venice-audio-speech

Text-to-speech models, voices, formats, and streaming via Venice.ai. Useful for narration, voiceover, and conversational agent voices.

Quality

61%

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/venice-audio-speech/SKILL.md

Quality

Content

53%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.

A tidy, well-organized catalogue entry that functions as a pointer to the upstream Venice.ai skill bundle. Its main weakness is actionability: it tells the agent to go read an external README rather than providing concrete, executable steps for the TTS task itself.

Suggestions

Add concrete installation steps (e.g., the exact git clone/copy command and target skills-directory path) instead of 'install the upstream bundle into your active agent's skills directory'.

Replace the non-portable `open https://...` with an actionable instruction such as fetching and reading the upstream README via the available tools.

Include at least one minimal usage example (e.g., how to invoke the TTS endpoint/skill once installed) so the entry is self-contained beyond pointing upstream.

Dimension	Reasoning	Score
Conciseness	The body is lean (under 30 lines), well-sectioned, and does not over-explain concepts Claude already knows; it loses a point only because the 'What it does' section repeats the frontmatter description verbatim and the 'How to use' prose could be slightly tighter.	4 / 5
Actionability	Guidance is high-level ('install the upstream bundle into your active agent's skills directory') with only one marginal command (`open https://github.com/veniceai/skills`), and no concrete, executable steps for actually producing speech — it redirects to an external README rather than instructing.	2 / 5
Workflow Clarity	A rough sequence is present (inspect upstream README → install bundle → invoke by name or trigger), but the install step is undefined ('install the upstream bundle' gives no command/path) and there are no checkpoints; this is a pointer skill so the destructive-operation cap does not apply, but the gaps keep it at 3.	3 / 5
Progressive Disclosure	No local bundle files exist, and the short body is organized into clear sections (What it does, Source, How to use) with a single one-level-deep external pointer (the upstream GitHub URL); it is well-structured for a sub-50-line skill, with only minor gaps keeping it from a 5.	4 / 5
	Total	13 / 20 Passed

Description

70%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.

A concise, mostly clear description that names a distinct niche (Venice.ai TTS) and surfaces several natural trigger terms. It would benefit from converting topical categories into concrete actions and making the 'when' guidance more explicit.

Suggestions

Lead with concrete verbs (e.g., 'Generate speech audio from text, list available voices, select formats, and stream audio via Venice.ai') instead of noun-based category lists.

Replace 'Useful for...' with an explicit 'Use when the user wants narration, voiceover, TTS, or a conversational agent voice.' clause to lock in the 'when'.

Add 'TTS' and 'text to speech' as natural synonyms alongside 'Text-to-speech' for fuller keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (TTS) and several capability areas ('models, voices, formats, and streaming'), but these are topical categories rather than concrete verb-based actions like 'generate speech' or 'convert text to audio', so it stops at listing 1-2 concrete actions rather than comprehensive coverage.	3 / 5
Completeness	Clearly states what it does (TTS models/voices/formats/streaming via Venice.ai) and gives an equivalent 'when' clause ('Useful for narration, voiceover, and conversational agent voices'); the 'when' is present but not framed as an explicit 'Use when...' trigger list, so it is not a full 5.	4 / 5
Trigger Term Quality	Includes natural terms a user would say — 'Text-to-speech', 'narration', 'voiceover', 'voices' — giving good keyword coverage, though a few common variants like 'TTS' or 'audio' are absent.	4 / 5
Distinctiveness Conflict Risk	The Venice.ai-specific TTS niche ('via Venice.ai') gives it a clear, distinct scope with minimal conflict risk, though 'conversational agent voices' introduces minor overlap with general voice/conversational skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/venice-audio-speech/SKILL.md
Commit: d4138ea

Reviewed: 3 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.