← 返回 Skills 市场
Text To Video Io
作者
vynbosserman65
· GitHub ↗
· v1.0.0
· MIT-0
81
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-io
功能描述
Get AI generated videos ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, SRT, up to 200MB), say something like "tur...
安全使用建议
This skill appears to really target a text→video backend and only asks for a single API token, but you should: (1) verify you trust the API host (mega-api-prod.nemovideo.ai) and the developer because there is no source/homepage listed; (2) confirm you are comfortable the agent may read install paths or the skill file frontmatter (the SKILL.md directs that); (3) be cautious about letting the agent access arbitrary local files — when uploading, prefer sending files through the UI rather than letting the agent reference local filesystem paths; (4) note the registry/frontmatter mismatch about a config path (~/.config/nemovideo/) and ask the maintainer to clarify; (5) if you need stronger assurance, request the skill's source or a homepage and avoid installing until you can inspect how tokens are stored/used.
功能分析
Type: OpenClaw Skill
Name: text-to-video-io
Version: 1.0.0
The skill is a legitimate integration for the NemoVideo AI service (mega-api-prod.nemovideo.ai), allowing users to generate videos from text prompts. It includes standard API interaction logic for authentication (including an anonymous token flow), session management, file uploads, and video rendering. The instructions in SKILL.md are well-defined and align with the stated purpose of converting text to video, with no evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
The declared primary environment variable (NEMO_TOKEN) and the documented API endpoints are coherent with a cloud text→video service. However the SKILL.md frontmatter also lists a config path (~/.config/nemovideo/) that the registry metadata did not list, which is an internal inconsistency worth clarifying.
Instruction Scope
Runtime instructions ask the agent to: detect install path (reading local paths), read the skill's YAML frontmatter for headers, and include an example of multipart upload using files=@/path. These items imply filesystem access and automatic token generation/management beyond just relaying user-uploaded files. While each action can be reasonable for this service, they expand the agent's runtime scope and could lead to unintended local file access if not constrained.
Install Mechanism
No install spec and no code files — instruction-only skills present a lower install-time risk because nothing is downloaded or written to disk by an installer.
Credentials
Only NEMO_TOKEN is required, which fits the described API usage. The skill also instructs creating an anonymous token when none is present — reasonable for unauthenticated use — but this behavior means the skill will make outbound network calls to obtain credentials and may persist/use that token.
Persistence & Privilege
always is false and there is no instruction to modify other skills or system-wide config. The skill requests only session-level interaction with the backend, not elevated platform privileges.
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-io - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-io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 IO.
- Instantly convert text prompts (TXT, DOCX, PDF, SRT) into AI-generated videos with visuals and background music.
- Simple workflow: upload text, describe your video, and download ready-to-use 1080p MP4s—no editing required.
- Session-based API integration with automatic handling of authentication, token renewal, and session creation.
- Built-in support for status checking, credit balance, video export, and file uploads up to 200MB.
- Clear error handling and guided user feedback for common issues.
- Designed for marketers, content creators, and educators seeking quick AI video creation at scale.
元数据
常见问题
Text To Video Io 是什么？
Get AI generated videos ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, SRT, up to 200MB), say something like "tur... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 81 次。
如何安装 Text To Video Io？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-io」即可一键安装，无需额外配置。
Text To Video Io 是免费的吗？
是的，Text To Video Io 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Io 支持哪些平台？
Text To Video Io 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 Io？
由 vynbosserman65（@vynbosserman65）开发并维护，当前版本 v1.0.0。
推荐 Skills