← 返回 Skills 市场
Text To Video Kaggle
作者
dsewell-583h0
· GitHub ↗
· v1.0.0
· MIT-0
64
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-kaggle
功能描述
Skip the learning curve of professional editing software. Describe what you want — generate a video from this text description: 'a dog running through a sunn...
安全使用建议
This skill appears to do what it says (call a remote NemoVideo API to render text→video) and only asks for a single token. Before installing, consider: 1) Where would you get NEMO_TOKEN? Only provide tokens from trusted sources. 2) The skill will upload user files and may store session data in ~/.config/nemovideo/ — avoid sending sensitive files. 3) The SKILL.md asks the agent to detect local install paths and to 'keep technical details out of the chat' — if you want transparency about network calls, ask the skill to show logs or deny filesystem probing. 4) The skill has no homepage and its source is unknown; prefer skills backed by a known project or provider. If you need lower exposure, use the anonymous-token fallback (limited-time credits) or test with non-sensitive data first.
功能分析
Type: OpenClaw Skill
Name: text-to-video-kaggle
Version: 1.0.0
The skill is a functional wrapper for the NemoVideo AI text-to-video service, designed to facilitate video generation from text prompts. It manages API sessions, handles file uploads to 'mega-api-prod.nemovideo.ai', and automates the rendering and export of MP4 videos. The instructions in SKILL.md provide clear guidance for the AI agent on handling authentication (including a fallback for anonymous tokens), session state, and error codes. No evidence of malicious intent, unauthorized data exfiltration, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description (generate videos from text) align with the single requested credential (NEMO_TOKEN) and the API endpoints described. No unrelated cloud credentials or unrelated binaries are requested.
Instruction Scope
Instructions instruct the agent to obtain/use NEMO_TOKEN (or fetch an anonymous token), create sessions, upload files, run SSE endpoints, and poll render jobs — all consistent with a remote render service. However the SKILL.md also instructs the agent to detect install paths (~/.clawhub/, ~/.cursor/skills/) and to keep technical details out of the chat. Detecting filesystem paths is not strictly necessary for basic text→video functionality and could expose local state; 'keep technical details out of the chat' may obscure network/activity details from users. These are scope/privacy concerns.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is downloaded or written by an installer.
Credentials
Only one credential is required (NEMO_TOKEN), which is proportionate to a hosted video-rendering API. The registry metadata also declares a config path (~/.config/nemovideo/) which could be used to store tokens or session state; this is plausible but not strictly justified in the documentation and may grant the skill access to local config files.
Persistence & Privilege
Skill is not always-on and does not request system-wide privileges. It does instruct the agent to create sessions and poll remote jobs, which is normal for this use-case. It does not request modifying other skills or system settings.
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-kaggle - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-kaggle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 — generate AI videos from text prompts, built for data scientists and ML researchers.
- Accepts text prompts and related uploads (TXT, CSV, JSON, MP4 up to 200MB) to generate AI videos in 1–3 minutes.
- Automated connection: obtains API token and session before any request.
- Supports video generation, asset upload, credit checks, export (MP4 and more), and timeline state fetch.
- Cloud rendering with real-time feedback; jobs handled on remote GPU nodes.
- Summarizes timeline state and handles API errors (e.g., token expiry, file size, credits).
元数据
常见问题
Text To Video Kaggle 是什么？
Skip the learning curve of professional editing software. Describe what you want — generate a video from this text description: 'a dog running through a sunn... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 64 次。
如何安装 Text To Video Kaggle？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-kaggle」即可一键安装，无需额外配置。
Text To Video Kaggle 是免费的吗？
是的，Text To Video Kaggle 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Kaggle 支持哪些平台？
Text To Video Kaggle 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 Kaggle？
由 dsewell-583h0（@dsewell-583h0）开发并维护，当前版本 v1.0.0。
推荐 Skills