sherpa-onnx-tts
Local text-to-speech via sherpa-onnx (offline, no cloud)
70
56%
Does it follow best practices?
Impact
100%
1.51xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/sherpa-onnx-tts/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 (offline TTS via sherpa-onnx) which makes it distinctive, but it is too terse to be effective for skill selection. It lacks specific actions, common trigger terms users would naturally use, and has no explicit 'Use when...' guidance to help Claude know when to select this skill.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks to convert text to speech, generate audio from text, or needs TTS functionality without cloud services.'
Include common trigger term variations like 'TTS', 'speech synthesis', 'generate audio', 'read aloud', 'voice output', and 'convert text to audio'.
List specific concrete actions such as 'Converts text to speech audio files, selects from available voice models, adjusts speech parameters like rate and pitch using sherpa-onnx locally.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (text-to-speech) and the tool (sherpa-onnx), and mentions key characteristics (offline, no cloud), but does not list specific concrete actions like 'convert text to audio files', 'adjust speech rate', or 'select voice models'. | 2 / 3 |
Completeness | Provides a brief 'what' (text-to-speech via sherpa-onnx) but completely lacks a 'when should Claude use it' clause. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also thin, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'text-to-speech' and 'sherpa-onnx' which are relevant, but misses common user variations like 'TTS', 'speech synthesis', 'read aloud', 'generate audio', 'voice output', or 'convert text to speech'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'text-to-speech', 'sherpa-onnx', and 'offline/local' creates a very specific niche that is unlikely to conflict with other skills. This is a clearly distinct tool and use case. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise and well-structured skill for local TTS via sherpa-onnx. Its main weakness is the vague installation step (no download URLs or commands) and the absence of a verification step to confirm the setup works. The usage section is clear and the notes handle edge cases well.
Suggestions
Add concrete download commands or URLs for the runtime and voice model (e.g., 'wget https://... -O runtime.tar.gz && tar xzf ...')
Add a verification step after installation, such as 'Run `sherpa-onnx-tts --help` to confirm the binary is accessible and the model is loaded correctly'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. No unnecessary explanations of what TTS is or how sherpa-onnx works internally. Every section serves a clear purpose and there's no padding. | 3 / 3 |
Actionability | Provides concrete config JSON and CLI commands, but the install step is vague ('Download the runtime for your OS') without specifying URLs, exact commands, or download scripts. The {baseDir} placeholder is useful but the initial setup lacks executable specificity. | 2 / 3 |
Workflow Clarity | The install-configure-use sequence is present but lacks validation checkpoints. There's no step to verify the installation worked (e.g., 'run sherpa-onnx-tts --help to confirm setup'), and no error recovery guidance if the model path is wrong or the binary fails. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized into clear Install/Usage sections with notes for edge cases. No unnecessary nesting or external references needed. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 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 |
Total | 9 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
af8bd5f
- 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.