whisper

Transcribe audio files to text using OpenAI Whisper

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

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

The body is concise, executable, and clearly organized for a single-purpose skill, with copy-paste commands and a real bundled script. Its main gap is progressive disclosure: most detail is inlined rather than split into reference files.

Suggestions

Move the model-size table and supported-format list into a reference file (e.g. references/models.md) and link to it, keeping SKILL.md a lean overview.

Consider a references/ file for advanced options (timestamps, JSON metadata format, language codes) and signal it from the body to deepen progressive disclosure.

Add a one-line note confirming the bundled script's CLI matches the documented flags, so the inline examples and script stay in sync.

Dimension	Reasoning	Score
Conciseness	The body is lean and reference-style: capabilities, command examples, a parameter list, a model-size table, and dependencies — no padded conceptual explanation of what Whisper or audio files are. Every section earns its place.	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands with real flags and arguments, plus a parameter reference and a real bundled script (scripts/transcribe.py), matching the 'copy-paste ready' 3-anchor.	3 / 3
Workflow Clarity	This is a simple single-action skill; the single invocation is unambiguous and the per-option examples make sequencing clear, so per the simple-skills note workflow clarity can score 3 without multi-step checkpoints.	3 / 3
Progressive Disclosure	It is well-organized into clear sections and references one real bundled file (scripts/transcribe.py), but most detail (model table, format list, install steps) that could live in references is inlined and there are no other reference files for advanced content, so it falls short of the 'appropriately split, one-level-deep references' 3-anchor.	2 / 3
	Total	11 / 12 Passed

Description

60%

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 clear about its single domain (Whisper audio transcription) and is distinct from other skills, but it is terse and lacks trigger guidance. It states what the skill does without telling Claude when to invoke it.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrasings, e.g. 'Use when the user asks to transcribe audio, convert speech to text, or generate transcripts/subtitles from audio files.'

List concrete actions (transcribe, auto-detect language, add timestamps, output JSON) directly in the description to raise specificity from a single action to multiple.

Include common trigger terms users actually say — 'audio', 'transcription', 'speech-to-text', 'subtitles' — alongside 'Whisper'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Transcribe audio files to text') and the tool ('OpenAI Whisper') but lists only a single action rather than multiple concrete operations, matching 'Processes PDF files and extracts content' more than the multi-action 3-anchor.	2 / 3
Completeness	It answers 'what does this do' explicitly but provides no 'Use when...' clause or equivalent trigger guidance, so the 'when' is only implied — capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	'Transcribe audio files to text' and 'Whisper' are relevant natural terms, but common variations a user would actually say ('audio', 'transcription', 'speech-to-text', 'subtitles') are missing.	2 / 3
Distinctiveness Conflict Risk	The OpenAI Whisper / audio-transcription niche is clear and distinct; this description is unlikely to trigger for the wrong skill compared to overlaps like 'Works with document files'.	3 / 3
	Total	9 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.