OpenSkillIndex← back to search
claude-codeautomation

Claude-code-plugins-plus-skills vertex-ai-media-master

install
source · Clone the upstream repo
git clone https://github.com/jeremylongshore/claude-code-plugins-plus-skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/jeremylongshore/claude-code-plugins-plus-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/productivity/003-jeremy-vertex-ai-media-master/skills/vertex-ai-media-master" ~/.claude/skills/jeremylongshore-claude-code-plugins-plus-skills-vertex-ai-media-master-ce9d31 && rm -rf "$T"
manifest: plugins/productivity/003-jeremy-vertex-ai-media-master/skills/vertex-ai-media-master/SKILL.md
tags
#vertex-ai#media-generation#video-analysis#audio-creation#image-generation#campaign-automation
source content

Vertex AI Media Master

Overview

Multimodal media operations on Google Cloud Vertex AI covering video understanding, audio generation, image creation, and marketing campaign automation. This skill orchestrates Gemini 2.5 Pro/Flash, Imagen 4, and Lyria models to process, analyze, and generate rich media assets.

Prerequisites

  • Google Cloud project with Vertex AI API enabled
  • google-cloud-aiplatform
    Python SDK installed (
    pip install google-cloud-aiplatform[vision,audio]
    )
  • GOOGLE_CLOUD_PROJECT
    and 
    GOOGLE_APPLICATION_CREDENTIALS
    environment variables set
  • Service account with 
    roles/aiplatform.user
    permission
  • Sufficient quota for target models (Gemini 2.5 Pro: 2M tokens/min; Imagen 4: 100 images/min)

Instructions

  1. Initialize the Vertex AI client with the target project and region (
    us-central1
    recommended for model availability).
  2. Select the appropriate model for the task:
    • Video analysis: Gemini 2.5 Pro (up to 6 hours at low resolution, 2 hours at default).
    • Image generation: Imagen 4 for highest quality stills; Gemini 2.5 Flash Image for interleaved text+image output.
    • Audio generation: Lyria for music composition and background tracks.
    • Campaign automation: Gemini 2.5 Pro for multi-asset generation from a single prompt.
  3. Prepare input media: upload source files to Cloud Storage (
    gs://
    URIs) or provide local paths for smaller assets.
  4. Construct the generation request with explicit parameters (aspect ratio, duration, number of outputs, style constraints).
  5. Execute the request and capture response objects containing generated media bytes or analysis text.
  6. Post-process outputs: save generated images/audio to the target directory, extract structured insights from video analysis, or compile campaign asset bundles.
  7. Validate results against brand guidelines or schema expectations before delivery.

Output

  • Generated image files (PNG/JPEG) from Imagen 4 or Gemini Flash Image
  • Audio files (WAV/MP3) from Lyria model for background music, voiceovers, or sound effects
  • Video analysis reports: scene breakdowns, key-moment timestamps, transcript text, marketing-insight summaries
  • Campaign asset packages: hero images, social media graphics, ad copy, email marketing text, and video scripts
  • Structured JSON metadata for each generated asset (model used, prompt, parameters, cost estimate)

Error Handling

ErrorCauseSolution
PermissionDenied
on Vertex AI API		Service account lacks 
aiplatform.user
role		Grant the required IAM role to the service account
ResourceExhausted
/ quota exceeded		Too many concurrent requests or token limit hitImplement request batching; switch to Gemini 2.5 Flash for lower-cost operations
InvalidArgument
on image generation		Prompt violates safety filters or unsupported aspect ratioRevise the prompt to remove restricted content; use a supported aspect ratio (1:1, 16:9, 9:16)
Video processing timeoutSource video exceeds duration or resolution limitsUse low-resolution mode for videos over 2 hours; split longer videos into segments
Audio generation returns emptyPrompt too vague or duration parameter missingSpecify genre, tempo, mood, and an explicit duration in seconds
NotFound
on model ID		Incorrect model name or model not available in regionVerify the model ID against current Vertex AI documentation; try 
us-central1

Examples

Example 1: Analyze a competitor video ad

  • Input: A 60-second competitor video uploaded to 
    gs://bucket/competitor-ad.mp4
    .
  • Action: Send to Gemini 2.5 Pro with the prompt "Extract messaging themes, calls to action, visual style, and production techniques."
  • Output: Structured analysis with timestamps for key scenes, identified CTAs, and a competitive positioning summary.

Example 2: Generate campaign assets from a product brief

  • Input: Text brief describing a new product launch with target audience and brand guidelines.
  • Action: Use Imagen 4 to generate 4 hero image variations, Lyria for a 30-second background track, and Gemini 2.5 Pro for ad copy in 3 languages.
  • Output: Directory containing hero images, audio file, and a campaign-copy document organized by language.

Example 3: Repurpose a long-form video into short-form clips

  • Input: A 10-minute product demo video.
  • Action: Gemini 2.5 Pro identifies the three most engaging 15-second segments with scene-boundary timestamps.
  • Output: Timestamp list with suggested captions for TikTok/Reels, plus a storyboard summary for each clip.

Resources