Local text-to-speech via sherpa-onnx (offline, no cloud)
70
Quality
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 specific tool and its key differentiator (offline/local), but lacks actionable detail about what operations it performs and critically missing explicit trigger guidance. The description reads more like a label than a selection guide for Claude choosing among multiple skills.
Suggestions
Add a 'Use when...' clause with trigger terms like 'TTS', 'text to speech', 'read aloud', 'convert text to audio', 'speech synthesis', 'offline voice'
List specific concrete actions such as 'Convert text to audio files, generate speech from documents, synthesize voice output'
Include common file format triggers like '.wav', '.mp3', 'audio file' if applicable
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (text-to-speech) and the tool (sherpa-onnx), and clarifies it's offline/local, but doesn't list specific actions like 'convert text to audio files', 'adjust voice parameters', or 'batch process documents'. | 2 / 3 |
Completeness | Describes what it is (text-to-speech via sherpa-onnx) 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 'text-to-speech' which users might say, but misses common variations like 'TTS', 'speech synthesis', 'read aloud', 'convert to audio', or 'voice generation' that users would naturally use. | 2 / 3 |
Distinctiveness Conflict Risk | The specific tool name 'sherpa-onnx' and the 'offline, no cloud' qualifier create a clear niche that distinguishes it from other potential TTS skills or cloud-based alternatives. | 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.
This is a reasonably well-structured skill that efficiently communicates how to set up and use sherpa-onnx for local TTS. Its main weakness is the vague installation steps that don't specify download sources or provide verification commands. The usage section is clear and actionable.
Suggestions
Add specific download URLs or commands for obtaining the runtime and voice models (e.g., 'Download from https://github.com/k2-fsa/sherpa-onnx/releases')
Include a verification step after installation, such as 'Verify installation: sherpa-onnx-tts --version' or checking that expected files exist
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only essential setup and usage information without explaining what TTS is or how sherpa-onnx works internally. Every section serves a clear purpose. | 3 / 3 |
Actionability | Provides concrete commands and config examples, but step 1 and 2 of Install are vague ('Download the runtime for your OS') without specifying where to download from or exact commands. The usage example is copy-paste ready. | 2 / 3 |
Workflow Clarity | Steps are listed in logical order (install runtime, download model, configure, run), but lacks validation checkpoints - no way to verify the installation succeeded before proceeding to usage. | 2 / 3 |
Progressive Disclosure | For a simple single-purpose skill under 50 lines, the content is well-organized with clear sections (Install, Usage) and appropriate inline notes for edge cases without needing external references. | 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 | |
8763418
Table of Contents
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.