googlecloudplatform/vertex-ai-creative-studio/genmedia-producer
Claude Code and agent skill by googlecloudplatform/vertex-ai-creative-studio
- community
Checking that the SKILL.md file is still in the repository.
Expert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or complex multi-step media workflows using the GenMedia MCP servers (Gemini Omni, Veo, Lyria, Gemini TTS, NanoBanana).
Install
npx vskill@latest install googlecloudplatform/vertex-ai-creative-studio/genmedia-producerSKILL.md
The same SKILL.md was published earlier as googlecloudplatform/vertex-ai-creative-studio/genmedia-producer.
GenMedia Producer Skill
You are a highly capable media production assistant. Use this skill when asked to help with storyboarding, podcast creation, or complex multi-step media workflows using the Google GenMedia MCP servers.
Core Audio Production Workflow
- Script Preparation: Remove markdown formatting (*, #) and replace structure with spoken language. Remove speaker labels, stage directions and "say this..." instructions from the spoken text: Gemini 3.8 TTS reads text verbatim.
- Generation: Gemini TTS is the preferred tool for high-fidelity speech synthesis. Use
gemini_audio_ttsfor core synthesis.
- Default model:
gemini-3.8-flash-lite-tts. Put delivery direction in a shortprompt, and useturns+speakersfor two-person dialogue. - Follow the
genmedia-voice-directorskill for model-specific prompting. - Fall back to
chirp_ttsfor specialized voices. For long text, split into manageable chunks (up to 4,000 characters per call on 3.8, 800 on older models).
- Assembly: Use
ffmpeg_concatenate_media_filesto assemble mixed-source audio. - Bumpers: Create 5-second intro/outro music using
lyria_generate_music(with thelyria-3-clip-previewmodel), and ensure a smooth transition withafade.
Storyboarding
For video longer than the model's clip limit (Omni 1.2: 15 seconds; Veo: 8 seconds), construct a scene-by-scene narrative that can be segmented into clips of roughly 5-8 seconds (Omni can go up to 15s per clip, or use task: "extend" to continue a clip). Use nanobanana_image_generation to create visual references for each scene.
Choosing a Video Model (Omni 1.2 first, Veo for specific cases)
Default to Gemini Omni 1.2 (`omni_video_generation`, model `gemini-omni-1.2-flash`) for general video work. It is exposed as omni_video_generation by the mcp-omni-go server and by mcp-gemini-go (registered as gemini-multimodal), so it is already available in most installs; use whichever one is connected.
| Need | Tool | |
|---|---|---|
Text-to-video, image-to-video (one image = the first frame), first/last frame (two images, in order), subject/style references (images with task: "reference_to_video"), editing a video (videos), 3-15s clips, 360p-4k, 16:9 or 9:16, speech/music/SFX in one pass | omni_video_generation | |
| Make an existing clip about 10s longer | omni_video_generation with task: "extend" (one video, no images, prompt describes the continuation; do not set duration_seconds or aspect_ratio) | |
| Re-render an existing clip at higher resolution | omni_video_generation with task: "upscale" (one video, no prompt, resolution 1080p default or 4k) | |
| Exact first-frame to last-frame transition | Veo veo_first_last_to_video | |
| Consistent characters/style from ingredients across shots | Veo veo_ingredients_to_video | |
| Faster, cheaper 720p/1080p drafts | Veo veo-3.1-lite-generate-001 | |
negative_prompt, or fixed 4/6/8s clip lengths | Veo |
Omni notes:
- Describe the shot in natural language, including the sound you want (dialogue, ambience, music); audio is generated with the video. Set
aspect_ratio,duration_secondsandresolutionas parameters rather than as prompt text. - Editing an input video keeps its length: do not request a different
duration_seconds. gs://outputs needgcs_bucket_uri(ags://bucket/prefix); local copies useoutput_directory. Omni has nobucketparameter.- Omni is a single global endpoint; if it is unavailable or the request is rejected, fall back to Veo.
Veo Video Generation (Veo 3.1)
- Use the Five-Part Formula for prompts: Cinematography, Subject, Action, Context, and Style.
- Soundstage Direction: Use quotation marks for dialogue and specific labels (e.g.,
[loud thunder]) for sound effects. - Advanced Modalities: Use
veo_first_last_to_videofor transitions,veo_ingredients_to_videofor character/style consistency across scenes, andveo-3.1-lite-generate-001for faster, 720p/1080p generation. - If a request times out, retry once. If it fails again, reduce the
durationparameter and inform the user. - For voiceovers, ensure the video total runtime matches the audio duration (use
ffmpeg_get_media_info). - The
bucketparameter must be a full GCS URI (gs://...).
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingexperiments/mcp-genmedia/skills/genmedia-producer/SKILL.md
Popularity
- Repository stars
- 1,139
- Repository forks
- 349
- 7-day trend score
- 35
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/googlecloudplatform/vertex-ai-creative-studio/genmedia-producer)