lengyi-seedance2.5-prompt skill
A skill that turns an idea, theme or novel excerpt into a 30-second multi-shot prompt for the Seedance 2.5 video model.
- 139 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill writes text and runs no code; the video model is called separately.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/lengyi-seedance2-5-promptDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill writes text and runs no code; the video model is called separately.
This is third-party code. Review the repository files before installing.
What it does
The skill accepts any text: a novel excerpt, a one-line plot or a few theme words. The output has three blocks: a script overview, text-to-image prompts for anchor assets and a ready video prompt that pastes into Seedance 2.5 as one piece. The hero and scene are fixed first with separate image prompts so the look stays consistent. Then the story is split into shots with a number, a time range, framing, camera move and action. Total length is 20 to 30 seconds, and the shot count follows story rhythm, usually 8 to 14. Music is disabled in the prompt, leaving sound effects only.
Who it is for. Creators of short AI videos who write prompts for Seedance and want stable shots and pacing without hand storyboarding.
Good fit when
- A book scene should become a thirty-second clip.
- A single plot line needs a storyboard with timing.
- The hero and location must look the same in all shots.
- Work follows an image-to-video flow: references first, then the clip.
Not a fit when
- The video is made in another model, since the prompt structure is tuned to Seedance 2.5.
- A clip longer than 30 seconds is needed, since the cap is hard.
- Music inside the video is wanted, while the prompt disables it.
Example request
Make a thirty-second Seedance 2.5 storyboard from the line "A warrior's staff breaks on a mountain pass before a fight with a tiger".Limitations
The skill only writes prompt text; video and images are produced in Seedance and an image model separately. Part of the repository, including the author's notes, is in Chinese. Clip quality depends on the video model, and the 720P advice is based on the author's own experience. The author's rules such as no music and choosing 720P come from personal practice and may not fit your task. The Seedance 2.5 model may change, and prompt templates would then need an update.
How to disable. Delete the `lengyi-seedance2.5-prompt` folder from the agent's skills directory. The skill creates no files outside it.
FAQ
What does the output look like?
Three blocks: a script overview, prompts for anchor images and a video prompt with shots such as "Shot 01, 02". All of it copies as one piece.
How many shots will there be?
It depends on story rhythm. For thirty seconds it is usually 8 to 14.
How do I install the skill?
Put the folder into `<project>/.claude/skills/lengyi-seedance2.5-prompt/`. For other agents follow their skill installation guide.
Why is music disabled?
The author advises asking for sound effects only, since baked-in music complicates editing.
Are images needed to start?
Yes, the skill first writes prompts for anchor images of the hero and scene. They are generated in an image model and fed to Seedance together with the video prompt.
Discussion
No questions or reviews yet.
Related
SkillsA skill that turns a plot or scene into a cinematic AI video prompt for 6 to 30 seconds, with shots, performance and sound.
A skill that teaches an agent to write prompts for ByteDance's Jimeng Seedance 2.0 video model: @ references, camera language, timing, templates
A dialogue that turns an idea into a storyboard and a prompt for the Seedance 2.0 video model in Jimeng, with six templates and ten examples
A skill that writes structured prompts for Seedance, Kling, Veo and Sora: a home-footage look, camera flaws, a timeline and sound
A skill that improves Seedance prompts, plans storyboards and generates video through Atlas Cloud, plus a library of ready prompts
The skill breaks a sales video into a storyboard and writes a prompt pack for the Seedance video model in Jimeng.
README in short
The README explains why the skill exists, shows the output format and the workflow: images first, then video. It includes a one-line plot example and templates in `references/templates.md`.