CtrlK
BlogDocsLog inGet started
Tessl Logo

transcribe

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

93

4.42x
Quality

92%

Does it follow best practices?

Impact

93%

4.42x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An actionable, well-structured skill body with executable commands, a validated workflow, and clean one-level references. Its main weakness is minor redundancy in the API-key guidance across sections.

Suggestions

Consolidate the OPENAI_API_KEY guidance into one place (e.g., the Environment section) and reference it from the Workflow step rather than restating it.

Trim the overlapping CLI quick-start examples — the single-file and explicit plain-text examples cover the same --response-format text path.

DimensionReasoningScore

Conciseness

Mostly lean and free of concept explanations Claude already knows, but OPENAI_API_KEY handling is repeated across the Workflow and Environment sections and the CLI quick-start examples overlap somewhat, so it could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands — install via uv/pip, env-var exports, and concrete CLI invocations with real flags like --model gpt-4o-transcribe-diarize --known-speaker "Alice=refs/alice.wav".

3 / 3

Workflow Clarity

A clear 5-step sequence includes an explicit validation step ("Validate the output: transcription quality, speaker labels, and segment boundaries") with a feedback loop ("iterate with a single targeted change if needed").

3 / 3

Progressive Disclosure

Well-organized sections plus a clearly signaled, one-level-deep Reference map pointing to a real references/api.md; API detail is appropriately split out rather than inlined.

3 / 3

Total

11

/

12

Passed

Description

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.

A concise, third-person description that clearly states capabilities and provides explicit, natural-language trigger guidance. It is specific, complete, and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Names multiple specific concrete actions — "Transcribe audio files to text", "optional diarization", and "known-speaker hints" — rather than vague language.

3 / 3

Completeness

Explicitly states what it does (transcribe with diarization/speaker hints) and when to use it via a clear "Use when a user asks to..." clause.

3 / 3

Trigger Term Quality

The trigger clause uses natural user phrasing — "transcribe speech from audio/video", "extract text from recordings", "label speakers in interviews or meetings" — with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Audio transcription is a clear niche with distinct triggers unlikely to collide with other skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/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.