whisper
Transcribe audio files to text using OpenAI Whisper
70
Quality
62%
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 ./benchmark/gaia/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 clearly identifies its niche (audio transcription with Whisper) and is distinctive, but suffers from missing explicit trigger guidance and limited trigger term coverage. Adding a 'Use when...' clause and expanding natural keywords would significantly improve skill selection accuracy.
Suggestions
Add a 'Use when...' clause with trigger terms like 'transcribe audio', 'speech-to-text', 'convert recording to text', or 'audio to transcript'
Include common file format variations users might mention: '.mp3', '.wav', '.m4a', 'voice recording', 'podcast', 'meeting recording'
Expand capabilities if applicable, such as 'supports multiple languages' or 'handles various audio formats'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (audio files) and one specific action (transcribe to text), and mentions the tool (OpenAI Whisper), but only describes a single capability rather than multiple concrete actions. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'transcribe', 'audio files', 'text', and 'Whisper', but missing common variations users might say like 'speech-to-text', 'convert audio', 'voice recording', '.mp3', '.wav', or 'dictation'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on audio transcription using Whisper; unlikely to conflict with other skills due to the specific technology and task combination. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear executable examples and good organization. The main weakness is some verbosity in sections like Capabilities (redundant with Parameters) and the model sizes table, which add tokens without significant value for Claude. The installation section also explains things Claude already knows how to do.
Suggestions
Remove the Capabilities section as it duplicates information from Parameters and Usage examples
Consider removing or condensing the Model Sizes table to a single line recommendation (e.g., 'Use base for speed/accuracy balance, large for best quality')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary sections like the capabilities list (which largely duplicates the parameters section) and the model sizes table which Claude could infer or look up. The installation section is also somewhat redundant for Claude. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready commands with clear examples covering basic and advanced usage. Parameters are well-documented with specific values and defaults. | 3 / 3 |
Workflow Clarity | This is a simple single-task skill (run a script with options). The workflow is unambiguous: provide input file, output file, and optional flags. No multi-step process requiring validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized with clear sections (Usage, Parameters, Model Sizes). The structure allows quick scanning and finding relevant information. | 3 / 3 |
Total | 11 / 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
50ef2f3
- 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.