whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Quality

82%

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

65%

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

The content is highly actionable with abundant executable examples, but it is padded with redundant sections and fails to leverage its existing reference file, instead duplicating language material inline. Batch processing also lacks verification checkpoints.

Suggestions

Replace the inline "Language support" section and embedded language-code lists with a clear pointer to references/languages.md (e.g., "Full language list: see references/languages.md") to honor progressive disclosure and cut duplication.

Trim the "Best practices", "Performance", and "Resources" sections to remove guidance already covered inline, improving token efficiency.

Add a verification step to the batch-processing workflow (e.g., confirm each output file exists/is non-empty before proceeding) to satisfy the validation requirement for batch operations.

Dimension	Reasoning	Score
Conciseness	Mostly executable code with lean commentary, but the body is long with redundancy: the "Best practices" list restates inline guidance, and "Performance"/"Language support"/"Resources" sections duplicate earlier tables and the references file.	2 / 3
Actionability	Provides extensive copy-paste-ready Python and bash examples with specific options (language, task, word_timestamps, temperature fallback), fully executable throughout.	3 / 3
Workflow Clarity	The skill is mostly independent recipes rather than a fragile pipeline, but the batch-processing section performs batch operations with no validation/verification checkpoint, which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	A real references/languages.md bundle exists one level deep, but the body never signals or links it and instead duplicates language content inline, so structure that should be split out is kept in SKILL.md.	2 / 3
	Total	9 / 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.

The description is concise yet complete: it states concrete capabilities, gives natural trigger terms, includes an explicit Use-when clause, and occupies a distinct niche. No fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("transcription, translation to English, and language identification") plus concrete model sizing ("Six model sizes from tiny (39M params) to large (1550M params)"), matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers what the skill does and provides an explicit when-clause ("Use for speech-to-text, podcast transcription, or multilingual audio processing"), satisfying both halves.	3 / 3
Trigger Term Quality	Natural user-facing terms like "speech-to-text", "podcast transcription", and "multilingual audio processing" give good coverage of phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	"OpenAI's general-purpose speech recognition model" plus ASR-specific triggers carve a clear niche unlikely to collide with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 18-multimodal/whisper/SKILL.md
Commit: 773a529

Reviewed: about 12 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.