venice-audio-music

Music generation queueing, retrieval, and completion endpoints via Venice.ai. Suited for jingles, background loops, and prototype scoring.

Quality

58%

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-music/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.

The body is a lean, well-organized catalogue stub that clearly signals where the real content lives, but it offers almost nothing executable: no install commands, a non-portable `open` command, and no usage examples of the music generation endpoints. Its value depends entirely on the external upstream repository.

Suggestions

Replace `open https://github.com/veniceai/skills` with a portable, executable command (e.g. `git clone https://github.com/veniceai/skills` or a direct `curl` of the README) so the inspect step actually runs.

Add concrete install steps for the bundle (exact copy/clone commands and target skill-directory paths) instead of the vague "install the upstream bundle into your active agent's skills directory".

Include a minimal end-to-end example of invoking the skill (e.g. a sample queue-then-retrieve music generation call) so the agent knows what executing the skill looks like.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean with no concept explanations and assumes Claude's competence, but contains minor trimmable duplication: the frontmatter description is repeated verbatim in "What it does" and the upstream URL appears in both the "Source" section and the code block. This matches "efficient; minor instances that could be trimmed" rather than the every-token-earns-its-place anchor.	4 / 5
Actionability	The instruction to "install the upstream bundle into your active agent's skills directory" provides no actual commands, and the only code block (`open https://github.com/veniceai/skills`) is a macOS-only command that is not executable in most environments; there is no example of invoking the music endpoints. This is high-level hints missing the specific steps to execute.	2 / 5
Workflow Clarity	A rough sequence is present (inspect the upstream README, install the bundle, invoke by name or trigger phrase) but the critical install step is undefined and there are no checkpoints. It sits between the poorly-defined anchor and the clear-sequence anchor, closer to "steps listed but gaps".	3 / 5
Progressive Disclosure	Sections ("What it does", "Source", "How to use") are well organized and the pointer to detailed material is clearly signaled and one level deep. However, no bundle files exist (no references/, scripts/, or assets/) and all substantive content is delegated to an external repository, leaving a minor organization gap rather than fully self-contained, well-split content.	4 / 5
	Total	13 / 20 Passed

Description

62%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 and mostly well-targeted, clearly naming the domain and three concrete actions with natural trigger phrases. Its weaknesses are the absent explicit "Use when..." guidance and the overly generic "score" trigger, which cap completeness and distinctiveness.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when the user wants AI-generated music, jingles, background loops, or soundtrack prototypes via Venice.ai."

Replace or qualify the generic trigger "score" with unambiguous terms like "music scoring" or "soundtrack" to avoid conflicts with unrelated scoring tasks.

Add common synonyms such as "song", "soundtrack", and "make music" to the trigger terms for broader natural coverage.

Dimension	Reasoning	Score
Specificity	"Music generation queueing, retrieval, and completion endpoints via Venice.ai" names the domain and several concrete actions (queueing, retrieval, completion), matching the anchor for several specific actions with minor gaps. It falls short of 5 because no endpoint, parameter, or workflow detail is given beyond the three action names.	4 / 5
Completeness	The "what" is clear (queueing/retrieval/completion endpoints via Venice.ai), but the "when" is only weakly implied by "Suited for jingles, background loops, and prototype scoring" — there is no explicit "Use when..." clause or equivalent trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	Natural phrases like "jingles", "background loops", "music gen", and "venice music" appear (in the description and frontmatter triggers), giving good keyword coverage. Missing common variations such as "song", "soundtrack", or "make music" keep it below 5.	4 / 5
Distinctiveness Conflict Risk	"Music generation via Venice.ai" is a clear niche, but the trigger term "score" is highly generic and would fire on unrelated requests (game scores, test scoring, evaluation rubrics), creating real overlap risk. This places it at "somewhat specific but could still overlap" rather than the mostly-distinct anchor.	3 / 5
	Total	14 / 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-music/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.