openai-whisper

Local speech-to-text with the Whisper CLI (no API key).

0.91x

Quality

—

Does it follow best practices?

Impact

91%

0.91x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

100%

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

The content is a tight, executable quick-start for a simple single-task skill, with concrete commands and useful notes and no concept filler. The only minor blemish is the install-specific note that `--model` defaults to `turbo`, which is not universally portable.

Dimension	Reasoning	Score
Conciseness	The body is lean (a one-line intro, two commands, three notes) with no explanations of concepts Claude already knows; every token earns its place, matching the lean-and-efficient anchor.	3 / 3
Actionability	It provides two fully executable, copy-paste-ready commands with concrete flags (e.g. `whisper /path/audio.mp3 --model medium --output_format txt --output_dir .`), matching the fully-executable anchor.	3 / 3
Workflow Clarity	This is a simple single-task skill where the action is unambiguous (run `whisper` with flags) and the operation is non-destructive, so per the simple-skills scoring note workflow clarity can score 3.	3 / 3
Progressive Disclosure	The skill is under 50 lines with well-organized sections (Quick start, Notes) and no need for external references, which per the scoring notes lets progressive disclosure score 3 on structure alone.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 third-person with a clear niche (local Whisper, no API key), but it lacks an explicit use-when trigger clause and a fuller enumeration of capabilities. Adding trigger guidance and natural terms like "transcribe" would lift it.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user wants to transcribe audio, generate subtitles, or translate spoken audio to English locally.'

Include more natural trigger terms users actually say, such as 'transcribe', 'transcription', 'subtitles', 'SRT', or 'audio files'.

Enumerate concrete capabilities, e.g. 'Transcribe audio to text/SRT/VTT and translate spoken audio to English.'

Dimension	Reasoning	Score
Specificity	"Local speech-to-text with the Whisper CLI" names the domain and tool but lists only a single action with no enumeration of capabilities such as transcription vs. translation or output formats, matching the anchor that names domain and some actions but is not comprehensive.	2 / 3
Completeness	The description answers "what" (local speech-to-text) but has no "Use when..." trigger clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	"speech-to-text" and "Whisper" are relevant natural terms, but common variations a user would actually say ("transcribe", "transcription", "subtitles", "SRT", "audio files") are absent, so it has some relevant keywords but misses common variations.	2 / 3
Distinctiveness Conflict Risk	"Whisper CLI" and "(no API key)" give it a clearer niche than generic transcription skills, but without explicit triggers it could still overlap with other speech/audio skills.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: 737835b

Reviewed: 3 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.