Video Storyboard Generate

v1.0.4

1. 获取分镜信息

0· 464·1 current·1 all-time
bydlazy@dlazyai

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for dlazyai/video-storyboard-generate.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Video Storyboard Generate" (dlazyai/video-storyboard-generate) from ClawHub.
Skill page: https://clawhub.ai/dlazyai/video-storyboard-generate
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: npm, npx
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install video-storyboard-generate

ClawHub CLI

Package manager switcher

npx clawhub@latest install video-storyboard-generate
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the runtime behavior: the skill plans storyboard steps, builds a JSON workflow, and uses the dLazy CLI to generate media. Requiring npm/npx (for npx or npm install of @dlazy/cli) and referencing dLazy endpoints is coherent.
Instruction Scope
SKILL.md confines the agent to collecting requirements, drafting prompts, asking for confirmation, and running single synchronous dlazy CLI commands; it explicitly forbids saving prompts to files and batch command execution. It does instruct uploading local media (via the CLI) which is expected for this use-case.
Install Mechanism
No registry install spec is required by the platform (instruction-only), but metadata recommends installing or using the npm package @dlazy/cli@1.0.6 via npm/npx. Installing from npm (or using npx) is a normal, low-risk install mechanism — review the package/source before global install and prefer npx for one-off runs.
Credentials
The skill does not demand unrelated secrets. It reasonably requires a dLazy API key (config via dlazy auth set or DLAZY_API_KEY) to call the service. No other credentials or system paths are requested.
Persistence & Privilege
always:false and default autonomous invocation are used; the skill does not request elevated/system-wide persistence or modify other skills. The CLI stores the API key in a user config file (~/.dlazy/config.json), which is typical for CLIs.
Scan Findings in Context
[no_regex_findings] expected: The static scanner found no code files to analyze because this is an instruction-only skill. The SKILL.md itself contains the runtime guidance and references to the npm package and API endpoints.
Assessment
This skill is coherent but does perform networked generation via the dLazy service and will upload local media when you run commands. Before installing or running: (1) review the @dlazy/cli source on GitHub and prefer npx for one-off use instead of a global npm install; (2) be prepared to provide a dLazy API key — it will be stored in your user config (~/.dlazy/config.json) unless you pass DLAZY_API_KEY per-run; (3) avoid supplying sensitive audio/video that you don't want uploaded to a third-party service; (4) the agent is intended to execute terminal commands — only allow it to run commands you explicitly approve at each step (the skill also instructs the agent to pause and get confirmation before generation); (5) if you install the CLI, verify the npm package integrity (checksums, repo) and keep a revocable API key so you can rotate/revoke access if needed.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🤖 Clawdis
Binsnpm, npx
latestvk97dqd671c09abm2catryzjyxn85n9w0
464downloads
0stars
5versions
Updated 1d ago
v1.0.4
MIT-0

身份验证 (Authentication)

所有请求都需要 dLazy API key,通过 CLI 配置:

dlazy auth set YOUR_API_KEY

CLI 会把 key 保存在你的用户配置目录(macOS/Linux 上为 ~/.dlazy/config.json,Windows 上为 %USERPROFILE%\.dlazy\config.json),文件权限仅限当前操作系统用户访问。你也可以用 DLAZY_API_KEY 环境变量按次传入。

获取你的 API Key

  1. 登录或在 dlazy.com 创建账号
  2. 访问 dlazy.com/dashboard/organization/api-key
  3. 复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织,可在同一控制面板随时轮换或吊销

关于与来源 (Provenance)

如果你不希望在系统上长期保留一个全局 CLI,可以按需运行:

npx @dlazy/cli@1.0.6 <command>

如选择全局安装,技能的 metadata.clawdbot.install 字段已固定到 npm install -g @dlazy/cli@1.0.6。安装前建议先到 GitHub 仓库审阅源码。

工作原理 (How It Works)

此技能是 dLazy 托管 API 的轻量封装。调用时:

  • 你提供的提示词与参数会发送到 dLazy API(api.dlazy.com)进行推理。
  • 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储(oss.dlazy.com),以便模型读取 —— 与任何云端生成 API 的流程一致。
  • API 返回的生成结果 URL 由 oss.dlazy.com 托管。

