← 返回 Skills 市场
71
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-image
功能描述
Turn a written description of a sunset over a mountain lake into 1080p AI-generated video just by typing what you need. Whether it's generating short video c...
安全使用建议
This skill appears to be a straightforward cloud text→video client, but exercise caution: it uploads files and uses a bearer token (NEMO_TOKEN) to a third-party domain (mega-api-prod.nemovideo.ai). The SKILL.md will generate an anonymous token if you don't provide one, and it may check local install/config paths to build attribution headers. Before installing, consider: (1) there is no homepage or known source — that reduces traceability and accountability; (2) do not upload sensitive or private media until you’ve verified the service's privacy policy; (3) prefer providing a dedicated, limited-scope token (or none) and rotate it if compromised; (4) test the skill with non-sensitive content first; (5) if you need to be extra cautious, request the skill author/source or prefer a vetted provider.
功能分析
Type: OpenClaw Skill
Name: text-to-video-image
Version: 1.0.0
The skill is a standard integration for the NemoVideo AI service, providing instructions for an agent to manage authentication and video generation tasks via the mega-api-prod.nemovideo.ai API. It includes legitimate session management, credit checking, and error handling logic consistent with its stated purpose. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description (text→video) align with the declared NEMO_TOKEN and the API endpoints in SKILL.md. However metadata also lists a config path (~/.config/nemovideo/) and the runtime asks to detect install paths to set X-Skill-Platform; detecting local install paths for attribution is not required for core video generation and is an extra capability that should be justified.
Instruction Scope
The instructions will: check an env var (NEMO_TOKEN), if missing call an anonymous-token API to obtain a token, create sessions, upload user files (multipart) to the remote service, stream SSE responses, and poll render endpoints. These actions are expected for a cloud render skill. Concerns: (1) the skill may read/inspect local install paths to set X-Skill-Platform, which requires filesystem checks outside the stated core task; (2) user files are uploaded to a third-party backend — this is expected but carries privacy/exfiltration risk; (3) the SKILL.md tells the agent not to expose tokens, but there is no technical enforcement — the agent could still leak tokens or API responses if misused.
Install Mechanism
Instruction-only skill with no install spec and no bundled code — lowest install risk. All network activity comes from runtime API calls described in SKILL.md.
Credentials
Only one required env var (NEMO_TOKEN) is declared, which is appropriate. The skill also declares a config path (~/.config/nemovideo/) in metadata and expects to detect install paths — those imply the skill may read local filesystem state beyond a single token env var. The fallback behavior (automatically requesting an anonymous token from nemovideo.ai when NEMO_TOKEN is absent) is reasonable but means the agent will make outbound network calls autonomously.
Persistence & Privilege
always is false and there are no install scripts or instructions to modify other skills or global agent settings. The skill can invoke autonomously (default), which increases blast radius but is normal for skills; combined with network/file access noted above this raises operational privacy considerations but not an outright privilege escalation.
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-image - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-image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
Text to Video Image 1.0.0 — initial release!
- Generate 1080p AI video clips from written text prompts in 30–90 seconds.
- No manual editing needed: just type your idea to get a rendered video.
- Automatic first-time cloud backend setup with token generation.
- Supports export to multiple formats (mp4, mov, avi, webm, gif, etc.).
- Rapid workflows: upload, generate, preview, and export, all in the same session.
元数据
常见问题
Text To Video Image 是什么？
Turn a written description of a sunset over a mountain lake into 1080p AI-generated video just by typing what you need. Whether it's generating short video c... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 71 次。
如何安装 Text To Video Image？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-image」即可一键安装，无需额外配置。
Text To Video Image 是免费的吗？
是的，Text To Video Image 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Image 支持哪些平台？
Text To Video Image 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 Image？
由 tk8544-b（@tk8544-b）开发并维护，当前版本 v1.0.0。
推荐 Skills