Yummy Gen Video

v1.1.0

Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-...

0· 101·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for yummysource/yummy-gen-video.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Yummy Gen Video" (yummysource/yummy-gen-video) from ClawHub.
Skill page: https://clawhub.ai/yummysource/yummy-gen-video
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: yummycli
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install yummy-gen-video

ClawHub CLI

Package manager switcher

npx clawhub@latest install yummy-gen-video
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
Name/description (Gemini Veo video generation) align with required binary (yummycli) and primary credential (GEMINI_API_KEY). The declared dependency on a related skill (yummy-shared) is plausible for shared configuration.
Instruction Scope
SKILL.md contains concrete CLI usage (yummycli gemini veo), flag mappings, model/resolution/duration rules, and output parsing. It instructs reading local input images and the tool's JSON stdout — actions coherent with video generation. I found no instructions to read unrelated system files or exfiltrate data.
Install Mechanism
The skill declares a node install of @yummysource/yummycli (npm). This is a common delivery but carries moderate risk: npm packages can include install scripts and arbitrary code. No direct URL downloads or extract-from-unknown-host behavior is present, but you should verify the npm package and publisher before installing.
Credentials
Only GEMINI_API_KEY is declared as the primary credential — consistent with calling Gemini via yummycli. No unrelated secrets, config paths, or excessive env requirements are requested.
Persistence & Privilege
always is false and the skill is instruction-only. There is no request for permanent platform-wide privileges or modifications of other skills' configurations.
Assessment
This skill appears to do what it says: run yummycli to generate videos via Gemini Veo. Before installing or enabling it, verify the npm package @yummysource/yummycli and its publisher (review the package page, recent releases, and any install scripts). Limit the GEMINI_API_KEY scope/permissions you provide (use a key scoped only to generation if possible). Be cautious when allowing the skill to access local image files (it will read any input-image paths you provide). If you rely on the related yummy-shared skill, review that skill too. If you want stronger assurance, ask the publisher for source or a vetted distribution (GitHub repo or official homepage) before installing.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

Binsyummycli
Primary envGEMINI_API_KEY
latestvk975mzf40fxk9dggdtn63w3c6x850hwh
101downloads
0stars
1versions
Updated 1w ago
v1.1.0
MIT-0

Generate Video

Create videos with yummycli gemini veo using Google Veo.

When to Use

Load this skill when the user asks to generate, create, or animate a video using AI — including text-to-video, animating a still image, or generating a video guided by reference images.

Prerequisite: Apply the yummy-shared skill first.

This skill covers three generation modes with a single command:

  • Text-to-video (no images)
  • Image-to-video (one starting frame)
  • Reference-guided video (two or three reference images)

Command Contract

Two equivalent entry points are available:

Entry pointWhen to use
yummycli gemini veoDefault — human-friendly, Gemini Veo presets applied
yummycli video generate --provider geminiScripting / automation — explicit, provider-agnostic form

Both share the same flags and defaults. Prefer gemini veo unless the task explicitly requires the provider-agnostic form.

Basic usage:

yummycli gemini veo --prompt "<prompt>"

With one or more input images:

yummycli gemini veo \
  --prompt "<prompt>" \
  --input-image ./frame.png \
  --input-image ./style.jpg

Optional output controls:

--output <file.mp4>
--model <model>
--aspect-ratio <ratio>
--duration <seconds>
--resolution <resolution>

Default values when omitted: --model veo-3.1-fast-generate-preview, --aspect-ratio 16:9, --duration 8, --resolution 1080p.

Image Routing Rules

The number of --input-image flags determines the API path automatically:

CountBehaviour
0Text-to-video. Prompt drives the entire generation.
1Image-to-video. The image is used as the starting frame.
2–3Reference-guided. Images are passed as ASSET reference images; the prompt describes the motion and content.

Never pass more than 3 --input-image flags — the API rejects it.

Model Selection

Default model: veo-3.1-fast-generate-preview.

Use the following mapping when the user explicitly names a model variant:

User saysUse
veo 3.1, 3.1 fast, or no preferenceveo-3.1-fast-generate-preview (default)
veo 3.1 full or veo 3.1 standardveo-3.1-generate-preview
veo 3, veo 3 fastveo-3.0-fast-generate-001
veo 3 standardveo-3.0-generate-001
veo 2veo-2.0-generate-001

Do not switch models from vague quality words alone. Only apply a mapping when the user's wording clearly refers to model choice.