这是标准的 SaaS 调用模式;技能本身不会越权访问网络或文件系统,所有动作都由 dLazy CLI 完成。


name: 'video-storyboard-generate' description: '将一个分镜的内容,转换成一个分镜生成视频的生成流程,用户可以将流程添加到画布中'

分镜视频生成流程

English · 中文

  1. 获取分镜信息
  2. 定义视频的生成流程
  3. 画到画布中

获取分镜信息

从上下文中获取分镜信息:

  • 图片/视频比例:aspect_ratio, 例如:16:9、9:16、4:3、3:4、1:1
  • 图片/视频分辨率:resolution,例如:1080p、720p
  • 依据比率和分辨率,计算出视频的宽度和高度, width, height

提取分镜列表:

  • 分镜名称:story_name1

  • 对话文本:dialogue_text1

  • 视频生成提示词:video_prompt1

    定义视频的生成流程

    视频生成流程时一段JSON字符串,示例格式如下, 请注意以下问题:

    1. 记得替换{name}中的内容, 注意 x\y\w\h 是数值,替换后需要去掉引号;
    2. 原始声音和场景图是所有分镜共用的,只有一个,克隆声音和视频和分镜数量一致,请循环分镜列表创建。
    3. 元素的位置x和y,按分镜列表的顺序累加,每个分镜之间间隔100像素。
    [
      {
        "type": "audio",
        "x": 0,
        "y": 0,
        "props": {
          "name": "原始声音",
          "w": "{width}",
          "h": "{height}"
        }
      },
      {
        "type": "audio",
        "x": "{width + 100}",
        "y": 0,
        "props": {
          "name": "{story_name1} 克隆声音",
          "w": "{width}",
          "h": "{height}",
          "model": "vidu-audio-clone",
          "input": {
            "prompt": "{dialogue_text1}",
            "audio_url": "shape://name:原始声音"
          }
        }
      },
      {
        "type": "image",
        "x": 0,
        "y": "{height + 100}",
        "props": {
          "name": "场景图",
          "w": "{width}",
          "h": "{height}"
        }
      },
      {
        "type": "video",
        "x": "{width + 100}",
        "y": "{height + 100}",
        "props": {
          "name": "{story_name1} 视频",
          "w": "{width}",
          "h": "{height}",
          "model": "jimeng-omnihuman-1_5",
          "input": {
            "audio": ["shape://name:{story_name1} 克隆声音"],
            "images": ["shape://name:场景图"],
            "prompt": "{video_prompt1}",
            "fast_mode": false,
            "resolution": "{resolution}"
          }
        }
      }
    ]
    

    画到画布中

    调用 MCP 的 drawToCanvas 工具, 将前面定义的流程添加到画布中。

🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)

你是可以执行终端命令的智能 Agent!

【严格禁止行为】

  • 严禁:将提示词保存到任何文件中(如 txt, md)。
  • 严禁:要求用户自己去第三方平台(如 Midjourney)生成图片。
  • 严禁:一次性批量生成所有图片,或一次性执行多个命令。

【必须遵循的交互与执行流程】 你必须严格分步执行,并在每一步停下来等待用户回复:

  1. 第一步:主动收集需求。当用户提出需求时,不要做任何设计和生成,先向用户提问(如产品特点、目标人群、想要几张图等)。必须等待用户回答。
  2. 第二步:输出草案并请求确认。根据用户的回答,制定套图计划,并输出第一张图的提示词草案。询问用户:“是否确认这个提示词,可以开始生成第一张图了吗?” 必须等待用户回答“确认”。
  3. 第三步:单次执行终端命令。用户确认后,你必须使用终端执行命令(如 dlazy seedream-4.5 --prompt "..."),每次只能执行一个生成命令。重要:必须使用同步命令,绝不要在命令末尾加 &,绝不要使用 &&,这是在 Windows PowerShell 下运行!
  4. 第四步:交付与循环。命令返回结果后,把图片 URL 发给用户,并询问“对这张满意吗?我们可以继续生成下一张了吗?”。收到确认后再继续下一步。

Comments

Loading comments...