venice-audio-speech

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

Quality

55%

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

40%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.

This is a thin catalogue/advertisement entry rather than a usable skill body: it delegates all substantive guidance to an external GitHub repository. The structure is clean and lean, but it provides almost no executable guidance and its workflow is a vague pointer sequence with no validation.

Suggestions

Replace the placeholder 'open https://github.com/veniceai/skills' with an executable install step (e.g., a git clone command into the agent's skills directory with a concrete target path).

Add a minimal inline quick-start (e.g., one working text-to-speech request against the Venice.ai API) so the skill is usable without round-tripping to the external README.

Spell out the usage workflow with numbered steps — install, verify the skill is discoverable, then invoke with an example prompt — instead of the current vague narrative paragraph.

Dimension	Reasoning	Score
Conciseness	The body is short, but it repeats the frontmatter description verbatim in 'What it does', restates the upstream URL in both 'Source' and the code block, and repeats the category — several elements that could be tightened. It does not pad with concepts Claude already knows, so it sits above anchor 2 but not fully at 'efficient'.	3 / 5
Actionability	The only concrete command is 'open https://github.com/veniceai/skills', and even that is preceded by the comment 'Inspect the upstream README for exact paths', admitting the actual install steps are absent. 'Install the upstream bundle into your active agent's skills directory' is a high-level hint with no specific steps to execute, matching anchor 2.	2 / 5
Workflow Clarity	A rough sequence exists (inspect upstream README → install bundle → invoke by name or trigger), but the steps are poorly defined — no install command, no target path, no verification that the skill was installed and discovered. This matches 'rough sequence present but many gaps; validation absent' rather than anchor 3's 'steps listed' with only checkpoint gaps.	2 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), and the body has clear, well-organized sections with no inlined content that belongs in separate files. The single reference (the upstream repo) is clearly signaled and one level deep, but it is an external URL carrying all of the skill's substance rather than bundled navigable material — good structure with a minor gap, matching anchor 4.	4 / 5
	Total	11 / 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 solid, concise description with a clear domain and genuinely useful trigger phrases. Its main weakness is that it enumerates features as nouns rather than stating concrete actions, and the use-case clause could be more explicit.

Suggestions

Rewrite the first sentence with action verbs (e.g., 'Generate spoken audio from text using Venice.ai models: list voices, select formats, and stream output').

Add trigger synonyms such as 'speech synthesis', 'generate speech', or 'spoken audio' to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	'Text-to-speech models, voices, formats, and streaming via Venice.ai' names the domain clearly and touches on capabilities (streaming, formats), but these are enumerated nouns rather than concrete actions — it never says what the skill does (e.g., generate speech, list voices). This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') rather than anchor 4's list of several specific actions.	3 / 5
Completeness	The 'what' is reasonably clear (TTS models, voices, formats, streaming via Venice.ai) and 'Useful for narration, voiceover, and conversational agent voices' is an explicit equivalent of a 'use when' clause, so it clears the cap at 3. The 'when' could still be more specific (e.g., 'Use when the user wants spoken audio...'), matching anchor 4 rather than 5.	4 / 5
Trigger Term Quality	The triggers 'tts', 'text to speech', 'voiceover', and 'narration' are phrases users would naturally say, and 'venice speech' covers the brand angle. Common synonyms like 'speech synthesis', 'generate speech', or 'spoken audio' are missing, so it falls just short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The Venice.ai TTS niche is clear and unlikely to trigger for unrelated skills, though 'narration', 'voiceover', and 'conversational agent voices' carry minor overlap risk with other audio or voice-related skills. This is 'mostly distinct; minor overlap risk' (anchor 4) rather than a fully conflict-free niche.	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: 1b47e60

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.