openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
76
70%
Does it follow best practices?
Impact
91%
2.27xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/openai-whisper-api/SKILL.mdQuality
Discovery
40%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 clearly identifies a specific tool and API for audio transcription, giving it good distinctiveness. However, it is too terse—it lacks a 'Use when...' clause, misses common user trigger terms like 'speech-to-text' or audio file extensions, and only describes a single action without elaborating on capabilities.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to transcribe audio files, convert speech to text, or process .mp3/.wav/.m4a recordings.'
Include natural trigger term variations such as 'speech-to-text', 'voice recording', 'audio file', and common file extensions like '.mp3', '.wav', '.m4a'.
List additional concrete capabilities beyond basic transcription, such as language detection, timestamp generation, or supported audio formats.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (audio transcription) and the specific tool (OpenAI Audio Transcriptions API / Whisper), but only describes a single action ('transcribe audio') without listing additional concrete capabilities like format handling, timestamp extraction, or language detection. | 2 / 3 |
Completeness | Answers 'what does this do' (transcribe audio via Whisper) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also minimal, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'transcribe', 'audio', 'OpenAI', and 'Whisper', but misses common user variations such as 'speech-to-text', 'convert audio to text', 'voice recording', or file extensions like '.mp3', '.wav'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is quite distinctive by specifying both the exact API (OpenAI Audio Transcriptions API) and the model (Whisper), making it clearly distinguishable from other audio or transcription skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, lean skill that respects Claude's intelligence and provides fully actionable guidance. It covers the essential use cases with concrete examples, organizes content cleanly into three focused sections, and avoids any unnecessary explanation. The only minor note is that bundle files weren't provided to verify the referenced script exists, but the skill content itself is exemplary.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No unnecessary explanations of what Whisper is or how APIs work. Lean structure with just the essentials: quick start, flags, and API key configuration. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready shell commands with realistic flag examples covering common use cases (language, prompt, JSON output). The API key configuration is specific with an exact JSON structure. | 3 / 3 |
Workflow Clarity | This is a simple single-task skill (run a script to transcribe audio). The single action is unambiguous with clear defaults stated and flag variations shown. No multi-step process requiring validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a simple, short skill under 50 lines, the content is well-organized into logical sections (quick start, flags, API key). No need for external references given the scope, and the script itself is appropriately delegated to the bundle. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
- Repository
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- Reviewed
Table of Contents
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.