whisper

Transcribe audio files to text using OpenAI Whisper

Quality

38%

Does it follow best practices?

Impact

Pending

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 is concise and identifies a clear, distinct capability (audio transcription via Whisper), which gives it strong distinctiveness. However, it lacks a 'Use when...' clause and misses common trigger term variations users might naturally use, significantly weakening its completeness and discoverability among many skills.

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', and 'dictation'.

List additional specific capabilities if applicable, such as 'supports multiple audio formats, handles multiple languages, generates timestamps or subtitles'.

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 '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', 'voice recording', '.mp3', '.wav', 'convert audio', or 'dictation'.	2 / 3
Distinctiveness Conflict Risk	Audio transcription using OpenAI Whisper is a clearly distinct niche that is unlikely to conflict with other skills. The combination of 'transcribe', 'audio', and 'Whisper' creates a unique fingerprint.	3 / 3
	Total	8 / 12 Passed

Implementation

37%

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 clear CLI interface description with useful parameter documentation and a model comparison table, but it references a script that is never provided or linked, undermining actionability. It lacks any error handling, validation steps, or troubleshooting guidance, and includes some content Claude doesn't need (capabilities list, basic installation commands, supported formats enumeration).

Suggestions

Provide the actual `scripts/transcribe.py` implementation or link to it so Claude can execute the transcription end-to-end.

Add validation/error-handling steps: check FFmpeg availability, verify audio file exists and is readable, handle model download failures.

Remove the 'Capabilities' bullet list and 'Supported Audio Formats' section—these restate what Whisper/FFmpeg already do and waste tokens.

Add a brief troubleshooting section for common failure modes (missing FFmpeg, out-of-memory for large models, unsupported file).

Dimension	Reasoning	Score
Conciseness	The capabilities list and supported audio formats section are somewhat redundant—Claude already knows what Whisper does and what formats FFmpeg supports. The model sizes table is useful but the 'Supported Audio Formats' line and 'Capabilities' bullet list add little value. Installation instructions for well-known packages are also unnecessary.	2 / 3
Actionability	The commands are concrete and copy-paste ready, but they reference a script (`scripts/transcribe.py`) whose contents are never shown or linked. Without the actual script or a reference to where it lives, Claude cannot execute the workflow—it's a CLI wrapper with no implementation.	2 / 3
Workflow Clarity	There is no multi-step workflow, no validation or error-handling guidance (e.g., what if FFmpeg is missing, the file is corrupt, or the model fails to download). For a task that can fail in several ways (missing dependencies, large files, wrong format), the absence of any verification or troubleshooting steps is a significant gap.	1 / 3
Progressive Disclosure	The content is reasonably structured with clear sections and a parameters table, but everything is inline in one file. The model sizes table and installation instructions could be separated or omitted, and there are no references to external docs or the actual script implementation.	2 / 3
	Total	7 / 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: fcc550d

Reviewed: 6 days 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.