← 返回 Skills 市场
Text To Video Gemini
作者
linmillsd7
· GitHub ↗
· v1.0.0
· MIT-0
68
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-gemini
功能描述
generate text prompts into AI generated videos with this skill. Works with TXT, DOCX, PDF, plain text files up to 500MB. content creators use it for generati...
安全使用建议
What to consider before installing:
- Domain & provenance: the skill talks to mega-api-prod.nemovideo.ai but has no homepage/source listed; verify the service/operator and privacy/terms before sending content.
- Token behavior: the skill uses NEMO_TOKEN and will auto-request an anonymous token if none is present. Ask whether that anonymous token or any token is persisted to disk (e.g., in ~/.config/nemovideo/) before you install. Prefer ephemeral tokens if possible.
- File uploads: any file you give will be uploaded to the remote service. Do not upload sensitive documents, secrets, or private videos unless you trust the service and its retention policy.
- Install-path probing: the skill derives an X-Skill-Platform header by checking install paths. This leaks which agent/installation layout you use; if you dislike this fingerprinting, ask for it to be removed or sandbox the skill.
- Clarify the config-path mismatch: registry metadata said no config paths required but SKILL.md lists ~/.config/nemovideo/. Ask the author which is correct and whether anything will be written there.
- If you need higher assurance, request the skill's source or a privacy/security statement, run it only when explicitly invoked, and avoid granting broad persistent tokens until you confirm token storage/rotation policies.
功能分析
Type: OpenClaw Skill
Name: text-to-video-gemini
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. The SKILL.md file contains detailed, functional instructions for an AI agent to manage authentication, sessions, file uploads, and video rendering. It includes security-conscious directives, such as preventing the exposure of API tokens to the user, and provides comprehensive error handling and state management logic. While it performs minor environment fingerprinting to identify the host platform (e.g., checking for ~/.cursor/skills/), this behavior is transparently documented for API attribution purposes and does not constitute a security threat.
能力评估
Purpose & Capability
Name/description match the instructions: it connects to a NemoVideo cloud backend, creates sessions, uploads user files, streams SSE, and returns download URLs. Requested credential (NEMO_TOKEN) is appropriate. However, the SKILL.md metadata references a config path (~/.config/nemovideo/) while the registry metadata listed no required config paths — this mismatch is unexplained and worth clarifying.
Instruction Scope
Runtime instructions direct the agent to call https://mega-api-prod.nemovideo.ai endpoints (auth, session, upload, render, credits, state) and to POST multipart files or URLs you provide. It also instructs deriving an X-Skill-Platform header by probing install paths (e.g., ~/.clawhub), which requires inspecting local paths and thus leaks which platform/layout you use. The skill will auto-request an anonymous token if NEMO_TOKEN is absent. It does not instruct reading arbitrary system files beyond these behaviors, but file uploads and install-path detection are privacy-relevant.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing will be written to disk by an installer step. Lowest install risk from this angle.
Credentials
Only one environment credential is declared (NEMO_TOKEN), which is proportional for a cloud service. The skill will also obtain an anonymous token from the service if none is provided. The aforementioned inconsistency about a required config path (~/.config/nemovideo/) raises a question about whether the skill expects or will create on-disk config (and whether tokens might be persisted).
Persistence & Privilege
always:false and normal autonomous invocation settings. There is no claim to modify other skills or system-wide settings. The primary privilege is network access to the external API and the ability to upload files you provide.
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-gemini - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-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 Text to Video Gemini — generate videos from text prompts with easy cloud processing.
- Converts text prompts or documents (TXT, DOCX, PDF, up to 500MB) into AI-generated videos.
- Simple onboarding: automatic NEMO_TOKEN setup and session management for new users.
- Supports video editing actions (add tracks, overlays, BGM) and export to 1080p MP4.
- Exposes intuitive commands for upload, export, credits, and project status checks.
- Clear backend integration: real-time feedback, error handling, and multi-format export (video, audio, images).
元数据
常见问题
Text To Video Gemini 是什么？
generate text prompts into AI generated videos with this skill. Works with TXT, DOCX, PDF, plain text files up to 500MB. content creators use it for generati... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 68 次。
如何安装 Text To Video Gemini？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-gemini」即可一键安装，无需额外配置。
Text To Video Gemini 是免费的吗？
是的，Text To Video Gemini 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Gemini 支持哪些平台？
Text To Video 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 Text To Video Gemini？
由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。
推荐 Skills