CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

veo-use

Create and edit videos using Google's Veo 2 and Veo 3 models. Supports Text-to-Video, Image-to-Video, Reference-to-Video, Inpainting, and Video Extension. Available parameters: prompt, image, mask, mode, duration, aspect-ratio. Always confirm parameters with the user or explicitly state defaults before running.

Quality

82%

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

80%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 highly actionable and well-structured with externalized detail, but lacks explicit validation/verification steps for video-editing and generation operations, which caps workflow clarity. Prose lead-ins are slightly redundant but otherwise lean.

Suggestions

Add explicit validation/verification steps to destructive or quota-consuming workflows (e.g., after generation, confirm the output file exists and is a non-empty valid video; before inpainting, confirm the source video and mask before running; prompt the user to confirm parameters before paid generation).

Trim or merge the one-line prose lead-ins that restate the command's obvious purpose to improve token efficiency.

DimensionReasoningScore

Conciseness

Lean and mostly efficient with executable commands and minimal concept explanation, but the one-line prose lead-ins per section (e.g., "Generate a video starting from a static image context.") mildly restate what each command does and could be trimmed.

4 / 5

Actionability

Every usage mode ships a fully executable, copy-paste-ready `uv run` command with concrete flags, real script paths, and realistic examples covering the common cases.

5 / 5

Workflow Clarity

Each task has a clear single-command sequence, but the body shows no validation/verification checkpoints for operations that modify videos or consume paid API quota; per the rubric, missing validation in destructive/batch workflows caps workflow clarity at 3.

3 / 5

Progressive Disclosure

The body is a clear overview that externalizes detail to one well-signaled one-level-deep reference (references/prompting.md, a real file) and keeps executable code in bundled scripts/, with clean section navigation.

5 / 5

Total

17

/

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 and distinctive, naming concrete actions and parameters, but lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger-term coverage is good though not exhaustive.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user wants to generate or edit videos with Google Veo, or mentions text-to-video, image-to-video, inpainting, or video extension.') to satisfy the 'when' half of completeness.

Include a few natural synonyms/file extensions (e.g., 'mp4', 'make a video', 'animate an image') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Text-to-Video, Image-to-Video, Reference-to-Video, Inpainting, and Video Extension") plus concrete parameters ("prompt, image, mask, mode, duration, aspect-ratio"), giving comprehensive coverage.

5 / 5

Completeness

Has a clear "what" (create/edit videos via Veo with named modes and parameters) but no explicit "Use when..." trigger clause; per the rubric a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("videos", "edit videos", "Inpainting", "Video Extension"); missing a few synonyms/file extensions (e.g. "mp4", "make a video"), so good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

Targets a clearly distinct niche (Google's Veo video generation) with specific named capabilities, so it is unlikely to trigger for the wrong skill.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

cnemri/google-genai-skills

Path

skills/veo-use/SKILL.md

Revision

7277476

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill