Menu

Individual skill

seedance-prompt-library

0upvotes

Verified prompt templates and structures for Seedance 2.5 / 2.0 video generation, distilled from the highest-performing published cases on goodcase.ai. Use when the user asks to write, revise, or review a Seedance video prompt, or asks how to prompt Seedance for a specific kind of shot (narrative short, ad/commercial, UGC talk-to-camera, dialogue with lip-sync, action, product reveal, retro home video, travel film, pet or animal lead, comedy skit, horror, fantasy or sci-fi spectacle, 3D cartoon, car spot, fashion film, sports, storyboard image to video, and similar). Also use when the user names Seedance, 即梦视频, or Seedance 2.5/2.0 directly.

agents/skills/seedance-prompt-library/SKILL.md

Read pinned source

Source commit e4a70e7a1e2d2fc8aba9ec6a85ff1360f3f42404

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
2,482
Repository last updated
Nov 7, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Seedance Prompt Library

A structured template library for writing Seedance 2.5 / 2.0 video prompts, sourced from `references/style-library.md` — templates distilled from real, human-verified, high-heat cases on [goodcase.ai](https://goodcase.ai). Do not invent prompt structure from general video-generation knowledge when a matching template exists here; use the template.

## Workflow

1. **Identify intent.** Work out what kind of shot the user wants: narrative short, ad/commercial, UGC talk-to-camera, dialogue with lip-sync, action/movement, product reveal, retro found footage, travel, pets and animals, comedy, horror, fantasy or sci-fi spectacle, 3D cartoon, cars, fashion and portrait, sports, storyboard grid to video, or something else. The reference file lists every template with its `useWhen`; skim those headings first. Ask a clarifying question only if the intent is genuinely ambiguous (e.g. "a video of my product" could be a commercial orbit shot or a UGC review — ask which).

2. **Select a template.** Read `references/style-library.md` and pick the template whose `useWhen` matches the identified intent. If no template matches closely, say so and build the prompt from first principles instead of forcing a mismatched template.

3. **Fill the structure.** Walk the template's `structure` field block by block (shot type, subject, setting, camera behavior, etc.) and fill each with specifics from the user's request. Don't skip blocks — an empty block in the structure is where prompts usually go generic and vague.

4. **Apply guidance, avoid pitfalls.** Cross-check the draft against the template's `guidance` and `pitfalls` lists before finalizing. These come from what actually worked (or broke) in real published cases, not general advice.