openai-whisper-api

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

2.27x

Quality

76%

Does it follow best practices?

Impact

91%

2.27x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/openai-whisper-api/SKILL.md

The canonical home for this skill is openai-whisper-api in Hung-Reo/hungreo-openclaw

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 an exemplary lean, single-purpose skill: copy-paste-ready commands, accurate flag documentation verified against the bundled script, sensible defaults, and clean section organization with zero padding. Nothing needs to be split out into reference files at this size.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: "Transcribe an audio file via OpenAI's /v1/audio/transcriptions endpoint" plus a quick-start command, a short defaults list, four flag examples, and a compact key-config snippet. Every token earns its place with no explanation of concepts Claude already knows. Not a 4 because there are no instances of over-explanation to trim.	5 / 5
Actionability	The quick start is copy-paste ready ("{baseDir}/scripts/transcribe.sh /path/to/audio.m4a") and the "Useful flags" section gives executable commands for the common cases (model, output path, language, prompt, JSON), all of which match the actual script's interface. This is fully executable guidance covering the common cases rather than the minor-gaps level of a 4.	5 / 5
Workflow Clarity	This is a simple single-task skill (under 50 lines) whose single action — run transcribe.sh on an audio file — is unambiguous, which the guidelines say can score 5. The referenced script itself also handles validation (file-not-found and missing OPENAI_API_KEY checks), so the operation is not risky or unguarded.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external reference files, and per the guidelines well-organized sections suffice for a 5. Sections (Quick start, Useful flags, API key) are clear, and the one referenced path, {baseDir}/scripts/transcribe.sh, exists in the bundle and matches the documented flags.	5 / 5
	Total	20 / 20 Passed

Description

53%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, specific, and clearly identifies its niche (OpenAI Whisper transcription), but it completely lacks a "when to use" trigger clause and misses common synonyms like "speech-to-text" and audio file extensions. These gaps limit discovery and leave completeness and trigger quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to transcribe audio, convert speech to text, or mentions Whisper, .mp3/.m4a/.wav files."

Include natural synonyms and file extensions (speech-to-text, transcription, .mp3, .m4a, .wav) to improve trigger term coverage.

Optionally name 1-2 more concrete capabilities (e.g., language hints, prompt-based speaker names, JSON output) to raise specificity.

Dimension	Reasoning	Score
Specificity	"Transcribe audio via OpenAI Audio Transcriptions API (Whisper)" names the domain and a single concrete action (transcribe audio), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because no additional specific actions (e.g., language hints, output formats) are listed.	3 / 5
Completeness	The description has a clear "what" (transcribe audio via the OpenAI API) but contains no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 2 because the "what" is specific and unambiguous rather than vague.	3 / 5
Trigger Term Quality	"Transcribe audio" and "Whisper" are natural phrases users would say, but common variations and synonyms like "speech-to-text", "subtitles", or audio file extensions (.mp3, .m4a, .wav) are absent. This fits "some relevant keywords but missing common variations or synonyms" rather than the good coverage of a 4.	3 / 5
Distinctiveness Conflict Risk	"OpenAI Audio Transcriptions API (Whisper)" carves out a clear niche with distinct triggers, but the bare phrase "transcribe audio" overlaps with local Whisper or other transcription skills. This is "mostly distinct; minor overlap risk with closely related skills" rather than the minimal conflict risk of a 5.	4 / 5
	Total	13 / 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: trpc-group/trpc-agent-go
Path: openclaw/skills/openai-whisper-api/SKILL.md
Commit: 9bb1c42

Reviewed: 8 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.