openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
76
70%
Does it follow best practices?
Impact
91%
0.91xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/openai-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 identifies a clear niche (local Whisper CLI speech-to-text) which makes it distinctive, but it lacks specific actions, natural trigger terms users would say, and an explicit 'Use when...' clause. It reads more like a tagline than a functional skill description.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to transcribe audio files locally, convert speech to text, or generate subtitles without an API key.'
List specific concrete actions such as 'Transcribes audio/video files to text, generates SRT/VTT subtitles, supports multiple languages and audio formats (.mp3, .wav, .m4a).'
Include natural user keywords like 'transcribe', 'audio', 'transcription', 'subtitle', 'voice to text', and common file extensions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (speech-to-text) and the tool (Whisper CLI), and notes 'no API key', but doesn't list specific actions like transcribing audio files, generating subtitles, converting formats, etc. | 2 / 3 |
Completeness | Describes what it does at a high level but has no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the 'what' is also quite thin, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes good terms like 'speech-to-text', 'Whisper', and 'CLI', but misses common user variations like 'transcribe', 'audio', 'transcription', '.wav', '.mp3', 'subtitle', or 'STT'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Whisper CLI', 'local', and 'no API key' creates a very clear niche that is unlikely to conflict with other skills, even other audio or transcription skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, minimal skill that respects Claude's intelligence and token budget. It provides immediately actionable CLI commands with just enough context (model defaults, cache location) to avoid common pitfalls. The brevity is a strength, not a weakness, for this single-purpose tool.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — no unnecessary explanations, no description of what Whisper is or how speech-to-text works. Every line adds value. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready CLI commands with realistic flags and file paths. The notes section adds practical details about model defaults and cache location. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose skill (run a CLI command). The single action is unambiguous, and the two example commands clearly show the primary use cases. No multi-step process or destructive operations require validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized into a quick start section and notes. No bundle files are needed for this simple skill. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
- Repository
- Hung-Reo/hungreo-openclaw
- Commit
d8d7f4b
- 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.