openai-whisper-api

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%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 content is an exemplar of a lean, executable single-purpose skill: tight Quick start, concrete flag examples, and a real backing script. No padding, no over-explanation, no missing validation for a non-destructive task.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient, with no over-explanation of what Whisper is or how the API works; every line is actionable.	5 / 5
Actionability	Copy-paste-ready commands with concrete flags (model, out, language, prompt, json) and a real referenced script cover the common transcription cases.	5 / 5
Workflow Clarity	This is a simple single-action skill where the action is unambiguous; the simple-skill exception applies and no destructive/batch validation cap is triggered.	5 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (Quick start, flags, API key) and a real scripts/transcribe.sh bundle, fitting the simple-skill progressive disclosure guidance.	5 / 5
	Total	20 / 20 Passed

Description

62%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 and distinct but lacks a "Use when..." trigger clause and broader natural keywords like "speech-to-text". It clearly communicates what the skill does but not when Claude should reach for it.

Suggestions

Add a "Use when..." clause naming trigger contexts, e.g. "Use when transcribing audio files or converting speech to text."

Broaden trigger terms to include natural synonyms like "speech-to-text", "transcription", and common audio extensions (.mp3, .m4a, .wav).

Optionally mention supported output formats (text, JSON) to round out the capability description.

Dimension	Reasoning	Score
Specificity	"Transcribe audio via OpenAI Audio Transcriptions API (Whisper)" names a concrete action and the specific API/endpoint, with only minor coverage gaps rather than a single generic verb.	4 / 5
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant keywords like "Transcribe audio", "Whisper", and "OpenAI" but misses common natural variations such as "speech-to-text", "transcription", or audio file extensions (.mp3, .m4a).	3 / 5
Distinctiveness Conflict Risk	The OpenAI Whisper transcription niche is clearly defined with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/openai-whisper-api/SKILL.md
Commit: f8d9f0b

Reviewed: ~9 hours ago

Table of Contents

Discovery Implementation Validation

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.