← 返回 Skills 市场
66
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-ai-video
功能描述
Skip the learning curve of professional editing software. Describe what you want — turn this text into a 30-second explainer video with visuals and voiceover...
安全使用建议
This skill will send whatever text and files you provide to an external service (https://mega-api-prod.nemovideo.ai) for processing and will include an API token in requests. The registry declares NEMO_TOKEN as required but the skill will instead obtain an anonymous token automatically if you don't provide one — decide whether you want to supply your own token or rely on the anonymous flow. Before installing, consider: 1) Do you trust the external service and its privacy/data retention policy for any text or files (including proprietary content) you upload? 2) If using your own NEMO_TOKEN, ensure that token's scope is limited and revocable. 3) Be aware of credit/usage limits and any billing or rate-limit behaviors described in the skill. 4) The metadata lists a config path (~/.config/nemovideo/) — verify whether the skill will actually read local config files if that matters to you. If you need higher assurance, request more details from the skill author (why the env/config mismatch, data retention policy, and whether uploads are stored long-term).
功能分析
Type: OpenClaw Skill
Name: text-to-ai-video
Version: 1.0.0
The skill is a functional integration for an AI video generation service hosted at mega-api-prod.nemovideo.ai. It provides the agent with clear instructions for session management, file uploads, and polling for video rendering results. There are no indicators of data exfiltration, malicious execution, or harmful prompt injection; the automated token acquisition and platform detection are consistent with the stated purpose of providing a seamless 'Quick Start' experience for the service.
能力评估
Purpose & Capability
The skill's name/description (text→video via a cloud backend) matches the API endpoints and actions described. However the registry metadata marks NEMO_TOKEN as a required env var and declares a config path (~/.config/nemovideo/) even though the runtime instructions implement an anonymous-token acquisition flow when NEMO_TOKEN is absent and do not read the declared config path. This is an inconsistency (why declare a required env var/config path if the skill can obtain an anon token and doesn't read that path?).
Instruction Scope
SKILL.md confines actions to the stated purpose: creating sessions, sending SSE messages, uploading files or URLs, polling render status, and asking for credits/state. It explicitly instructs network requests to the nemo API and to include specific headers. It does not instruct reading unrelated system files or other credentials. The only scope oddity is the requirement to auto-detect an install path for X-Skill-Platform and the metadata config path, which are mentioned but not clearly required for core functionality.
Install Mechanism
This is an instruction-only skill with no install spec or code files — lowest-risk install mechanism. Nothing is written to disk by the skill itself per the provided instructions.
Credentials
Only one credential is declared (NEMO_TOKEN), which is appropriate for a cloud video API. But the skill's runtime allows creating an anonymous token if NEMO_TOKEN is missing, which conflicts with the 'required env var' declaration. The metadata also lists a config path that the instructions don't use; this could be a benign metadata artifact but is disproportionate unless the skill actually reads that path.
Persistence & Privilege
Skill is not always-enabled and is user-invocable; it does not request system-wide changes or alter other skills. It creates and holds a session token for the cloud service (expected behavior) but does not request elevated persistence 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-ai-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-ai-video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 AI Video skill.
- Instantly generates explainer videos from text prompts with visuals and voiceover.
- Supports input via TXT, DOCX, PDF, or pasted text (up to 500MB).
- No editing experience required; cloud GPU processing delivers 30s videos in 1–2 minutes.
- Automatic setup with anonymous token (100 free credits); manages sessions and cloud export.
- Exports in multiple formats (MP4, MOV, GIF, audio, image); 1080p output by default.
- Designed for marketers, content creators, and educators who want fast video creation without technical overhead.
元数据
常见问题
Text To Ai Video 是什么？
Skip the learning curve of professional editing software. Describe what you want — turn this text into a 30-second explainer video with visuals and voiceover... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 66 次。
如何安装 Text To Ai Video？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-ai-video」即可一键安装，无需额外配置。
Text To Ai Video 是免费的吗？
是的，Text To Ai Video 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Ai Video 支持哪些平台？
Text To Ai Video 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 Ai Video？
由 mory128（@mory128）开发并维护，当前版本 v1.0.0。
推荐 Skills