openai-whisper-api

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Quality

80%

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 body is a model of token-efficient skill writing: fully executable commands, useful flag examples, and just enough configuration guidance, with zero padding or explanations of things Claude already knows. Structure and workflow are appropriate for a simple single-purpose tool skill.

Dimension	Reasoning	Score
Conciseness	The body is ~40 lean lines: a quick-start command, defaults, four runnable flag examples, and an API-key snippet. It assumes Claude's competence (no explanation of what Whisper or transcription is), so every token earns its place — a clear match for the anchor-5 example.	5 / 5
Actionability	Quick start is a copy-paste-ready command ("{baseDir}/scripts/transcribe.sh /path/to/audio.m4a"), the "Useful flags" section gives fully executable examples covering the common cases (model, output path, language, prompt, JSON), and the API-key section includes a concrete config snippet. This matches the fully-executable anchor with examples covering common cases.	5 / 5
Workflow Clarity	This is a simple single-task skill and the single action is unambiguous: run the script, get a transcript file; the referenced script itself validates the input file and API key before doing work. Per the rubric's simple-skill exception this earns a 5, and no destructive/batch cap applies.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external reference files, and it is organized into clear, well-labeled sections (Quick start, Useful flags, API key). The one referenced path, scripts/transcribe.sh, exists in the bundle, satisfying the short-skill exception for a 5.	5 / 5
	Total	20 / 20 Passed

Description

61%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 concise and specific about what the skill does and which API it targets, with a low risk of triggering for unrelated skills. Its main weakness is the complete absence of any "when to use" trigger guidance, which caps completeness and limits trigger-term coverage.

Suggestions

Append a trigger clause such as "Use when the user wants to transcribe or get text from an audio file (speech-to-text), or mentions Whisper, .mp3/.m4a/.wav files, or audio transcription."

Add common synonyms and file extensions ("speech-to-text", "captions", "subtitles", ".mp3", ".m4a", ".wav") to broaden natural keyword coverage.

Optionally name one or two concrete capabilities beyond plain transcription (e.g., language hinting or a conditioning prompt) to lift specificity.

Dimension	Reasoning	Score
Specificity	"Transcribe audio via OpenAI Audio Transcriptions API (Whisper)" names the domain and exactly one concrete action against a specific API. It matches the anchor for 1-2 concrete actions without comprehensive coverage, and lacks the several specific actions needed for a 4.	3 / 5
Completeness	The "what" is clear (transcribe audio via the OpenAI transcriptions API), but there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the rubric guidelines. It is not a 4 because the "when" is entirely absent rather than merely implicit or imprecise.	3 / 5
Trigger Term Quality	Includes natural terms users would say — "Transcribe audio", "Whisper", "OpenAI" — giving good keyword coverage. A few natural terms are missing (e.g., "speech-to-text", "captions/subtitles", audio file extensions like .mp3), keeping it below the comprehensive synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	Naming a specific vendor endpoint ("OpenAI Audio Transcriptions API (Whisper)") gives it a clear niche with only minor overlap risk against closely related skills (e.g., local Whisper transcription). It falls short of a 5 because the anchor-5 examples pair the niche with explicit distinct trigger phrases, which are absent here.	4 / 5
	Total	14 / 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: 1c7dc1b

Reviewed: 20 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.