GC Still Image Motion Director

English · 简体中文

A Codex skill that analyzes a real still image, decides whether it should use motion, micro-motion, or remain static, and writes a restrained image-to-video prompt without breaking typography, paper texture, framing, or layout.

The callable skill name is gc-still-image-motion-director.

This skill writes motion direction and a copy-ready prompt. It does not generate the final video.

What It Does

The skill:

• reads the actual image before proposing motion;
• separates visible observations from recommendations;
• selects at most one primary action and one physically related response;
• explicitly locks text, numbers, paper, frames, grids, and composition;
• supports motion, micro-motion, and static decisions;
• adapts the final prompt to a named image-to-video platform when requested;
• diagnoses text, paper, camera, and layout drift in failed results.

It avoids stock effects such as automatic camera push-ins, floating layers, breathing paper, generic particles, and unsupported parallax.

Examples

These two supplied cases show the intended difference between motion and micro-motion.

For each case, the user supplied the source image and asked Codex to use this Skill. Codex inspected the image and generated the Chinese Seedance 2.0 prompt shown below; that prompt was then used with Seedance 2.0 to generate the linked result clip. The clips are real outputs from those runs. Generative results can vary, and a returned take may not obey every lock perfectly.

motion — CHOICE

The butterfly stays in its original focal region and completes one bounded wingbeat. The blue rectangle, envelope drawing, typography, Chinese copy, paper texture, and full composition remain fixed.

Watch the 4-second MP4 result

The source was a verified Apple Live Photo pair. This repository uses a silent MP4 derivative for browser compatibility and does not publish the Live Photo package.

micro-motion — Walk Slowly

Motion remains inside the two photo windows: light and grass shift subtly in the left image while the cloud changes gently in the right image. The path text, Chinese title, paper texture, spacing, and full layout remain fixed.

Watch the 4-second MP4 result

Installation

Clone the public repository directly into the Codex skills directory:

git clone https://github.com/LiamGvchi/gc-still-image-motion-director.git \
  ~/.codex/skills/gc-still-image-motion-director

Restart Codex if the skill does not appear immediately.

Usage

Invoke the skill with a still image:

用 $gc-still-image-motion-director 分析这张海报应该怎么动，
锁住文字和纸张，并给我一条可复制的图生视频 Prompt。

For a folder of images:

用 $gc-still-image-motion-director 分析这个图片文件夹，
分别判断哪些适合动、哪些只适合微动、哪些应该保持静止。

To repair a failed result:

用 $gc-still-image-motion-director 重写这条 Prompt：
上一版出现了文字变化、纸张呼吸和镜头漂移。

Output

For each image, the skill can return:

1. visible image observations;
2. a motion, micro-motion, or static decision;
3. one bounded primary action and an optional linked response;
4. an explicit lock list;
5. a copy-ready image-to-video prompt;
6. the main predicted failure risks.

The default is a restrained 4-second clip when no platform or duration is specified.

Repository Structure

• SKILL.md: the core workflow and output contract
• references/motion-decision-framework.md: motion suitability, amplitude, timing, and composition rules
• references/prompt-construction.md: prompt order, lock lists, negative constraints, and repair guidance
• agents/openai.yaml: Codex UI metadata
• evals/evals.json: representative trigger and non-trigger cases
• examples/: two supplied still-and-result pairs demonstrating motion and micro-motion
• LICENSE: MIT license

This repository publishes one standalone skill. It does not include private backups, unrelated user media, platform credentials, or claims that the Skill itself generated the example videos.

Compatibility Notice

This project is independent and is not affiliated with or endorsed by Jimeng or any image-to-video platform. Product names are used only to describe compatibility.

Platform behavior may change. The skill does not claim undocumented controls and falls back to a platform-neutral prompt when behavior is uncertain.

Related Skill

For quiet minimal zine-style poster generation, see GC Minimal Zine Poster.

License

MIT. See LICENSE.