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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/llm-tools/whisper/SKILL.md

Quality

Content

65%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.

Highly actionable reference with strong executable examples, but it carries marketing padding and misses validation in batch operations plus an orphaned bundle reference that is never navigated to.

Suggestions

Remove the 'Metrics' (GitHub stars) and 'Use alternatives instead' sections and the redundant opening line; keep the body focused on usage Claude cannot infer.

Add a validation/verification step to the batch-processing loop (e.g., check that the output file was written and is non-empty before proceeding).

Replace the inline 'Language support' list with a pointer to references/languages.md (e.g., 'Full list: see references/languages.md') so the bundle file is actually used.

Dimension	Reasoning	Score
Conciseness	Core content is lean code, but it includes unnecessary padding such as GitHub star counts, a 'Use alternatives instead' section, and a redundant restatement of the model description.	3 / 5
Actionability	Fully executable, copy-paste-ready Python and CLI examples cover the common cases (transcription, translation, timestamps, batch, GPU, output formats).	5 / 5
Workflow Clarity	The batch-processing example overwrites output files with no validation or verification step, capping workflow clarity at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	Sections are well-headered, but references/languages.md is never linked from the body and the inline 'Language support' section duplicates content that belongs in that file.	3 / 5
	Total	14 / 20 Passed

Description

87%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.

A strong description that concretely names capabilities, includes natural trigger terms, and explicitly answers both what and when. Minor room to add file extensions and tighten 'Best for robust, multilingual ASR'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('transcription, translation to English, and language identification') plus model sizes, but stops short of fully comprehensive coverage of capabilities.	4 / 5
Completeness	Clearly states what the model does ('Supports 99 languages, transcription, translation to English, and language identification') and gives an explicit 'Use for...' trigger clause with concrete use cases.	5 / 5
Trigger Term Quality	Good natural keyword coverage with synonyms ('speech recognition', 'speech-to-text', 'ASR', 'podcast transcription'), but omits common audio file extensions like .mp3 or .wav.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (OpenAI speech recognition / ASR) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/whisper/SKILL.md
Commit: fcd2e11

Reviewed: 2 days 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.