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.

80

3.86x
Quality

75%

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/skills/azure-ai-transcription-py/SKILL.md

The canonical home for this skill is azure-ai-transcription-py in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

The body is efficiently organized with executable examples for both transcription modes, but it lacks result-extraction examples for its headline features and any validation/error-handling guidance for batch jobs. Adding a status-check/feedback loop and a snippet accessing timestamps and diarization would raise the weakest dimensions.

Suggestions

Add a short snippet showing how to read timestamps and diarization from a batch result, since the description promises these but no code demonstrates them.

Include a validation/feedback loop for batch jobs (e.g., check result.status, handle Failed, retry) to lift workflow_clarity above the batch-operation cap of 3.

Replace the generic 'When to Use' boilerplate with concrete trigger conditions (e.g., 'Use when the user needs to transcribe audio on Azure with speaker separation or subtitle timestamps').

DimensionReasoningScore

Conciseness

The body is lean with executable snippets and no padding of concepts Claude already knows, but the generic 'When to Use' boilerplate ('applicable to execute the workflow or actions described in the overview') and the slightly redundant intro could be trimmed.

4 / 5

Actionability

Concrete, copy-paste-ready code covers both batch and real-time modes, but no example shows how to extract the promised timestamps and diarization from results — a notable gap for the stated capabilities.

4 / 5

Workflow Clarity

Batch and real-time sequences are present, but neither shows validation or error-handling feedback loops; per the rubric, batch operations without validation checkpoints cap this dimension at 3.

3 / 5

Progressive Disclosure

Under 50 lines with no need for external references and well-organized into clearly headed sections (Installation, Authentication, Batch, Real-time, Best Practices), satisfying the simple-skill exception.

5 / 5

Total

16

/

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.

The description is specific, well-scoped, and includes an explicit use clause, scoring solidly across all dimensions. The main weakness is the 'when' guidance restating capabilities instead of giving concrete user-side trigger phrases.

DimensionReasoningScore

Specificity

Names the domain plus several concrete capabilities — 'real-time and batch speech-to-text transcription with timestamps and diarization' — but omits adjacent actions like language identification or custom-model adaptation, leaving minor coverage gaps.

4 / 5

Completeness

Explicit 'what' (Azure AI Transcription SDK) and a 'Use for...' trigger clause are both present, but the 'when' restates the capabilities rather than naming concrete trigger phrases ('when the user mentions audio files, transcripts').

4 / 5

Trigger Term Quality

Includes natural user terms ('speech-to-text', 'transcription', 'real-time', 'batch', 'diarization') but misses common synonyms such as 'speech recognition', 'STT', or 'audio to text'.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Azure AI Transcription SDK for Python) with distinct triggers and minimal overlap risk against generic or other-provider transcription 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.

Validation15 / 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.