← 返回 Skills 市场
244
总下载
1
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install vidu-anime-production
功能描述
将用户创意或剧本转化为完整动漫成片,从剧本创作到自动拼接全流程使用 Vidu API 完成生图、生视频与 TTS,且禁止使用任何非 Vidu 模型。在用户需要制作动漫/动画短片、提供创意主题或详细剧本需求时使用;依赖 ffmpeg 与已配置的 Vidu API 凭证。
安全使用建议
Before installing or enabling this skill:
- Expect to supply a Vidu API key: the scripts look for VIDU_API_KEY or COZE_VIDU_API_7610322785025425408. Ask the author to update the skill metadata to declare the exact required env var name(s) and mark the primary credential. Do not assume your existing tokens will be picked up under another name.
- Ensure ffmpeg and Python dependencies (requests and any platform-provided coze_workload_identity module) are installed where the skill will run. The SKILL.md suggests apt-get install ffmpeg but installation is not automated.
- Review the scripts yourself (they are included). They make HTTP calls to api.vidu.cn and will download arbitrary URLs provided in timeline configs (video/audio/BGM URLs). Running in an isolated environment is recommended because the skill will fetch and write remote content to disk and may reach internal/external endpoints (risk of SSRF or unintended network access).
- Confirm what COZE_* env vars and coze_workload_identity mean on your platform — this looks like a platform-specific credential integration. If you don't recognize it, ask the publisher how credentials are injected and whether credentials are scoped/limited.
- If you plan to use real credentials, limit token scope and monitor usage (API calls, credits). Test first with a throwaway/dummy Vidu key to verify behavior.
- If these gaps (undeclared env vars, unspecified dependencies) are not fixed by the author, consider the skill suspicious and avoid granting it real credentials or running it in a production environment.
功能分析
Type: OpenClaw Skill
Name: vidu-anime-production
Version: 1.0.1
The skill bundle provides a legitimate workflow for automating anime production using the Vidu API and ffmpeg. The scripts (e.g., vidu_generate_video.py, merge_video_audio.py) are functional wrappers for API calls and media processing, and the instructions in SKILL.md are well-structured, emphasizing user confirmation at key stages of the creative process. While the merging script has the capability to download from arbitrary URLs and access local file paths, these functions are aligned with the stated purpose of assembling video assets, and no evidence of malicious intent or data exfiltration was found.
能力评估
Purpose & Capability
The skill's name/description claim it uses Vidu API and ffmpeg — the code indeed calls Vidu endpoints and requires ffmpeg — but the registry metadata does not declare any required environment variables or primary credential. The scripts expect VIDU_API_KEY or a specific env var COZE_VIDU_API_7610322785025425408. That missing declaration is an incoherence (the skill will fail or silently look for other env names).
Instruction Scope
SKILL.md instructs installing ffmpeg and to configure Vidu API credentials; the included scripts access environment variables, call external HTTP endpoints (api.vidu.cn and arbitrary user-supplied URLs for assets/BGM), download resources, and write temporary files. The instructions and scripts are broadly scoped to generate/fetch media (expected) but they reference environment variables and a platform-specific import (coze_workload_identity) that are not declared in registry metadata — granting the agent access to system-level install commands and arbitrary network downloads without those requirements documented.
Install Mechanism
This is instruction-only (no install spec) so nothing is automatically downloaded at install time, which is lower risk. However SKILL.md suggests running apt-get install ffmpeg (system-level), and the scripts import requests and (in one file) coze_workload_identity.requests — runtime dependencies are not documented. There's no packaged install step, so operator must ensure ffmpeg/requests/coze_workload_identity are present.
Credentials
The code expects API credentials via VIDU_API_KEY or a vendor/platform-specific env name COZE_VIDU_API_7610322785025425408. Registry metadata lists no required env vars or primary credential. Requiring an API token for Vidu is proportional for this skill, but the missing declaration plus a hard-coded skill id/env-var name is an incoherence and a risk (you may need to provide a differently named secret). Also the coze_workload_identity usage implies platform-specific credential behavior that should be explained.
Persistence & Privilege
Flags show always:false and default autonomous invocation settings. The skill does not request permanent platform privileges, does not modify other skills' configs, nor claim to persist credentials itself. This is normal.
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 vidu-anime-production - 安装完成后,直接呼叫该 Skill 的名称或使用
/vidu-anime-production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
anime-production-update v1.0.1
- 全新设计动漫成片制作Skill,支持从剧本到最终成片的全流程自动化
- 明确规定所有图片、视频、语音合成步骤只能调用Vidu API(禁止任何非Vidu模型)
- 细化10大操作步骤,包括每步的脚本调用、用户确认节点以及可选分支场景支持
- 详细分镜和分镜提示词规范,确保风格、角色、场景高度一致和高质量输出
- 集成ffmpeg和脚本执行需求,实现时间轴自动拼接和成片产出
- 完善用户交互流程,每个关键资产均需用户确认以保证创作质量
元数据
常见问题
Vidu API comic strip short film generation capability, with built-in AI-generated videos, images, and TTS. 是什么?
将用户创意或剧本转化为完整动漫成片,从剧本创作到自动拼接全流程使用 Vidu API 完成生图、生视频与 TTS,且禁止使用任何非 Vidu 模型。在用户需要制作动漫/动画短片、提供创意主题或详细剧本需求时使用;依赖 ffmpeg 与已配置的 Vidu API 凭证。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 244 次。
如何安装 Vidu API comic strip short film generation capability, with built-in AI-generated videos, images, and TTS.?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vidu-anime-production」即可一键安装,无需额外配置。
Vidu API comic strip short film generation capability, with built-in AI-generated videos, images, and TTS. 是免费的吗?
是的,Vidu API comic strip short film generation capability, with built-in AI-generated videos, images, and TTS. 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Vidu API comic strip short film generation capability, with built-in AI-generated videos, images, and TTS. 支持哪些平台?
Vidu API comic strip short film generation capability, with built-in AI-generated videos, images, and TTS. 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 Vidu API comic strip short film generation capability, with built-in AI-generated videos, images, and TTS.?
由 Vidu AI(@x-jihua)开发并维护,当前版本 v1.0.1。
推荐 Skills