← 返回 Skills 市场
Text To Video Ai App
作者
mhogan2013-9
· GitHub ↗
· v1.0.0
· MIT-0
61
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-ai-app
功能描述
Skip the learning curve of professional editing software. Describe what you want — turn this script into a 30-second video with visuals and background music...
安全使用建议
This skill appears to implement a cloud text→video workflow and will send user text and uploaded files to an external API (mega-api-prod.nemovideo.ai). Before installing: (1) Confirm you trust that external service and its privacy policy — do not upload sensitive data. (2) Ask the author to clarify the configPaths vs registry metadata mismatch (why ~/.config/nemovideo/ is referenced). (3) If you do not want the agent to reveal local install paths or extra context, request that headers be fixed to not depend on filesystem detection. (4) Consider using an anonymous/throwaway NEMO_TOKEN for testing, and review logs to confirm only intended data is transmitted. (5) Because source/homepage are unknown, treat this as unverified third-party software and test with non-sensitive files first.
功能分析
Type: OpenClaw Skill
Name: text-to-video-ai-app
Version: 1.0.0
The skill is a legitimate integration for the NemoVideo AI service, providing a text-to-video generation interface via the 'mega-api-prod.nemovideo.ai' backend. It implements standard authentication flows, session management, and error handling consistent with its stated purpose. While it performs minor environment inspection of installation paths to set attribution headers (X-Skill-Platform), it lacks any indicators of malicious intent, data exfiltration, or unauthorized command execution.
能力评估
Purpose & Capability
The skill's stated purpose (convert text/scripts to videos) matches the runtime instructions that call a nemovideo.ai API and accept uploads. However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — that mismatch is unexplained. The skill also requires detecting an install path to set an attribution header, which implies the agent may read local path information. These details are not clearly justified by the short description.
Instruction Scope
The instructions tell the agent to upload user text/files (up to 200MB) and send them to https://mega-api-prod.nemovideo.ai, obtain or use a Bearer token, open SSE streams, and poll export endpoints. That is coherent for a cloud rendering service, but the instructions also (a) derive an X-Skill-Platform header from the install path (which requires filesystem inspection) and (b) do not explicitly limit what agent context is sent — conversation context or other environment values could be included unless implementation is careful. The agent is also instructed to auto-acquire an anonymous token if NEMO_TOKEN is absent, which is fine but means network calls will be made automatically.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, which minimizes install-time risk (nothing is downloaded or written by the skill bundle itself).
Credentials
Only one credential is declared (NEMO_TOKEN) and that aligns with a hosted API service. The SKILL.md flow will auto-request an anonymous token if none is present. The remaining concern is that metadata references a config path (~/.config/nemovideo/) and the agent may read install paths to build headers — both could expose local paths or config contents; the registry did not declare these config paths, so the reason for them is unclear.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform persistence. Autonomous invocation is allowed (platform default) but that alone is not a new risk given the skill's network behaviour.
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 text-to-video-ai-app - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-ai-app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
v1.0.0
Initial release of Text to Video AI App — generate AI videos from your text in minutes.
- Upload TXT, DOCX, PDF, or SRT files up to 200MB for automatic AI video creation with visuals and background music.
- Simple workflow: connect, upload text, describe your video, and receive a 1080p video download link within 1–2 minutes.
- Supports direct text prompts, video edits, and batch file processing for marketers, creators, and social media managers.
- Credit system with free starter tokens and session management for easy onboarding.
- Built-in error handling for unsupported files, low credits, and session/token management.
元数据
常见问题
Text To Video Ai App 是什么？
Skip the learning curve of professional editing software. Describe what you want — turn this script into a 30-second video with visuals and background music... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 61 次。
如何安装 Text To Video Ai App？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-ai-app」即可一键安装，无需额外配置。
Text To Video Ai App 是免费的吗？
是的，Text To Video Ai 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 Ai App 支持哪些平台？
Text To Video Ai 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 Ai App？
由 mhogan2013-9（@mhogan2013-9）开发并维护，当前版本 v1.0.0。
推荐 Skills