mcpField
G
generative-media-director

generative-media-director

github.com/frankxaiCreative & media85109 installsUpdated 2w ago
Repository

About generative-media-director

A workflow skill for directing generated images and video, from defining the creative task to provider selection, finishing, and QA. It helps creators shape prompts and deliver channel-ready media.

Key features

  1. 01Creative brief and source planning
  2. 02Image and video prompt templates
  3. 03Provider routing guidance
  4. 04Captions and format variants
  5. 05Media QA and provenance

Use cases

  1. 01Planning generated video for a campaign
  2. 02Selecting a provider for a media task
  3. 03Preparing social or ad variants

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/frankxai/awesome-motion-design-agent-skills --skill generative-media-director

After installing, type/generative-media-directorin Claude Code to confirm it loaded.

Details

From the project README

Generative Media Director

Workflow

  1. Define the job:

    • audience
    • surface
    • output format
    • desired viewer action
    • brand role

  2. Decide the source of truth:

    • product UI: code and browser capture
    • static visual direction: imagegen/GPT Image
    • cinematic generated clip: Sora, Grok, Veo, Luma, Runway, or Higgsfield
    • exact typography/layout/video package: Remotion
    • export/compression: ffmpeg

  3. Write the still-frame prompt before the video prompt.

  4. Generate or select style frames.

  5. Write the video prompt:

    • source frame
    • camera
    • subject motion
    • environmental motion
    • audio
    • beginning/middle/end
    • constraints

  6. Route providers:

    • Sora for OpenAI-first cinematic video and image-to-video.
    • Veo for high-fidelity controlled video, native audio, first/last-frame workflows.
    • Grok Imagine for fast social/audio-synced clips and stylized tests.
    • Luma for cinematic exploration and creative-agent workflows.
    • Runway for production editing and existing-video transformation.
    • Higgsfield for creator/social/ad variants.
    • Remotion for final deterministic finishing.

  7. Finish:

    • captions
    • title cards
    • logo lockups
    • CTA
    • aspect-ratio variants
    • GIF/MP4/WebM exports

  8. QA:

    • first frame works as still
    • crop works on target channels
    • text is readable
    • loop resolves cleanly
    • audio is intentional
    • file size is acceptable
    • provenance is complete

Image Prompt Shape

Use case:
Asset type:
Primary request:
Input images:
Scene/backdrop:
Subject:
Style/medium:
Composition/framing:
Lighting/mood:
Color palette:
Materials/textures:
Text (verbatim):
Constraints:
Avoid:

Video Prompt Shape

Output:
Aspect ratio:
Duration:
Provider candidates:
Source frame:
Subject:
Setting:
Camera:
Subject motion:
Environmental motion:
Audio:
Beginning:
Middle:
End:
Style:
Constraints:
Avoid:

Output Shape

Return:

  • creative diagnosis
  • recommended workflow
  • provider routing
  • still-frame prompt
  • video prompt
  • finishing plan
  • QA checklist
  • provenance template

Comments

Markdown supported