← 返回 Skills 市场
susan4731-wilfordf

Text To Video App

作者 susan4731-wilfordf · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
66
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-app
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 voiceover and visuals — a...
安全使用建议
This skill will send whatever text and uploaded files you provide to a remote service at mega-api-prod.nemovideo.ai for rendering — treat that as data exfiltration to a third party. The manifest claims NEMO_TOKEN is required, but SKILL.md documents a fallback anonymous-token flow and also references a local config path in its frontmatter; those inconsistencies mean the publisher metadata may be out of sync with the runtime instructions. Before installing or using: (1) avoid uploading sensitive or confidential text/files unless you trust the nemovideo.ai service and its privacy policy; (2) prefer using a disposable or limited token if you must set NEMO_TOKEN; (3) ask the publisher for provenance (owner identity, homepage, privacy/TOS) and clarification about the config path and whether persistent credentials are stored locally; (4) be aware the skill will include attribution headers that can reveal platform/install-path hints — if that is a concern, get clarification about what the headers contain. Providing that additional provenance and clarification could raise confidence to benign; without it, treat the mismatches and external data flow as a risk.
功能分析
Type: OpenClaw Skill Name: text-to-video-app Version: 1.0.0 The skill bundle provides a legitimate integration for a text-to-video service hosted at mega-api-prod.nemovideo.ai. The SKILL.md file contains standard instructions for the AI agent to manage sessions, handle file uploads, and process video rendering tasks via a remote API. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found; the behavior is entirely consistent with the stated purpose of the application.
能力评估
Purpose & Capability
Name/description match the instructions: the skill routes user text/files to a remote video-rendering API. Requesting a service token (NEMO_TOKEN) is proportionate. However, the SKILL.md frontmatter includes a config path (~/.config/nemovideo/) that the registry metadata did not list, and the SKILL.md also documents a fallback anonymous-token flow — so the manifest and runtime docs disagree about whether a persistent token/config is required.
Instruction Scope
All instructions describe expected API flows (session creation, SSE, upload, export). These stay within the stated purpose, but they explicitly instruct the agent to send user-provided files (up to 200MB) and metadata to a third-party domain (mega-api-prod.nemovideo.ai). The skill also asks for constructing attribution headers (X-Skill-Platform) by inspecting install path patterns, which implies the agent may inspect environment/install paths to populate headers.
Install Mechanism
Instruction-only skill with no install spec and no included code — no additional software is written to disk by the skill itself.
Credentials
Only one credential (NEMO_TOKEN) is declared, which is appropriate for an API-backed service. But SKILL.md explicitly supports generating an anonymous token if NEMO_TOKEN is absent, contradicting the registry's 'required env var' claim. The skill also instructs including attribution headers that may reveal platform/install-path details.
Persistence & Privilege
always=false and there is no install or code writing to agent configs. The skill does not request permanent presence or modification of other skills.
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-app
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /text-to-video-app 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 of Text to Video App — quickly convert text into AI-generated, shareable videos. - Upload TXT, DOCX, PDF, SRT files up to 200MB and generate videos automatically. - Simple prompts allow users to specify video length, voiceover, and visual preferences. - Seamless cloud rendering with 30–90 second turnaround for most exports. - Backend connection and authentication handled automatically (including anonymous mode with free credits). - Supports export to MP4, MOV, AVI, WebM, MKV, GIF, and audio/image formats. - File upload, video export, credits, and real-time editing operations all available via chat.
元数据
Slug text-to-video-app
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 App 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 voiceover and visuals — a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 66 次。

如何安装 Text To Video App?

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

Text To Video App 是免费的吗?

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

Text To Video App 支持哪些平台?

Text To Video App 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 App?

由 susan4731-wilfordf(@susan4731-wilfordf)开发并维护,当前版本 v1.0.0。

💬 留言讨论