Agent skill · Media & Video

video-creation-collaborator

影品智创多智能体协同视频创作管理工具,提供11个智能体结构化分工、5阶段协同流程、质量管控标准与数据反馈机制,解决生图失真、视频合成瑕疵等问题,确保输出统一可控

anbeimegithub.com/anbeimeGitHub ↗
claude-codeships scripts
Install
npx skills add anbeime/skill --skill video-creation-collaborator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 12
SKILL.md size: 11 KB
Bundled scripts: yes
Path: skills/video-creation-collaborator/video-creation-collaborator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 4,714
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 影品智创 - 多智能体协同视频创作管理 ## 任务目标 - 本Skill用于: 规范化和指导10个智能体的协同创作流程,解决生图失真(多肢体/畸形)、视频合成瑕疵等问题 - 能力包含: - 11个智能体结构化分工(文案创作/故事策划/脚本创作/分镜导演/分镜画师/字幕师/配音师/音效师/视频工程师/质检/数据反馈) - 5阶段协同流程管理(需求承接→内容创作→生图创作→音频字幕→视频合成→全流程质检→数据迭代) - 质量管控与闭环反馈(前置质检拦截、数据沉淀迭代) - 素材生成支持(图片/音频/字幕/音乐) - 技术检测工具支持(图片质量、视频质量、音画同步) - 触发条件: 用户需要进行短视频创作,或需要规范化多智能体协同流程 ## 前置准备 - 依赖说明: ``` opencv-python>=4.8.0 pillow>=10.0.0 moviepy>=1.0.3 numpy>=1.24.0 ``` - 非标准文件/文件夹准备: ```bash # 创建工作目录 mkdir -p ./input/{materials,scripts} mkdir -p ./output/{drafts,storyboards,final} mkdir -p ./cache/{images,audio} ``` ## 操作步骤 ### 标准流程(5个阶段,10个智能体) #### 第一阶段: 需求承接与内容框架搭建 **触发节点**: 用户输入核心需求(商品信息+视频需求) **步骤1: 文案创作师智能体(首节点)** - 职责: 基于商品信息提炼核心卖点,生成适配短视频的文案 - 输入: 商品品类、核心卖点、目标受众、视频风格、时长 - 输出: - 核心Slogan(8-12字,简洁有力) - 分镜适配文案(3-5句,每句4-8字) - 质量标准: 无歧义、无夸大,贴合视频调性 - 下一级触发: 立即触发【故事策划师】、【字幕师】(暂存) **步骤2: 故事策划师智能体** - 职责: 基于卖点、文案,设计适配短视频时长的场景化故事线 - 输入: Slogan、分镜文案、商品信息、视频时长、风格 - 输出: - 场景化故事线(镜头拆分、场景/动作标注) - 镜头数量(30秒8-10个、45秒12-15个、60秒15-18个) - 质量标准: 逻辑连贯,时长严格匹配,无无关场景 - 下一级触发: 立即触发【脚本创作师】 **步骤3: 脚本创作师智能体** - 职责: 将故事线转化为标准化、可执行的分镜脚本 - 输入: 故事线、文案、视频时长、分辨率、比例 - 输出: - 标准化分镜脚本(镜头序号、时长、场景描述、画面动作、文案、音效备注) - 画面动作描述(明确人体肢体姿态,规避模糊表述) - 质量标准: 时长精准分配,画面动作具体,格式统一 - 下一级触发: 立即触

What's inside
Steps it walks through
  1. 任务目标
  2. 前置准备
  3. 操作步骤
  4. 标准流程(5个阶段,10个智能体)
  5. 并行协同与闭环管控
  6. 并行执行
  7. 闭环管控
  8. 迭代联动
  9. 质量检测工具使用
  10. 图片质量检测
  11. 视频质量检测
  12. 素材生成与视频合成流程
  13. 素材生成流程
  14. 视频合成流程
Ships with 11 files
  • assets/reports/quality-report-template.md
  • assets/templates/storyboard-template.md
  • references/agent-prompts.md
  • references/asset-specifications.md
  • references/quality-standards.md
  • scripts/audio_generator.py
  • scripts/image_generator.py
  • scripts/image_quality_checker.py
  • scripts/subtitle_generator.py
  • scripts/video_compositor.py
  • scripts/video_quality_checker.py
Commands it runs
mkdir -p ./input/{materials,scripts}
mkdir -p ./output/{drafts,storyboards,final}
mkdir -p ./cache/{images,audio}
python scripts/image_quality_checker.py --image ./cache/images/shot_001.jpg --resolution 1920x1080
python scripts/video_quality_checker.py --video ./output/final/video.mp4 --resolution 1920x1080 --duration 30 --fps 25
cat > ./scripts/storyboard.json << 'EOF'
python scripts/image_generator.py \
python scripts/audio_generator.py \
python scripts/music_generator.py \
python scripts/subtitle_generator.py \
More from skill
All skills →
About this skill
What does the video-creation-collaborator skill do?

影品智创多智能体协同视频创作管理工具,提供11个智能体结构化分工、5阶段协同流程、质量管控标准与数据反馈机制,解决生图失真、视频合成瑕疵等问题,确保输出统一可控

How do I install it?

Run `npx skills add anbeime/skill --skill video-creation-collaborator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From anbeime/skill, a repository with 4,714 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going