CtrlK
BlogDocsLog inGet started
Tessl Logo

sherpa-onnx-tts

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

71

1.51x
Quality

Does it follow best practices?

Impact

100%

1.51x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The content is admirably concise and mostly actionable, with a clear install→config→usage flow. Its main gaps are non-literal '{baseDir}' placeholders, absent validation steps, and a referenced wrapper script that is not actually bundled.

Suggestions

Replace '{baseDir}' placeholders with a concrete note on how to resolve the skill directory, or show an explicit resolved example, so commands are copy-paste ready.

Add a verification step after install (e.g., 'confirm runtime/ sherpa-onnx-offline-tts exists and models/ contains the .onnx file') to close the workflow gap.

Either include the referenced bin/sherpa-onnx-tts wrapper as a bundled scripts/ file or remove/clarify the reference so progressive disclosure is not left dangling.

DimensionReasoningScore

Conciseness

The body is lean: brief install steps, a necessary json5 config snippet, a PATH export, one usage command, and a few tight notes — it assumes Claude's competence and does not explain what TTS or sherpa-onnx is.

3 / 3

Actionability

Provides a usage command and a concrete config block, but examples use a '{baseDir}' placeholder rather than copy-paste-ready paths, and the actual runtime/model download commands are not given in the body (they live in frontmatter metadata).

2 / 3

Workflow Clarity

Install is a clearly numbered two-step sequence followed by config, but there are no validation checkpoints (e.g., verify the runtime binary exists or the model dir is correct), so it sits at 'steps present, checkpoints missing'.

2 / 3

Progressive Disclosure

Sections are well organized and the file is short, but the body references a wrapper at '{baseDir}/bin/sherpa-onnx-tts' that is not present as a bundle file, leaving a dangling, unclearly-signaled reference.

2 / 3

Total

9

/

12

Passed

Description

50%

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 non-vague, naming the tool and its offline nature, but it omits explicit usage triggers and only lightly covers natural keywords. Adding a 'Use when...' clause and synonyms like 'TTS'/'voice' would raise it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants speech/audio output, text-to-speech, or TTS without cloud or network access.'

Include common synonyms users say — 'TTS', 'voice', 'speech synthesis', 'audio' — alongside 'text-to-speech'.

Optionally list a second concrete capability (e.g., 'generate WAV audio files') to strengthen specificity.

DimensionReasoningScore

Specificity

Names the domain and tool ('Local text-to-speech via sherpa-onnx') plus an attribute ('offline, no cloud'), but lists only one capability rather than multiple concrete actions, matching the 'names domain and some actions' anchor.

2 / 3

Completeness

Clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

Includes the natural term 'text-to-speech' but omits common variations users would say ('TTS', 'voice', 'speech', 'audio'); 'sherpa-onnx' is technical jargon, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

The 'sherpa-onnx' and 'offline, no cloud' qualifiers give it a recognizable niche, but the thin trigger set means it could still overlap with other TTS skills.

2 / 3

Total

8

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
trpc-group/trpc-agent-go
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.