whisper
Transcribe audio files to text using OpenAI Whisper
61
52%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skill/skills/whisper/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 is concise and identifies a clear niche (audio transcription via Whisper), which makes it distinctive. However, it lacks a 'Use when...' clause and misses common trigger term variations that users might naturally use, significantly reducing its effectiveness for skill selection among many options.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to transcribe audio, convert speech to text, or process audio/voice recordings.'
Include common trigger term variations such as 'speech-to-text', 'voice recording', '.mp3', '.wav', '.m4a', 'convert audio to text', or 'dictation'.
List additional specific capabilities if applicable, such as supported formats, language detection, or timestamp generation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (audio transcription) and one specific action (transcribe audio files to text), and mentions the tool (OpenAI Whisper), but only describes a single action rather than listing multiple concrete capabilities. | 2 / 3 |
Completeness | Describes what the skill does (transcribe audio to text) 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 since the 'what' is also minimal, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'transcribe', 'audio files', 'text', and 'Whisper', but misses common user variations such as 'speech-to-text', 'voice recording', '.mp3', '.wav', 'convert audio', or 'dictation'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of audio transcription and OpenAI Whisper creates a clear, distinct niche that is unlikely to conflict with other skills. Audio transcription is a well-defined task domain. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A solid, actionable skill with clear executable commands and good parameter documentation. Its main weaknesses are some unnecessary verbosity (capabilities list, supported formats that Claude already knows) and the lack of any error handling or validation guidance for a tool that depends on external software (ffmpeg, model downloads). The content is well-structured but could be leaner.
Suggestions
Remove the 'Capabilities' and 'Supported Audio Formats' sections—Claude already knows Whisper's capabilities, and these waste tokens.
Add a brief validation/troubleshooting note: how to verify ffmpeg is installed (`ffmpeg -version`), what errors look like if it's missing, and how to verify the transcription succeeded.
Consider adding an example of expected output (a snippet of transcript text or JSON) so Claude knows what success looks like.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The capabilities list and supported audio formats section are somewhat redundant—Claude already knows what Whisper supports. The model sizes table is useful reference but the 'Capabilities' bullet list largely restates what the description already covers. Some tightening possible. | 2 / 3 |
Actionability | Provides fully executable bash commands with clear flag usage, a complete parameter reference, and concrete examples for different use cases. The installation commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | This is essentially a single-command tool, so multi-step workflow isn't strictly needed. However, there's no validation or error handling guidance—what if ffmpeg isn't installed, the audio file is corrupted, or the model fails to download? For a tool with external dependencies, some verification steps would be valuable. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. The model sizes table and parameter reference could potentially be separated, though the file isn't excessively long. No references to external files for advanced usage or troubleshooting. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- trpc-group/trpc-agent-go
- Commit
0c1ec2b
- 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.