azure-ai-transcription-py
Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.
59
68%
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-transcription-py/SKILL.mdQuality
Discovery
100%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 is a strong, concise description that clearly identifies the technology stack (Azure AI, Python SDK), the core capability (speech-to-text transcription), and specific features (real-time, batch, timestamps, diarization). The 'Use for...' clause provides explicit trigger guidance. The description is well-targeted and distinctive, making it easy for Claude to select appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'real-time and batch speech-to-text transcription with timestamps and diarization.' These are concrete, well-defined capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both what ('Azure AI Transcription SDK for Python' with 'speech-to-text transcription with timestamps and diarization') and when ('Use for real-time and batch speech-to-text transcription'). The 'Use for...' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Azure', 'transcription', 'speech-to-text', 'timestamps', 'diarization', 'real-time', 'batch', 'Python', 'SDK'. These cover the main terms a user working with Azure speech services would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Azure-specific, Python SDK, speech-to-text transcription. The combination of platform (Azure), language (Python), and domain (speech transcription with diarization) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable starting point with concrete authentication and basic transcription code examples, but falls short on workflow clarity — batch transcription is inherently multi-step (submit, poll, retrieve, validate) yet is presented as a simple two-line snippet. The best practices are vague platitudes without executable guidance, and the boilerplate 'When to Use' and 'Limitations' sections waste tokens without adding value.
Suggestions
Add a complete batch transcription workflow with explicit steps: submit job → poll status → retrieve results → validate output, including error handling for common failures (invalid audio format, expired URLs, quota limits).
Replace vague best practices with executable code examples — e.g., show how to access diarization speaker labels and timestamps from the result object, and demonstrate handling streaming backpressure.
Remove the boilerplate 'When to Use' and 'Limitations' sections which add no skill-specific information and waste tokens.
Add error handling patterns for authentication failures and common API errors (e.g., invalid locale, unsupported audio format) to make the skill more robust in practice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with good code examples, but the 'Best Practices' section contains some generic advice Claude would already know (e.g., 'specify language to improve accuracy'), and the 'When to Use' and 'Limitations' sections are boilerplate filler that add no actionable information. | 2 / 3 |
Actionability | Provides concrete code examples for authentication, batch, and real-time transcription, but they are incomplete — no error handling, no example of accessing timestamps or diarization results from the response object, and best practices are vague directives rather than executable guidance (e.g., 'handle streaming backpressure' with no code showing how). | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow connecting the pieces (e.g., authenticate → submit job → poll/wait → process results → handle errors). Batch transcription is an async operation but there's no guidance on polling, error recovery, or validation of results. The code snippets are isolated fragments without sequencing or checkpoints. | 1 / 3 |
Progressive Disclosure | Content is reasonably organized into sections with clear headers, but there are no references to external files for advanced topics (diarization details, error handling, timestamp extraction). The skill is short enough that no bundle is strictly needed, but the inline best practices section could be replaced with more actionable content or a reference. | 2 / 3 |
Total | 7 / 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
76aea27
- 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.