← 返回 Skills 市场
Video Generator Free Gemini
作者
vcarolxhberger
· GitHub ↗
· v1.0.0
· MIT-0
70
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-generator-free-gemini
功能描述
Turn a short text prompt describing a 30-second explainer video into 1080p AI-generated videos just by typing what you need. Whether it's generating videos f...
安全使用建议
This skill uploads your text, scripts, and any files you provide to an external service (mega-api-prod.nemovideo.ai) for rendering — expect that content to be processed off your machine. Before installing or using it: 1) Confirm you trust nemovideo.ai (privacy, retention, and terms), 2) Understand that NEMO_TOKEN is the credential controlling access — the skill can also create an anonymous short-lived token if none is present, so the registry claiming NEMO_TOKEN is “required” is misleading, 3) Ask the author to clarify the ‘Gemini’ branding vs the nemovideo API, and to correct the metadata inconsistencies (declared configPaths / required env vars), 4) Avoid uploading sensitive content until you verify the service and its data-handling policy. If you need stronger assurance, request source code, a homepage/maintainer identity, or run the integration in a restricted environment/account.
功能分析
Type: OpenClaw Skill
Name: video-generator-free-gemini
Version: 1.0.0
The skill facilitates video generation via a remote API (nemovideo.ai) but includes instructions that establish a potential remote command-and-control (C2) pattern. Specifically, SKILL.md directs the agent to process 'tool calls' from a Server-Sent Events (SSE) stream 'internally' and 'don't forward' them to the user, which could be used to hide unauthorized actions. It also performs environment fingerprinting by checking installation paths (e.g., ~/.cursor/skills/) and automatically initiates network connections to fetch tokens and create sessions on first interaction. While these behaviors might support complex AI interactions, the combination of stealthy execution and environment discovery is high-risk.
能力评估
Purpose & Capability
The skill's name/description promise is a text→video generator. The runtime instructions consistently call a nemovideo cloud API (https://mega-api-prod.nemovideo.ai) and require a NEMO_TOKEN, which is coherent with a cloud rendering service. Minor mismatch: the visible marketing repeatedly references “Gemini AI” while the API endpoints are for nemovideo.ai — this could be just branding/implementation detail but the skill does not explain the relationship.
Instruction Scope
Instructions direct the agent to authenticate (either using NEMO_TOKEN or by requesting an anonymous token), create a session, upload user files (multipart or URLs), run SSE streaming endpoints, poll render status, and return download URLs. These actions are expected for a video-rendering skill, but they also mean user scripts/media are transmitted to an external service. The SKILL.md also instructs the agent to read this file's YAML frontmatter at runtime and detect install path(s) to populate attribution headers — that requires reading local skill files and probing install locations. Also: the registry metadata lists NEMO_TOKEN as required, but the instructions provide an anonymous-token flow if NEMO_TOKEN is not set, which is an inconsistency in declared vs actual runtime requirements.
Install Mechanism
No install spec and no code files — instruction-only skill. That minimizes on-disk changes and install-time risk.
Credentials
Only one credential is declared (NEMO_TOKEN), which is appropriate for a cloud API. However the SKILL.md frontmatter includes a config path (~/.config/nemovideo/) while the registry metadata earlier showed no configPaths — another small inconsistency. Also, although NEMO_TOKEN is declared as required, the instructions implement an anonymous-token flow when the variable is absent, so the variable is not strictly necessary; this mismatch should be corrected or clarified by the author.
Persistence & Privilege
always is false, the skill is user-invocable and allowed to be called autonomously (platform default). The skill does instruct saving session_id/token in-session for operation but does not request system-wide configuration or modify other skills.
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 video-generator-free-gemini - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-generator-free-gemini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 Video Generator Free Gemini skill.
- Generate 1080p AI-powered explainer videos from short text prompts using Gemini AI.
- Simple workflow: type your request, connect, and receive a download link in 1–2 minutes.
- Seamless session setup with free, expiring token support; no account needed for first 100 credits.
- Supports uploads, timeline previews, edits via keyword actions, and easy export of MP4 and other media formats.
- Built-in error handling and clear, text-based summaries for session and video state.
元数据
常见问题
Video Generator Free Gemini 是什么？
Turn a short text prompt describing a 30-second explainer video into 1080p AI-generated videos just by typing what you need. Whether it's generating videos f... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 70 次。
如何安装 Video Generator Free Gemini？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-generator-free-gemini」即可一键安装，无需额外配置。
Video Generator Free Gemini 是免费的吗？
是的，Video Generator Free Gemini 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Generator Free Gemini 支持哪些平台？
Video Generator Free Gemini 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 Video Generator Free Gemini？
由 vcarolxhberger（@vcarolxhberger）开发并维护，当前版本 v1.0.0。
推荐 Skills