sherpa-onnx-tts

Local text-to-speech via sherpa-onnx (offline, no cloud)

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sherpa-onnx-tts/SKILL.md

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, well-structured overview with concrete install and usage instructions and no padding. Its main weaknesses are a missing validation checkpoint for verifying output and a referenced wrapper script that is not present in the bundle, which together cap workflow clarity and progressive disclosure at 4.

Suggestions

Add a brief verification step after usage, e.g. "Verify: play ./tts.wav or check it is non-empty," to give the workflow an explicit checkpoint.

Ship the referenced wrapper in a discoverable location (e.g. scripts/ or bin/) or document its expected location/contents so the {baseDir}/bin/sherpa-onnx-tts reference resolves.

Document the wrapper's full flag set inline or in a short reference file so the usage example is fully self-contained.

Dimension	Reasoning	Score
Conciseness	The body is lean (~38 lines) with no explanation of what TTS is or how sherpa-onnx works; install steps, a config block, and a usage command each earn their place, matching the lean-and-efficient anchor that assumes Claude's competence.	5 / 5
Actionability	Install steps, a copy-paste json5 config, an executable usage command, and concrete override flags (--model-file, --tokens-file, --data-dir) give mostly executable guidance; the gap is that the wrapper script itself is referenced but its behavior/flags beyond the notes are not documented, keeping it below fully copy-paste-ready 5.	4 / 5
Workflow Clarity	The install → config → usage sequence is clearly ordered and the skill is single-purpose, but there is no validation checkpoint (e.g. verifying the produced .wav plays or that env vars resolved), a minor validation gap that holds it at 4 rather than 5.	4 / 5
Progressive Disclosure	Sections are well-organized into Install and Usage with no nested references, and the simple-skill exception would allow 5; however the body references a wrapper at {baseDir}/bin/sherpa-onnx-tts that is not present in any discoverable bundle directory (no scripts/ or bin/ shipped), a minor organization gap that keeps it at 4.	4 / 5
	Total	17 / 20 Passed

Description

61%Weight 40%Scale 1-5

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 is concise and names a specific tool with a clear offline/local niche, but it omits any explicit "Use when..." trigger guidance and lists only a single concrete action. Adding trigger phrases and one or two more concrete capabilities would raise completeness and specificity.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants speech output, local/offline TTS, or to generate audio from text without a cloud service."

List one or two more concrete actions (e.g. "generate .wav audio from text", "swap voices/models") to lift specificity from 3 to 4-5.

Include common synonyms such as "voice", "speech synthesis", or "read aloud" to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Local text-to-speech via sherpa-onnx (offline, no cloud)" names the domain (TTS) and one concrete action (text-to-speech) plus the specific tool, matching the anchor that names a domain with 1-2 concrete actions; it is not a 4 because no additional specific actions are listed.	3 / 5
Completeness	It clearly states what the skill does (local offline TTS via sherpa-onnx) but provides no "Use when..." clause or explicit trigger guidance, so per the rubric a missing when-clause caps completeness at 3.	3 / 5
Trigger Term Quality	"text-to-speech", "sherpa-onnx", "offline", and "no cloud" give good keyword coverage of natural phrasings a user would say, but common synonyms like "voice", "speech synthesis", or "read aloud" are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Naming a specific tool (sherpa-onnx) plus the "offline, no cloud" qualifier carves a clear niche distinct from cloud TTS skills, but the description is terse and lacks explicit trigger phrases, so it does not reach the minimal-conflict anchor of 5.	4 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/sherpa-onnx-tts/SKILL.md
Commit: 017761f

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.