CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-transcription-py

Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.

79

3.86x
Quality

73%

Does it follow best practices?

Impact

85%

3.86x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-transcription-py/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 tidy, actionable SDK reference with executable auth, batch, and real-time examples and sensible best practices. Its weak spot is workflow clarity: the batch transcription flow lacks validation/checkpoint steps the rubric requires for batch operations, and the closing 'When to Use' line is filler.

Suggestions

Add an explicit validation/verification step to the batch flow — e.g. check job status and handle failure before calling result() — so the batch operation includes a checkpoint and can clear the workflow_clarity cap of 3.

Replace the filler 'When to Use' sentence with concrete, situation-based trigger guidance (e.g. 'Use when converting recorded meetings or blob-stored audio to searchable text, or when live captioning a stream').

Round out actionability with a short error-handling snippet (e.g. catching transcription job failures or stream interruption) so the common cases are fully complete.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows, with clean code blocks and one useful constraint ('DefaultAzureCredential is not supported'); the only inefficiency is the vague filler line 'This skill is applicable to execute the workflow or actions described in the overview.'

4 / 5

Actionability

It provides copy-paste-ready code for authentication, batch, and real-time transcription along with install and env-var setup, covering the common cases; minor placeholders (e.g. 'https://<storage>/audio.wav', 'audio.wav') and absent error-handling details keep it just below fully complete.

4 / 5

Workflow Clarity

The batch and real-time flows show a basic sequence (create job -> poll result -> print status; open stream -> send -> iterate), but neither includes explicit validation or verification checkpoints, which caps this batch operation at 3 per the rubric's destructive/batch guideline.

3 / 5

Progressive Disclosure

The body is organized into clear, well-labeled sections (Installation, Authentication, Batch, Real-time, Best Practices) with no nested or buried references, and no bundle files exist to structure; it sits just over 50 lines, so it narrowly misses the simple-skill exception for a 5.

4 / 5

Total

15

/

20

Passed

Description

78%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.

A concise, specific description with third-person voice and concrete capabilities plus a trigger clause. Its main weakness is that the 'Use for...' trigger restates the 'what' rather than describing user situations, and it omits common synonyms like 'STT' or 'audio-to-text'.

DimensionReasoningScore

Specificity

The description names the domain and several concrete actions — 'real-time and batch speech-to-text transcription with timestamps and diarization' — which is several specific capabilities rather than generic language, though coverage of the SDK's full surface is not exhaustive.

4 / 5

Completeness

Both a 'what' (the SDK and its capabilities) and a 'when' trigger ('Use for real-time and batch speech-to-text transcription...') are present, but the 'when' clause restates the capabilities rather than naming concrete user situations, so it could be more explicit.

4 / 5

Trigger Term Quality

It includes natural terms a user would say ('speech-to-text', 'transcription', 'real-time', 'batch', 'diarization'), but misses common synonyms such as 'STT', 'audio-to-text', or audio file extensions, so it is not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

'Azure AI Transcription SDK for Python' with speech-to-text/diarization triggers carves a clear niche with distinct trigger terms and minimal overlap risk against other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.