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), making it distinctive. However, it lacks an explicit 'Use when...' clause and misses common trigger term variations that users might naturally use when requesting transcription services.
Suggestions
Add a 'Use when...' clause such as 'Use when the user wants to transcribe audio, convert speech to text, or process audio/video files (.mp3, .wav, .m4a, .mp4).'
Include natural trigger term variations like 'speech-to-text', 'voice recording', 'dictation', and common audio file extensions (.mp3, .wav, .m4a, .flac).
List additional specific capabilities if applicable, such as 'supports multiple languages, generates timestamps, handles various audio formats'.
| 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 has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and since the 'when' is entirely missing, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'transcribe', 'audio files', 'text', and 'Whisper', but misses common variations users might say such as 'speech-to-text', 'voice recording', 'mp3', 'wav', 'dictation', or 'convert audio'. | 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. Main weaknesses are some verbosity in listing capabilities that are already evident from usage examples, and the lack of any validation/verification guidance for checking transcription output. The model comparison table is useful reference but could be externalized.
Suggestions
Remove the 'Capabilities' bullet list since it restates what's already clear from the usage and parameters sections.
Add a brief validation step, e.g., 'Verify output: check that the output file is non-empty and spot-check a few lines for accuracy.'
Move the model sizes table and installation instructions to a separate REFERENCE.md to keep the main skill lean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The capabilities list is somewhat redundant with the parameters/usage sections. The model sizes table and supported audio formats section add reference value but the 'Capabilities' bullet list largely restates what's obvious from the usage examples. Installation instructions for ffmpeg and whisper are borderline unnecessary for Claude. | 2 / 3 |
Actionability | Provides fully executable bash commands with clear flag usage, specific examples for different scenarios (language specification, timestamps, JSON output), and concrete parameter documentation. 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 — no mention of what to do if transcription fails, how to verify output quality, or how to handle unsupported formats. For a transcription task, some verification step (e.g., checking output file is non-empty) would be valuable. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the model sizes table and installation instructions could be in a separate reference file. For a skill under ~60 lines this is acceptable, but the inline reference material makes it slightly heavier than needed for the main skill file. | 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
af8bd5f
- 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.