openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
74
Quality
66%
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 ./openclaw/skills/openai-whisper/SKILL.mdQuality
Discovery
32%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 the core technology (Whisper CLI) and differentiates it from API-based solutions, but lacks specific actions and completely omits trigger guidance. Without a 'Use when...' clause, Claude cannot reliably determine when to select this skill over alternatives.
Suggestions
Add a 'Use when...' clause with trigger terms like 'transcribe audio', 'convert speech to text', 'voice recording', or file extensions like '.mp3', '.wav'
List specific capabilities such as 'transcribe audio files, support multiple languages, handle various audio formats'
Include natural user terms like 'transcribe', 'audio file', 'recording', 'voice memo' that users would actually say
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (speech-to-text) and tool (Whisper CLI), and clarifies 'no API key', but doesn't list specific actions like transcribe audio files, convert formats, or handle multiple languages. | 2 / 3 |
Completeness | Describes what (speech-to-text with Whisper CLI) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'speech-to-text' and 'Whisper CLI' which are relevant, but misses common user terms like 'transcribe', 'audio', 'voice', 'recording', '.mp3', '.wav', or 'convert speech'. | 2 / 3 |
Distinctiveness Conflict Risk | Specifying 'Whisper CLI' and 'no API key' provides some distinction from cloud-based transcription services, but could still overlap with other audio processing or transcription skills. | 2 / 3 |
Total | 7 / 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 the token budget. It provides exactly what's needed: executable commands with practical flags, and only the non-obvious details (cache location, default model). The brevity is a strength, not a weakness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what Whisper is or how speech-to-text works. Every line provides actionable information Claude wouldn't inherently know (CLI flags, cache location, default model). | 3 / 3 |
Actionability | Provides copy-paste ready commands with real file paths and flags. Two concrete examples cover the main use cases (transcription and translation) with different output formats. | 3 / 3 |
Workflow Clarity | This is a simple, single-task skill where the commands are self-contained and non-destructive. The workflow is unambiguous: run the command, get output. No multi-step process requiring validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized with clear sections (Quick start, Notes). Appropriate structure for the scope. | 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
- trpc-group/trpc-agent-go
- Commit
8763418
- 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.