← 返回 Skills 市场
326
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install video-film-maker-pro
功能描述
AI视频成片制作流水线。从参考图+提示词生成完整视频成片。特点：画风统一、叙事连贯、节奏紧凑（每镜头2-4秒）。流程：剧情大纲 → 关键帧提示词 → 关键帧图片 → 分镜提示词 → 视频生成，每步用户确认。触发：生成视频、制作成片、视频故事、短片制作等请求。
安全使用建议
Do not install blindly. Ask the publisher for: (1) the Vidu API endpoint and exact authentication method (API key name, header format, or SDK) and where you should store credentials (env var names); (2) a privacy/TOS statement describing what happens to uploaded images and generated content; (3) whether the skill will perform web searches automatically and whether that can be disabled. Verify ffmpeg availability and output paths before running. Avoid sending sensitive images or credentials until the endpoint/authentication details and publisher identity are confirmed. If you lack trust in the author or cannot get clear details, treat this skill as unsafe to run because it would send data to an unspecified external service.
功能分析
Type: OpenClaw Skill
Name: video-film-maker-pro
Version: 1.0.1
The video-film-maker-pro skill is a legitimate workflow for automating AI video production. It provides structured instructions for an agent to generate plot outlines, image prompts, and video segments using the Vidu API, including mandatory user confirmation steps at every stage. The use of web search for character references and ffmpeg for video concatenation in SKILL.md is consistent with the stated purpose and lacks any indicators of malicious intent or unauthorized data access.
能力评估
Purpose & Capability
The skill's stated purpose is to call a Vidu image/video generation pipeline, but the package declares no required environment variables, no primary credential, and no endpoint information. A remote media-generation API normally requires an API key/URL — the absence of any declared credential or guidance is inconsistent with the skill's purpose.
Instruction Scope
SKILL.md instructs the agent to perform web searches for reference images, convert images to base64, call an external Vidu API to generate images and video, and write output files (~/Desktop/*.mp4) and call ffmpeg to merge files. These runtime actions include network requests, third-party content fetching, file creation, and execution of local commands; the document does not specify where API calls are sent, how to authenticate, or whether user uploads are transmitted to third parties.
Install Mechanism
This is instruction-only (no install spec and no code files), so nothing is written to disk by an installer and there is low install-time risk. However, runtime actions still require binaries (e.g., ffmpeg) and network access.
Credentials
Despite making repeated example payloads for Vidu API calls, the skill lists no required environment variables or credentials. That is disproportionate: calling a remote API should normally require declared API key or endpoint configuration. Additionally, the skill instructs web image searches and sending images to external services without documenting required permissions or secrets.
Persistence & Privilege
The skill does not request always:true and does not modify other skills. It does assume ability to write files (~/Desktop) and run ffmpeg at runtime — typical for a video workflow but worth noting because it involves local filesystem writes and executing a binary that may not be present or may need permissions.
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-film-maker-pro - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-film-maker-pro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
v1.0.1
video-film-maker-pro 1.0.0 - Initial Release
- Introduces a step-by-step AI video creation workflow from story outline to final edit.
- Ensures consistent art style and tight narrative pacing (2-4s per shot) based on user input.
- Requires explicit user confirmation at every major stage: outline, prompts, images, shot instructions, and final generation.
- Supports reference images, detailed prompts, style, mood, and duration control.
- Integrates Vidu models for both image and video synthesis with recommended models per scene type.
- Provides detailed user guidance, interactive confirmations, and error handling for iterative creation.
元数据
常见问题
One-click generation of stories from text and images, provided by Vidu API. 是什么？
AI视频成片制作流水线。从参考图+提示词生成完整视频成片。特点：画风统一、叙事连贯、节奏紧凑（每镜头2-4秒）。流程：剧情大纲 → 关键帧提示词 → 关键帧图片 → 分镜提示词 → 视频生成，每步用户确认。触发：生成视频、制作成片、视频故事、短片制作等请求。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 326 次。
如何安装 One-click generation of stories from text and images, provided by Vidu API.？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-film-maker-pro」即可一键安装，无需额外配置。
One-click generation of stories from text and images, provided by Vidu API. 是免费的吗？
是的，One-click generation of stories from text and images, provided by Vidu API. 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
One-click generation of stories from text and images, provided by Vidu API. 支持哪些平台？
One-click generation of stories from text and images, provided by Vidu API. 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 One-click generation of stories from text and images, provided by Vidu API.？
由 Vidu AI（@x-jihua）开发并维护，当前版本 v1.0.1。
推荐 Skills