial for what is essentially an API reference. | 2 / 3 |
Actionability | All code examples are concrete, executable TypeScript with proper imports, error handling patterns, and realistic usage. The examples cover authentication, text translation, document translation, batch operations, and status checking — all copy-paste ready with real API paths and parameter structures. | 3 / 3 |
Workflow Clarity | The batch document translation involves a multi-step process (generate SAS URLs → start batch → poll status → check documents) but these steps are spread across separate code blocks without an explicit sequenced workflow or validation checkpoints. There's no feedback loop for retrying failed translations or handling partial batch failures. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical grouping (Text vs Document translation), but it's a monolithic file with no references to external files. The extensive API reference content (key types, all endpoints) could be split into separate reference files, keeping the SKILL.md as a concise overview. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
9e5d4dd
- 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.