sherpa-onnx-tts
Local text-to-speech via sherpa-onnx (offline, no cloud)
63
56%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./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 and lacks both specific action verbs and explicit trigger guidance. It reads more like a label than a functional description that would help Claude reliably select this skill from a large pool.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to convert text to speech, generate audio from text, or needs offline/local TTS capabilities.'
Include common trigger term variations such as 'TTS', 'speech synthesis', 'generate audio', 'read aloud', and 'convert text to audio'.
List specific concrete actions the skill performs, e.g., 'Converts text to speech audio files, supports multiple voices and languages, generates .wav output using sherpa-onnx models.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (text-to-speech) and the tool (sherpa-onnx), and mentions key attributes (offline, no cloud), but does not list specific concrete actions like 'convert text to audio files', 'select voices', or 'adjust speech parameters'. | 2 / 3 |
Completeness | Describes what at a high level (text-to-speech via sherpa-onnx) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores 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', 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 clearly distinguishable. | 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 is concise and well-organized for its scope. Its main weaknesses are the vague installation steps (no download URLs or specific commands) and the lack of any validation/verification steps to confirm the setup works. The usage section is concrete and actionable.
Suggestions
Add specific download URLs or commands for the runtime and voice model (e.g., `wget <url>` or a script reference) to make the install steps fully actionable.
Add a verification step after installation, such as `sherpa-onnx-tts --help` or a test command, to confirm the setup is working before proceeding to usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what TTS is or how sherpa-onnx works internally. Every section serves a purpose: install, config, usage. The notes section is compact and covers edge cases without over-explaining. | 3 / 3 |
Actionability | The usage command is concrete and copy-paste ready, and the config JSON is specific. However, the install section is vague—'Download the runtime for your OS' and 'Download a voice model' lack specific URLs, commands, or scripts to execute. This leaves a critical step incomplete. | 2 / 3 |
Workflow Clarity | The install → configure → use sequence is clear, but there are no validation checkpoints. There's no way to verify the runtime installed correctly, no test command to confirm the model works, and no error recovery guidance if the TTS command fails. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized into clear sections (Install, Usage, Notes). No bundle files are provided, but the skill is compact enough that external references aren't needed. The structure is easy to scan. | 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
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- 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.