whisper

Transcribe audio files to text using OpenAI Whisper

Quality

45%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./examples/skill/skills/whisper/SKILL.md

Quality

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 (OpenAI Whisper) and a focused task (audio transcription), giving it good distinctiveness. However, it lacks a 'Use when...' clause and misses common user trigger terms like 'speech-to-text', '.mp3', '.wav', or 'voice recording', which limits its effectiveness for skill selection in a large pool.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to transcribe audio, convert speech to text, or process audio/video files (.mp3, .wav, .m4a).'

Include common user-facing trigger terms and file extensions such as 'speech-to-text', 'STT', 'voice recording', '.mp3', '.wav', '.m4a', '.flac'.

Expand the capability list to mention additional actions if applicable, such as 'supports multiple audio formats, generates timestamps, handles multiple languages'.

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, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, 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', 'STT', '.mp3', '.wav', 'voice recording', 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. The domain is narrow and well-defined.	3 / 3
	Total	8 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides a well-structured CLI reference with concrete command examples and useful parameter documentation. However, it references a script (`scripts/transcribe.py`) that doesn't exist in the bundle, undermining its actionability. It also lacks error handling guidance and validation steps for common failure scenarios like missing dependencies or unsupported formats.

Suggestions

Provide the actual `scripts/transcribe.py` script in the bundle, or include inline Python code that performs the transcription so the skill is self-contained and executable.

Add error handling guidance: what to do if ffmpeg is missing, if the model fails to download, or if the audio format is unsupported.

Remove the 'Capabilities' section as it's redundant with the usage examples and parameters, and trim the installation section to just the commands.

Add a validation step such as checking the output file exists and is non-empty, or verifying dependencies before running transcription.

Dimension	Reasoning	Score
Conciseness	The model sizes table and supported audio formats section add useful reference value, but the 'Capabilities' bullet list is largely redundant with the parameters and usage sections. The installation section explains things Claude already knows. Some tightening possible.	2 / 3
Actionability	The CLI commands are concrete and copy-paste ready, but the skill references `scripts/transcribe.py` which is not provided in the bundle. Without the actual script, Claude cannot execute the guidance. The commands themselves are well-structured but depend on a missing artifact.	2 / 3
Workflow Clarity	The skill presents a single-step process (run a script with options) which is clear, but there are no validation or error-handling steps. What happens if ffmpeg is missing? What if the audio file is corrupted or the model fails to download? No feedback loops for common failure modes.	2 / 3
Progressive Disclosure	The content is reasonably organized with clear sections, but everything is inline in one file. The model sizes table and parameter reference could be in a separate reference file. No bundle files are provided despite referencing `scripts/transcribe.py`, which is a significant gap.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: trpc-group/trpc-agent-go
Commit: b22744d

Reviewed: 1 day 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.