Kling 3 Prompting

This is an interactive prompt builder for Kling 3.0 video generation that walks you through crafting better prompts by asking questions about scene details, camera movement, lighting, and audio. Instead of treating prompts like keyword lists, it pushes you toward cinematic direction with specific techniques like dolly zooms, rack focus, and named light sources. Works across text-to-video, image-to-video, keyframe transitions, and multi-shot sequences up to 15 seconds. The strength here is the reference tables for camera movements, lens choices, and lighting specifics that produce better results than vague descriptors. Use it when you're stuck translating a video idea into something Kling will actually understand, or when your outputs feel generic and you need more precise control.

skills.sh installs: 618
GitHub stars: 29
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aedev-tools/kling-3-prompting-skill --skill kling-3-prompting --agent claude-code

Installs into .claude/skills of the current project.

Files

Overview

Kling 3.0 is a unified multimodal video model. It understands cinematic direction, not keyword lists. Write prompts like a director — describe what the audience sees, hears, and feels over time.

Core shift: Description → Direction. Think "direct a scene" not "describe an image."

Interactive Builder Workflow

When invoked, guide the user through these steps using AskUserQuestion:

digraph builder {
  "1. Generation mode?" [shape=diamond];
  "Text-to-Video" [shape=box];
  "Image-to-Video" [shape=box];
  "Multi-Shot Sequence" [shape=box];
  "Keyframe Transition" [shape=box];
  "2. Gather scene details" [shape=box];
  "3. Assemble prompt" [shape=box];
  "4. Present & refine" [shape=box];

SKILL.md on GitHub

Details

Repository: github.com/aedev-tools/kling-3-prompting-skill
Category: Generative Media
First seen: Jun 3, 2026