video-agent-storyboarder — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited video-agent-storyboarder (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
分镜师是文字世界和画面世界的桥梁。通过 Gemini Flash API 自动生成分镜：
generate_storyboard.py 脚本自动拆稿和设计画面script.md（编剧产出的逐字稿）storyboard.json（结构化数据）+ storyboard.md（可读版本）python scripts/generate_storyboard.py <project_dir> [--style <风格>] [--duration <时长>]参数：
project_dir — 项目目录（包含 script.md）--style — 视频风格描述（默认："AI科技/知识分享"）--duration — 目标时长（默认："6-10分钟"）脚本会：
script.mdgemini-2.5-flash，低成本纯文本模型）storyboard.json + storyboard.md[
{
"shot_number": 1,
"time_range": "0:00-0:05",
"script_text": "你有没有想过一个问题",
"asset_type": "概念画面",
"media_format": "ai_video",
"visual_description": "A person scrolling through a phone with countless notification pop-ups flooding the screen, warm office lighting, close-up shot, dynamic movement",
"mood": "焦虑、快切",
"duration_seconds": 5
}
]# 分镜表 — 视频标题
> 总镜头数：XX 个
---
| 镜头 | 时间 | 秒 | 对应逐字稿 | 素材类型 | 媒体格式 | 画面说明 | 情绪 |
|------|------|----|-----------|---------|---------|---------|------|
| 001 | 0:00-0:05 | 5 | 你有没有想过一个问题 | 概念画面 | ai_video | A person scrolling... | 焦虑、快切 || 类型 | 说明 | 典型 media_format |
|---|---|---|
| 截图 | 真实产品/网页/App 界面截图或录屏 | manual |
| 真实人物 | 提到的真实公众人物照片 | manual |
| 文字卡 | 关键概念、金句、结论的排版动效 | post_production |
| 数据图表 | 统计数字、趋势图、对比图 | post_production |
| 概念画面 | 抽象隐喻、无法实拍的概念可视化 | ai_video / ai_image |
| 引用片段 | 新闻报道、产品演示、公开视频截取 | manual |
| 信息图 | 逻辑关系图、流程图、对比表 | post_production |
| 留白 | 纯色/渐变背景，让声音主导 | simple |
| 书籍 | 提到的书籍/论文封面 | ai_image / manual |
| 分屏 | 多画面同时展示 | post_production |
| 格式 | 说明 |
|---|---|
| ai_video | AI 生成 5-10 秒动态视频（Veo 3/Seedance/Kling/Sora） |
| ai_image | AI 生成静态图片 |
| manual | 需人工准备（截图、搜索真实照片、录屏） |
| post_production | 后期制作（文字动效、数据图表、信息图） |
| simple | 简单背景，无需制作 |
常用情绪词：
脚本生成后，人工或 Claude 审核以下项目：
#### 镜头检查
#### 覆盖检查
#### 格式检查
#### 情绪曲线检查
模板文件位于 prompts/storyboard_prompt.txt，包含：
{script_content}, {video_style}, {total_duration}| 环境变量 | 用途 |
|---|---|
| GEMINI_API_KEY | Gemini Flash API 调用 |
scripts/generate_storyboard.py — 分镜生成主脚本prompts/storyboard_prompt.txt — Prompt 模板~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.