← 返回 Skills 市场
931
总下载
3
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install video-script-generator
功能描述
生成短视频脚本和分镜。输入产品/主题描述、目标受众、时长，输出完整脚本+分镜结构（JSON/YAML）。支持多种模板：痛点-解决、反转剧情、before-after。触发词：视频脚本、短视频文案、分镜、storyboard、video script。
使用说明 (SKILL.md)
短视频脚本+分镜生成
工作流程
- 收集输入信息
- 选择模板风格
- 生成脚本+分镜结构
- 输出结构化数据供下游消费
输入参数
| 参数 | 必填 | 说明 |
|---|---|---|
| topic | ✓ | 产品/主题描述 |
| audience | ✓ | 目标受众 |
| duration | ✓ | 时长：15s / 30s / 60s / 90s |
| template | - | 模板：pain-solution / before-after / plot-twist |
| platform | - | 平台：douyin / xiaohongshu / youtube-shorts |
| tone | - | 语气：professional / casual / humorous / dramatic |
模板说明
pain-solution（默认）
痛点引入 → 解决方案 → 效果展示 → CTA
before-after
对比前的状态 → 转折点 → 对比后的状态 → CTA
plot-twist
正常叙事 → 意外反转 → 揭示真相 → CTA
详见 templates/ 目录。
输出格式
meta:
title: "脚本标题"
duration: 30s
platform: douyin
template: pain-solution
script:
hook: "开场钩子文案"
scenes:
- id: 1
type: hook # hook/pain/solution/demo/cta
duration: 3s
narration: "旁白/台词"
shot_description: "镜头描述：特写/中景/全景，动作，表情"
visual_style: "画面风格提示"
demo_insert: false
- id: 2
type: pain
duration: 5s
narration: "..."
shot_description: "..."
demo_insert: false
- id: 3
type: solution
duration: 8s
narration: "..."
shot_description: "产品界面展示"
demo_insert: true
demo_action: "点击生成按钮，展示结果"
- id: 4
type: cta
duration: 3s
narration: "链接在评论区"
shot_description: "logo + 二维码"
demo_insert: false
cta: "链接在评论区 / 点击头像私信"
music_suggestion: "轻快节奏 / 紧张悬疑 / 温馨治愈"
场景类型
| type | 用途 | 典型时长 |
|---|---|---|
| hook | 开场吸引 | 2-3s |
| pain | 痛点展示 | 3-5s |
| solution | 解决方案 | 5-10s |
| demo | 产品演示 | 5-15s |
| result | 效果展示 | 3-5s |
| twist | 反转 | 3-5s |
| cta | 行动号召 | 2-3s |
时长分配参考
| 总时长 | 场景数 | 分配建议 |
|---|---|---|
| 15s | 3-4 | hook(2) + core(10) + cta(3) |
| 30s | 4-6 | hook(3) + pain(5) + solution(15) + cta(3) |
| 60s | 6-8 | hook(3) + pain(8) + solution(35) + result(10) + cta(4) |
使用示例
用户：帮我写一个30秒的短视频脚本，推广我的AI写作工具，目标用户是自媒体博主
执行：
- 确认参数：topic=AI写作工具, audience=自媒体博主, duration=30s
- 选择模板：pain-solution（默认）
- 生成脚本+分镜
- 输出 YAML 结构
下游对接
输出的结构化数据可直接用于：
digital-avatarskill：提取 narration 生成口播scene-video-generatorskill：按 shot_description 生成画面video-stitcherskill：按 duration 拼接
安全使用建议
This skill is instruction-only and appears to do exactly what it says: generate short-video scripts and shot-level storyboards. There are no requested credentials or installs, which reduces risk. Before using, avoid pasting any sensitive or proprietary secrets (API keys, private images, or internal URLs) into the input fields because generated scripts may include or echo that content. Also note the SKILL.md mentions downstream skills (digital-avatar, scene-video-generator, video-stitcher) — if you connect outputs to other skills, review those skills' permissions and credentials separately. Overall this skill is coherent and low-risk, but exercise normal caution about the content you provide to it or to any downstream skill.
功能分析
Type: OpenClaw Skill
Name: video-script-generator
Version: 1.0.0
The video-script-generator skill is a legitimate tool designed to help an AI agent generate structured video scripts and storyboards. The files (SKILL.md and the templates directory) contain only formatting instructions, structural templates (pain-solution, before-after, plot-twist), and output specifications in YAML format. There is no evidence of malicious code, data exfiltration, or prompt injection intended to compromise the agent or the host system.
能力评估
Purpose & Capability
Name/description (video script + storyboard) match the included SKILL.md and template files; no unrelated binaries, credentials, or config paths are requested.
Instruction Scope
Runtime instructions only collect user inputs (topic, audience, duration, template, etc.) and produce structured YAML/JSON; they do not instruct the agent to read unrelated files, access environment variables, or transmit data to external endpoints.
Install Mechanism
No install spec and no code files to execute — this is instruction-only, so nothing is downloaded or written to disk during install.
Credentials
The skill declares no required environment variables or credentials; templates and examples do not request secrets or unrelated service tokens.
Persistence & Privilege
always:false and default autonomous invocation are normal. The skill does not request persistent system presence or modify other skills' configuration.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install video-script-generator - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-script-generator触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
常见问题
Video Script Generator 是什么？
生成短视频脚本和分镜。输入产品/主题描述、目标受众、时长，输出完整脚本+分镜结构（JSON/YAML）。支持多种模板：痛点-解决、反转剧情、before-after。触发词：视频脚本、短视频文案、分镜、storyboard、video script。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 931 次。
如何安装 Video Script Generator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-script-generator」即可一键安装，无需额外配置。
Video Script Generator 是免费的吗？
是的，Video Script Generator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Script Generator 支持哪些平台？
Video Script Generator 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Video Script Generator？
由 Olivia_Pp（@oliviapp8）开发并维护，当前版本 v1.0.0。
推荐 Skills