Shot Prompt Builder for ChatGPT: Write Framing, Motion, and Lighting
Convert scene beats into individual image or video prompts. Describe camera position, movement, material texture, and light for each shot before testing in a generator.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download experiments/agent-evals/control-news-lane/.content-machine/skills/shot-prompt-builder/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for shot-prompt-builder together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that shot-prompt-builder appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
A fictional short has a wide shot of a mobile library entering a village after rain, then a close-up of a book passed off a wooden shelf. Give one prompt and purpose for each shot.What to check
The wide shot establishes place and movement. The close-up emphasizes hands, paper, and light. Both retain time-of-day continuity while serving distinct editorial purposes.
Original SKILL.md on GitHub · Updated
Frequently asked question
Should every shot share the same style prefix?
Write the action and framing for each shot first. Put shared color and mood in a short continuity note and use individual details where they matter.