Prompt Translator (Cross-Model AI Video Prompts)

Converts an AI video prompt from one model's writing style into the target model's best-practice format (Sora, Kling, Veo, Wan, Hailuo and more).

Image & VideoIntermediate★ 382⑂ 91AI score 9/10Last updated: Jun 1, 2026

What it does

Rewrites an AI video prompt from a source model's style into the target model's optimal format.
Instead of guessing, it performs table-lookup in-context learning against a bundled benchmark of 110 paired prompts (10 scenes × 11 models) in prompts/data/cross-model-matrix.json.
Five-step workflow: collect input → strip style and extract semantics (subject, scene, motion, mood, camera, audio, dialogue, style) → find the closest benchmark scene → translate using the paired pattern → validate format and output.
Enforces hard label constraints per model: Kling 3.0 needs Scene/Characters/Action/Camera/Audio & Style/Negative, Sora 2 needs Style/Cinematography/Actions/Background Sound/Dialogue, Wan 2.7 needs Entity/Scene/Motion/Sound, Pika always needs no morphing.
Ships with a field mapping table, capability-gap warnings between models, and recommended aspect ratio / duration / resolution.

Who it's for

Creators juggling multiple AI video platforms who want to run the same idea on several models
Teams migrating prompt libraries when a model is deprecated or repriced
Marketers and editors running cross-model A/B tests for ads and short-form video

Examples

Sora 2 → Kling 3.0: layered Style:/Cinematography:/Actions: prompt is restructured into Kling's five blocks, with dialogue folded into the Action paragraph.
Wan 2.7 → Hailuo 02: the four-block structure is compressed into Hailuo's restrained 1–3 sentence prose.
Chinese Kling prompt → English Pika 2.5: single-focus rule applied plus a mandatory Negative: no morphing.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/cclank/lanshu-awesome-ai-video-kit/HEAD/skills/prompt-translator/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/prompt-translator folder from the GitHub repo cclank/lanshu-awesome-ai-video-kit into my ~/.claude/skills/prompt-translator/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/cclank/lanshu-awesome-ai-video-kit.git && mkdir -p ~/.claude/skills && cp -r lanshu-awesome-ai-video-kit/skills/prompt-translator ~/.claude/skills/ && cp -r lanshu-awesome-ai-video-kit/prompts ~/.claude/skills/prompt-translator/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal.
Clone the repository: git clone https://github.com/cclank/lanshu-awesome-ai-video-kit.git
Create the skills folder: mkdir -p ~/.claude/skills
Copy the skill: cp -r lanshu-awesome-ai-video-kit/skills/prompt-translator ~/.claude/skills/
Important: the skill depends on the benchmark data, so also run cp -r lanshu-awesome-ai-video-kit/prompts ~/.claude/skills/prompt-translator/ so prompts/data/cross-model-matrix.json is available.
Restart Claude Code and ask something like "convert this Sora 2 prompt to Kling 3.0" — always supply the source model, the original prompt, and the target model.

View source on GitHub ↗License: MIT