Model Compatibility

Supported duration values (seconds)

Duration accepts only discrete values — not a range.

ModelValid durations
veo-2.0-generate-0015, 6, 7, 8
veo-3.0-*4, 6, 8
veo-3.1-*4, 6, 8

Supported resolutions

ModelSupported resolutions
veo-2.0-generate-001720p only
veo-3.0-*720p, 1080p
veo-3.1-*720p, 1080p, 4k

Constraints:

  • 1080p requires --duration 8.
  • 4k requires --duration 8 and a veo-3.1 model.

Supported aspect ratios

All models: 16:9 (landscape) and 9:16 (portrait).

Intent to Parameters

Translate clear user intent into CLI flags when the mapping is obvious.

Aspect ratio guidance:

  • Use --aspect-ratio 9:16 for vertical/portrait outputs: phone wallpaper, short-form vertical video, story format.
  • Use --aspect-ratio 16:9 for landscape outputs: film, presentation, widescreen. This is the default.
  • If the user already specifies a ratio, pass it through directly.

Duration guidance:

  • Use the longest valid duration for the model unless the user requests shorter.
  • If the user says "short clip" or "quick", use --duration 4 (veo-3+) or --duration 5 (veo-2).
  • Never pass a duration that is not in the valid set for the selected model.

Resolution guidance:

  • Default (1080p) is appropriate for most requests.
  • Use --resolution 4k only when the user explicitly asks for 4K quality and a veo-3.1 model is in use; pair with --duration 8.
  • Use --resolution 720p when the user asks for a smaller or faster result.

Output path guidance:

  • If --output is omitted, yummycli generates a timestamped .mp4 filename in the current working directory. Do not invent your own filename unless the user provides one.
  • The output path must end in .mp4. Reject or correct any other extension.

Output Contract

Video commands return JSON on stdout. Read the response and use the output field as the generated file path.

Example (text-to-video):

{
  "provider": "gemini",
  "output": "veo_20260417_142301_047.mp4",
  "model": "veo-3.1-fast-generate-preview",
  "duration_seconds": 8,
  "aspect_ratio": "16:9",
  "resolution": "1080p",
  "elapsed_seconds": 73
}

Example (image-to-video, one starting frame):

{
  "provider": "gemini",
  "output": "veo_20260417_143010_112.mp4",
  "model": "veo-3.1-fast-generate-preview",
  "duration_seconds": 8,
  "aspect_ratio": "16:9",
  "resolution": "1080p",
  "elapsed_seconds": 89,
  "input_images": ["./dog.jpg"]
}

Execution Rules

  • Check yummycli auth status --provider gemini before running if credentials may not be configured.
  • Use one --input-image flag per local image file; preserve the user-specified order.
  • Validate duration and resolution against the selected model's constraints before running.
  • Video generation is slow (typically 45–120 seconds). Inform the user that generation is in progress; do not treat a long wait as an error.
  • If the command returns a validation error (bad duration, unsupported resolution, missing file), fix the arguments before retrying. Do not retry with the same invalid arguments.
  • Report the final output path back to the user after a successful run.

Examples

Text-to-video:

yummycli gemini veo \
  --prompt "A golden retriever puppy chasing a red ball in a sunny park"

Image-to-video (animate a still):

yummycli gemini veo \
  --prompt "The dog starts running toward the camera" \
  --input-image ./dog.jpg

Reference-guided (two images):

yummycli gemini veo \
  --prompt "Combine the character from the first image with the environment from the second" \
  --input-image ./character.png \
  --input-image ./background.jpg

Short portrait clip with veo-2:

yummycli gemini veo \
  --prompt "Falling cherry blossoms in slow motion" \
  --model veo-2.0-generate-001 \
  --aspect-ratio 9:16 \
  --duration 5 \
  --resolution 720p

4K landscape with veo-3.1:

yummycli gemini veo \
  --prompt "Timelapse of clouds moving over mountain peaks at golden hour" \
  --resolution 4k \
  --duration 8

Comments

Loading comments...