← 返回 Skills 市场
mhogan2013-9

Text To Video Creation

作者 mhogan2013-9 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
68
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-creation
功能描述
Skip the learning curve of professional editing software. Describe what you want — turn this blog intro into a 30-second video with visuals and background mu...
安全使用建议
This skill mostly behaves like a normal cloud text→video integrator: it needs a NEMO_TOKEN (or it will obtain a short-lived anonymous token) and it will upload whatever files you provide to mega-api-prod.nemovideo.ai. Things to consider before installing or using it: - Privacy: any text/files you upload (TXT, DOCX, PDF, images, audio) will be sent to the external API. Avoid uploading sensitive or confidential content unless you trust the service and its privacy policy. - Tokens: the skill will send Authorization: Bearer <NEMO_TOKEN> to the external domain. If you set NEMO_TOKEN in your environment, that secret will be transmitted to that host. - Unexpected local access: metadata and instructions indicate the skill may read the SKILL.md frontmatter and attempt to detect install paths (~/.clawhub/, ~/.cursor/skills/) and it declares ~/.config/nemovideo/ as a required config path. Ask the publisher why filesystem access is needed and what files under that path will be read. If you prefer, run the skill in an isolated environment or without a local NEMO_TOKEN. - Trust the domain: the API host (mega-api-prod.nemovideo.ai) is not a well-known public vendor in the manifest — verify the service owner and privacy/security practices before sending real data. - If you only want to test functionality, use throwaway content and do not provide proprietary data or your own production tokens. If the publisher is unknown, prefer not to store your main credentials in NEMO_TOKEN. Given these unexplained filesystem/access bits (configPath + install-path probing) I recommend asking the skill author for clarification or using it in a sandboxed environment; the mismatch is concerning enough to mark it as suspicious rather than benign.
功能分析
Type: OpenClaw Skill Name: text-to-video-creation Version: 1.0.0 The skill provides a legitimate interface for a text-to-video AI service hosted at mega-api-prod.nemovideo.ai. It manages session authentication, file uploads, and video rendering workflows as described in the documentation. The code and instructions in SKILL.md are consistent with the stated purpose, using standard environment variables (NEMO_TOKEN) and configuration paths (~/.config/nemovideo/) without any evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
Name/description, API endpoints, and required NEMO_TOKEN align with a cloud text-to-video service. However, the registry metadata declares a required config path (~/.config/nemovideo/) which is not justified by the SKILL.md instructions; that suggests the skill expects to read local configuration files without explanation and is disproportionate to the stated purpose.
Instruction Scope
Runtime instructions are detailed and stay within the expected domain (auth, session creation, SSE, upload, render). They do instruct the agent to read the skill's YAML frontmatter and detect install path to populate X-Skill-Platform, which implies filesystem probing. The SKILL.md also tells the agent to hide technical details from the chat. Reading frontmatter / detecting install path is outside the core text->video task and could access local state the user did not expect.
Install Mechanism
No install spec and no code files — instruction-only skill — so there is no download/execute risk from an install step. This is the lowest-risk install mechanism.
Credentials
Requiring a single credential, NEMO_TOKEN, is appropriate for a remote API. But metadata also lists a config path (~/.config/nemovideo/) and the skill will generate/obtain an anonymous token when NEMO_TOKEN is absent. The config path requirement and filesystem detection behavior increase the scope of access beyond a single API token.
Persistence & Privilege
always is false and there is no indication the skill requests permanent system presence or modifies other skills. The skill runs as-needed and uses remote API calls; no elevated persistence privileges are requested.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install text-to-video-creation
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /text-to-video-creation 触发
  4. 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: Convert text into shareable AI-generated videos quickly and easily. - Upload TXT, DOCX, PDF, or plain text files (up to 500MB) to generate videos with visuals and background music in 1-2 minutes. - No need for professional editing skills — just describe the video you want. - Supports checking credits, session status, file uploads, and video exports via simple commands. - All video creation is handled on cloud GPUs, returning MP4 files (1080p default). - Includes error handling, session management, and clear feedback for common issues (credits, file size, and types). - Ideal for marketers, content creators, and educators seeking fast, no-hassle video production.
元数据
Slug text-to-video-creation
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Text To Video Creation 是什么?

Skip the learning curve of professional editing software. Describe what you want — turn this blog intro into a 30-second video with visuals and background mu... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 68 次。

如何安装 Text To Video Creation?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-creation」即可一键安装,无需额外配置。

Text To Video Creation 是免费的吗?

是的,Text To Video Creation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Text To Video Creation 支持哪些平台?

Text To Video Creation 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 Text To Video Creation?

由 mhogan2013-9(@mhogan2013-9)开发并维护,当前版本 v1.0.0。

💬 留言讨论