openai-whisper-api

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Quality

78%

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 ./skills/openai-whisper-api/SKILL.md

Quality

Content

100%

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

The body is an exemplary lean, single-purpose skill: executable commands, clear defaults and flags, well-organized sections, and a real one-level-deep script reference with no unnecessary content. It earns top marks across all dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — a one-line endpoint description, defaults, flag examples, and API-key setup with no padding or explanation of concepts Claude already knows, matching the level-3 anchor.	3 / 3
Actionability	It provides concrete, copy-paste-ready commands via {baseDir}/scripts/transcribe.sh with specific flag variations (--model, --language, --prompt, --json) and a concrete API-key config block, matching the level-3 anchor.	3 / 3
Workflow Clarity	This is a simple single-task skill whose single action (run transcribe.sh) is unambiguous; transcription is not a destructive/batch operation, so the validation cap does not apply and the simple-skills note allows a 3.	3 / 3
Progressive Disclosure	The skill is under 50 lines with well-organized sections (Quick start, Useful flags, API key) and a single one-level-deep reference to a real bundle file (scripts/transcribe.sh), matching the level-3 simple-skill anchor.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 names a clear, specific niche, but it states only one action and lacks any explicit 'when to use' trigger guidance plus common natural keywords like 'speech-to-text'. It is solid but not comprehensive.

Suggestions

Add a 'Use when...' clause (e.g., 'Use when the user wants to transcribe audio, convert speech to text, or mentions Whisper') to explicitly answer when Claude should invoke the skill and lift completeness.

Include natural user variations such as 'speech-to-text', 'transcription', and 'speech to text' alongside 'transcribe audio' and 'Whisper' to improve trigger-term coverage.

Mention additional concrete capabilities (e.g., supported audio formats, language detection, timestamped/JSON output) to broaden specificity beyond the single 'Transcribe audio' action.

Dimension	Reasoning	Score
Specificity	Names the domain ('audio') and one concrete action ('Transcribe audio'), but lists only a single action rather than multiple specific capabilities, so it stops short of the level-3 anchor.	2 / 3
Completeness	It clearly answers 'what' (transcribe audio via OpenAI's API) but provides no 'Use when...' or equivalent explicit trigger guidance for 'when', which the guideline caps at 2.	2 / 3
Trigger Term Quality	'Transcribe audio' and 'Whisper' are natural user terms, but common variations a user would actually say such as 'speech-to-text' or 'transcription' are missing, matching the level-2 anchor.	2 / 3
Distinctiveness Conflict Risk	The named 'OpenAI Audio Transcriptions API (Whisper)' is a clear, specific niche unlikely to trigger for unrelated skills, matching the level-3 distinct-niche anchor.	3 / 3
	Total	9 / 12 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: e73c717

Reviewed: about 16 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.