← 返回 Skills 市场
90
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-dataset
功能描述
Turn a CSV file with 500 text prompt and video description pairs into 720p labeled video dataset just by typing what you need. Whether it's creating paired t...
安全使用建议
This skill is instruction-only and appears to do what it says: it will send your uploaded CSV/files and prompts to https://mega-api-prod.nemovideo.ai to create/render videos. Before installing/using: (1) Confirm you trust the nemo domain and understand their retention/privacy for uploaded media and prompts. (2) Only provide a NEMO_TOKEN that is scoped to this service — do not reuse a token that grants broader access elsewhere. (3) Note the skill will generate an anonymous token if no NEMO_TOKEN is present (it contacts the API to do so). (4) Because the skill is from an unknown source, prefer testing with non-sensitive sample data first. If you need higher assurance, ask the publisher for a homepage, privacy policy, or an official SDK/release notes for the mega-api-prod.nemovideo.ai service.
功能分析
Type: OpenClaw Skill
Name: text-to-video-dataset
Version: 1.0.0
The skill bundle provides a legitimate integration for a text-to-video generation service hosted at mega-api-prod.nemovideo.ai. It contains detailed instructions for the AI agent to manage API sessions, handle authentication (including a fallback for anonymous tokens), and process video rendering tasks via Server-Sent Events (SSE). The skill explicitly declares its requirements for the NEMO_TOKEN environment variable and access to ~/.config/nemovideo/, and its behavior is entirely consistent with its stated purpose of generating video datasets from text prompts.
能力评估
Purpose & Capability
Name/description (create paired text→video dataset) align with instructions: the SKILL.md describes authentic API calls for creating sessions, uploading files, streaming events, and exporting rendered MP4s. Requiring NEMO_TOKEN to authenticate to the nemo video API is proportionate. Small inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) even though registry metadata said no required config paths; this is a minor mismatch but not indicative of malicious intent.
Instruction Scope
Instructions only call the nemo backend endpoints, describe uploading user files (multipart or URL), reading session state, and using SSE. They do not instruct broad local file reads, credential harvesting beyond NEMO_TOKEN, or exfiltration to unknown hosts. The skill will use any NEMO_TOKEN present in the environment (or obtain an anonymous token via a POST), which is expected behavior for an API-backed skill.
Install Mechanism
No install spec and no code files (instruction-only). This is lower-risk because nothing is downloaded or written to disk by the skill itself.
Credentials
The only required secret is NEMO_TOKEN (declared as primary). The SKILL.md will also create an anonymous token if none is present. This is proportionate for a service that requires authentication, but users should be careful not to set a generic/privileged token named NEMO_TOKEN that belongs to other services.
Persistence & Privilege
always:false and no instructions to persist or modify other skills or system-wide configs. The skill does create session tokens for the backend, which is normal for an API client.
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-dataset - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-dataset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-dataset 1.0.0:
- Generate labeled video datasets from CSV prompts and descriptions, supporting 720p output by default.
- Seamless workflow: upload text/video description pairs, generate, and export MP4 datasets in 2–5 minutes.
- Automatic backend connection and session management, including free starter credits for new users.
- Keyword/intent-based action routing for common dataset and export actions.
- Detailed error handling and format support for common video, audio, and image export types.
元数据
常见问题
Text To Video Dataset 是什么？
Turn a CSV file with 500 text prompt and video description pairs into 720p labeled video dataset just by typing what you need. Whether it's creating paired t... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 90 次。
如何安装 Text To Video Dataset？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-dataset」即可一键安装，无需额外配置。
Text To Video Dataset 是免费的吗？
是的，Text To Video Dataset 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Dataset 支持哪些平台？
Text To Video Dataset 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 Dataset？
由 tk8544-b（@tk8544-b）开发并维护，当前版本 v1.0.0。
推荐 Skills