CtrlK
BlogDocsLog inGet started
Tessl Logo

omnivoice

Speak and transcribe through the user's local VoiceStudio — free, offline, no API key. Text-to-speech (including the user's cloned voices) and speech-to-text via the OpenAI-compatible API at localhost:3900.

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 content is lean, fully executable, and well-structured, with a gating health check and error-surfacing guidance providing clear validation. It is an exemplary simple, single-purpose skill body.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no concept explanations, just endpoints, params, and genuinely non-obvious notes; every line earns its place.

5 / 5

Actionability

Copy-paste-ready curl and Python SDK commands cover TTS, voice discovery, and STT, with concrete parameter values and response-format options enumerated.

5 / 5

Workflow Clarity

A pre-flight health check gates first calls with explicit failure handling (tell the user to launch, don't silently fall back), and error-recovery guidance surfaces engine errors verbatim — clear validation with a feedback loop.

5 / 5

Progressive Disclosure

Under 50 lines with no bundle files, organized into well-signaled sections; the bulk REST reference is appropriately deferred to the app's in-app OpenAPI Reference rather than inlined.

5 / 5

Total

20

/

20

Passed

Description

75%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 specific, concrete, and occupies a clear niche, but it lacks an explicit 'when to use' trigger clause, capping completeness at 3. Adding a 'Use when the user asks to generate speech, narrate text, clone a voice, or transcribe audio' clause would raise it.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to generate speech, narrate text, clone a voice, or transcribe audio.'

Include natural synonyms (narrate, dictation, voiceover, subtitles) so the description matches a wider range of user phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Speak and transcribe', 'Text-to-speech (including the user's cloned voices)', 'speech-to-text' — covering the domain comprehensively.

5 / 5

Completeness

The 'what' is clear (TTS incl. cloned voices and STT via a local OpenAI-compatible API), but there is no explicit 'Use when...' trigger clause, which caps completeness at 3 per the guidelines.

3 / 5

Trigger Term Quality

Natural terms like 'Speak', 'transcribe', 'Text-to-speech', 'speech-to-text', and 'cloned voices' are present, but common synonyms (narrate, dictation, voiceover) and file extensions are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche — the user's local VoiceStudio at localhost:3900 with cloned voice profiles — gives distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
debpalash/OmniVoice-Studio
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.