venice-video

Video generation and transcription workflows via the Venice.ai API.

Quality

53%

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-video/SKILL.md

Quality

Content

57%

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 concise, well-structured catalogue pointer that cleanly routes to the upstream bundle, so conciseness and progressive disclosure are strong. Its weakness is actionability: it provides no concrete install steps, punting the real workflow to an external README.

Suggestions

Replace the `open https://...` placeholder with concrete install commands (e.g. git clone path and the target skills directory) or at minimum link directly to the upstream README.

Add an explicit invoke example showing a trigger phrase or the `venice-video` name in use so the workflow is copy-paste ready.

If the bundle ships scripts/references, mirror their paths here so the agent can act without an extra round-trip to GitHub.

Dimension	Reasoning	Score
Conciseness	The body is lean (under 30 lines), assumes Claude's competence, and does not explain background concepts; the only mild redundancy is 'What it does' repeating the description, which still earns the 'lean and efficient' anchor 3.	3 / 3
Actionability	The sole command is `open https://github.com/veniceai/skills` (opens a URL), while the actual install is deferred to 'Inspect the upstream README for exact paths', so it describes rather than instructs, matching the 'vague or abstract; describes rather than instructs' anchor.	1 / 3
Workflow Clarity	A loose sequence exists (inspect upstream -> install bundle -> invoke by name/trigger), but the critical install step is undefined and there are no validation checkpoints, fitting the 'steps listed but validation gaps' anchor rather than anchor 1 (no sequence) or 3 (explicit checkpoints).	2 / 3
Progressive Disclosure	The skill is under 50 lines with well-organized sections (What it does, Source, How to use) and a single one-level reference to the upstream repo; per the scoring notes simple skills with clear organization can score 3.	3 / 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 clearly identifies the Venice.ai video/transcription niche but stops at naming workflows without concrete actions, natural trigger phrasing, or an explicit 'Use when' clause. It is adequate but generic, capping most dimensions at the midpoint.

Suggestions

Add concrete actions, e.g. 'Generate video clips from text prompts and transcribe audio/video files via the Venice.ai API.'

Append an explicit trigger clause such as 'Use when the user asks to generate video with Venice.ai or transcribe audio.'

Include natural user phrasings (e.g. 'venice video', 'transcribe audio') so trigger_term_quality and distinctiveness improve.

Dimension	Reasoning	Score
Specificity	Names the domain ('Video generation and transcription workflows') and the API ('Venice.ai API'), but does not list concrete actions like generating video from a prompt or transcribing an audio file, matching the 'names domain and some actions' anchor rather than the multi-action anchor 3.	2 / 3
Completeness	It states what the skill does but provides no explicit 'when should Claude use it' clause; per the judging guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	The description includes relevant keywords ('Video generation', 'transcription') but misses common natural variations a user would say and has no 'Use when' phrasing, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The Venice.ai tie gives it a niche, but bundling two unrelated domains (video generation and transcription) means it could still overlap with other video or transcription skills, matching the 'somewhat specific but could still overlap' anchor rather than the clearly-distinct anchor 3.	2 / 3
	Total	8 / 12 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-video/SKILL.md
Commit: a2ba3ee

Reviewed: 1 day 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.