# dexhunter/seedance2-skill

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

Repository: https://github.com/dexhunter/seedance2-skill
Canonical: https://ross.abutalabs.com/products/seedance2-skill
Homepage: https://seedance2.help
License: MIT
License Family: permissive
Topics: prompt, seedance, seedance-2, video-prompt
Last push: 2026-02-18T13:00:03+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 68, release rhythm 35, longevity 14
- inputs: {"age_days": 203, "days_push": 196, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3438, forks 324 (observed 2026-08-28T04:08:05.005699+00:00)

## What it is
A set of agent skill files (SKILL.md) that teach AI coding agents like Claude Code, Cursor, and Cline how to write effective video generation prompts for ByteDance's Seedance 2.0 model. It covers input constraints, @ reference syntax, camera language, prompt structure patterns, and templates for ads, dramas, MVs, and educational content, with an associated web-based prompt optimizer at seedance2.help.

## Use cases
- write better prompts for seedance 2.0 video generation
- turn rough video ideas into structured video prompts
- learn camera language and shot timing for AI video prompts
- generate ad or MV video prompts with templates
- add a seedance prompt skill to claude code or cursor
- optimize video prompts with camera movement and audio direction

## When to choose
- you generate videos with ByteDance's Seedance 2.0 and want production-style prompts
- you use Claude Code, Cursor, Cline, or compatible agents and want prompt-writing guidance built in
- you want ready-made templates for ads, dramas, MVs, or educational videos
- you prefer a web tool that automatically adds camera, timing, and audio direction to rough ideas

## When to avoid
- you generate videos with models other than Seedance 2.0, since the syntax and conventions are model-specific
- you need an official ByteDance tool - this is independent and unofficial
- you want a library or API to integrate into an application rather than prompt-writing guidance
- you need video generation itself - this only writes prompts, it does not generate video

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, video-processing, documentation
- domain: artificial-intelligence, tutorials
- platform: cli, cross-platform
- tags: agent-skills, video-generation, seedance, claude-skills, prompt-optimization, bytedance, text-to-video, video

## Member repositories
- dexhunter/seedance2-skill (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.005699+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:37:40.699748+00:00, confidence not recorded.
  - readme: https://github.com/dexhunter/seedance2-skill (fetched 2026-08-28T04:08:05.005699+00:00, sha ebea073d78b8)
  - homepage: https://seedance2.help (fetched 2026-08-29T09:32:00.444978+00:00, sha 41d17a7b7257)
  - site_page: https://seedance2.help/docs (fetched 2026-08-29T09:32:00.454192+00:00, sha 2e9b4137962f)
  - site_page: https://seedance2.help/about (fetched 2026-08-29T09:32:00.457843+00:00, sha 1681d6651442)
  - site_page: https://seedance2.help/pricing (fetched 2026-08-29T09:32:00.456147+00:00, sha 0942250a0e9b)
- Data as of 2026-08-30T08:39:29.467469+00:00.