Skip to the usage guide
Genmedia Video Editorby GoogleCloudPlatform

Genmedia Video Editor Skill.

Coordinate Veo generation and AVTool video composition through MCP.

  • Video Editing
  • Genmedia
Source Review · genmedia-video-editorSKILL.md
Task Coordinate Veo generation and AVTool video composition through MCP. Produces A generated or composited video through the configured MCP tools. Before You Start The listed Veo and AVTool tools, credentials and provider access must exist in the host.
Editorial summary · source reviewed 2026-11-02 · not a generated example

01 What It Does

Coordinate Veo generation and AVTool video composition through MCP

Explore Veo and AVTool workflows for video generation, image overlays, clip joining, GIF conversion and checked audio mixing.

Source-based workflowNot an execution benchmark

The Working Approach

genmedia-video-editor combines generative video and post-production through the Veo and AVTool MCP services. Its documented tasks include generating a clip, placing a logo over footage, joining clips, making a GIF and mixing audio with video. Media metadata is checked before coordinates, durations or filters are chosen.

The generation guidance describes a shot through cinematography, subject, action, context and style. Reference-image and first/last-frame routes are also listed. Those operations depend on the configured services and current model availability; the Skill is an orchestration guide rather than an independent video editor.

Expected Deliverables

  • A generated or composited video through the configured MCP tools.
  • A joined clip, image overlay or GIF when requested.
  • An audio/video composition with explicitly considered durations and levels.
See the Example Brief

From Brief to Review

  1. 01
    Inspect the media

    Read dimensions, frame rate and duration before overlaying, concatenating or adding audio. Identify the requested generation or editing operation.

  2. 02
    Select the service operation

    Use the relevant Veo mode for generation or the AVTool operation for post-production. Express camera, action and context clearly when drafting the shot.

  3. 03
    Verify the combined result

    Check framing, timing and sound after processing. If clips differ in dimensions or frame rate, account for their standardization before joining them.

02 When to Use It

When to Use It

The listed Veo and AVTool tools, credentials and provider access must exist in the host.

A Good Fit

  • Generation needs simple finishingUse it when an AI-generated clip also needs a logo, soundtrack or a joined sequence.
  • Several media operations share one tool environmentThe source gives a coordinated route through named MCP capabilities.

Limits to Check

  • Configured services are requiredThe listed Veo and AVTool tools, credentials and provider access must exist in the host.
  • Model details are time-sensitiveThe source names specific Veo models and modes; confirm their current availability before promising an operation.
  • Audio may be mixed rather than replacedThe documented combine operation retains existing audio and mixes the new track unless levels are adjusted.

Bring These Inputs

  • Media assetsProvide source clips, overlay images and any soundtrack or narration.
  • Shot or edit intentDescribe the generation prompt or the exact post-production change.
  • Output targetSpecify dimensions, format, audio balance and any timing constraints.

03 Decisions That Matter

Decisions That Matter

  1. Metadata-led placement

    Overlay coordinates are calculated from actual video dimensions.

  2. Coordinated finishing

    Generation and FFmpeg-based operations can be planned in one workflow.

  3. Explicit audio handling

    Checking durations and levels reduces accidental overlaps or unwanted source audio.

04 Try a Focused Brief

Try a Focused Brief

The example brief below has not been tested. Check the skill’s setup before using it.

Review the Source and Setup

Provide source clips, overlay images and any soundtrack or narration.

Upstream Source File
https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/blob/0ed98d58d53a648bc0c49c9135cb2fbd2292f8e2/experiments/mcp-genmedia/skills/genmedia-video-editor/SKILL.md

The reference below opens the upstream instructions. Review the repository setup before using them; it is not an installation command.

Start With One Deliverable

Adapt the scope, source material and constraints in this brief before running the skill.

Example Brief
Use genmedia-video-editor with the configured tools to finish my supplied product clip. Inspect its dimensions, frame rate, duration and existing audio first. Place the supplied transparent logo inside the lower-right safe margin without stretching it, then add the provided narration at an intelligible level. Preserve the original ambient sound only if it does not compete with the voice. Deliver an H.264 MP4 and a small preview GIF. Check the complete result for logo clipping, audio balance and duration mismatch. Do not generate replacement footage or invoke a paid model for this editing-only task.

Inspect the Result

Check the actual output against these observable criteria.

  • Inspect source metadata before calculating positions or joining clips.
  • Check mixed audio for unwanted overlap and level imbalance.
  • Verify final framing, duration, playback and requested format.

OpenDesign provides a local design workspace for coding agents. This listing does not mean the skill is bundled or that its external tools, credentials and software dependencies are included.

05 Source and License

Source and License

This page describes the pinned source revision linked below. Upstream behavior and requirements can change.

Skill File
SKILL.md
License
Apache-2.0
Reviewed Snapshot
2026-11-02 · 0ed98d58d53a
Editorial Source Summary
Coordinate Veo generation and AVTool video composition through MCP.

Original summary by OpenDesign, based on the linked source. Repository stars are a dated popularity signal, not skill usage or a quality score.

06 Questions Before You Start

Questions Before You Start

Does it require Veo for every task?

No. The source separates video generation from AVTool editing operations such as overlays, concatenation, GIF conversion and audio combination.

What happens to existing audio?

The documented combine tool mixes it with the incoming track. Volume parameters should be considered if the source sound needs reduction.

Can clips with different formats be joined?

The source expects matching dimensions and frame rates, or a standardization pass. The final output still needs inspection after that conversion.

OpenDesign

Keep Your Brief and Design Work Together.

Keep your brief, source material and design work together in a local workspace. Check the skill’s own setup before adding it to your workflow.

Upstream Source File
https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/blob/0ed98d58d53a648bc0c49c9135cb2fbd2292f8e2/experiments/mcp-genmedia/skills/genmedia-video-editor/SKILL.md