dexhunter/seedance2-skill

skill to create best prompts for generating videos with seedance2.0

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 13 minutes ago
Added to GitGenius on September 18th, 2026
Created on February 11th, 2026
Open Issues & Pull Requests: 1 (+0)
GitHub issues: Enabled
Number of forks: 338
Total Stargazers: 3,824 (+1)
Total Subscribers: 12 (+0)

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 0
New in 7 days: 0
Closed in 7 days: 0
Avg open age: N/A days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Seedance2-skill is an agent skill that teaches AI assistants how to write effective prompts for Jimeng Seedance 2.0, ByteDance's multimodal video generation model.

The tool addresses the challenge of crafting high-quality prompts for video generation by codifying best practices from official ByteDance documentation. It works by providing structured guidance on input constraints, the @ reference syntax for incorporating external content, camera language conventions, prompt structure patterns, and domain-specific templates. The skill integrates with Claude Code, Cursor, Cline, and other compatible AI agents, allowing developers to ask their agent for help writing Seedance 2.0 prompts and receive guidance grounded in the tool's knowledge base.

Developers should adopt this skill if they are using Seedance 2.0 for video generation and want to improve prompt quality without manually studying ByteDance's documentation. It suits projects across advertising, drama production, music videos, educational content, and other video domains where structured prompt engineering matters. The skill is available in both English and Chinese, making it accessible to teams in different regions.

The project maintains documentation directly sourced from official ByteDance materials covering parameters, interaction methods, multimodal capabilities, and real-world production cases. Installation is straightforward, with a recommended manual approach of copying skill files to a Claude skills directory, alongside an alternative CLI-based installation method. The tool is distributed under the MIT license and includes ready-to-use templates tailored to specific content categories.