← 返回 Skills 市场
Text To Video Ki
作者
vcarolxhberger
· GitHub ↗
· v1.0.0
· MIT-0
92
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-ki
功能描述
Turn a short paragraph describing a product launch scene into 1080p AI generated videos just by typing what you need. Whether it's generating videos from wri...
安全使用建议
This skill appears to do what it says: it sends your text and any media you provide to a remote video-rendering service (mega-api-prod.nemovideo.ai) and returns a downloadable video. Before installing or using it, consider: 1) Privacy — uploaded media will be sent to an external service; don't upload sensitive content unless you trust the service and its policies. 2) Token handling — the skill accepts a NEMO_TOKEN you provide or will obtain an anonymous token for you; providing your own token gives the service access tied to that token, while anonymous tokens have limited credits. 3) Metadata mismatch — the SKILL.md mentions a config path (~/.config/nemovideo/) that the registry metadata did not; this is likely benign but note the skill may read that folder. 4) Source trust — there is no homepage or known publisher in the registry entry; if you require stronger assurance, ask the publisher for a homepage, privacy policy, or source code before proceeding.
功能分析
Type: OpenClaw Skill
Name: text-to-video-ki
Version: 1.0.0
The skill provides a legitimate integration for an AI video generation service hosted at mega-api-prod.nemovideo.ai. It includes detailed instructions for the agent to manage authentication, session state, and video rendering workflows. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found; the behavior is consistent with the stated purpose of generating videos from text prompts.
能力评估
Purpose & Capability
Name/description, required credential (NEMO_TOKEN), and the SKILL.md behavior all align: the skill talks to a cloud video-rendering backend, uploads media, creates render jobs, polls for results, and returns download URLs. One inconsistency: the registry metadata lists no required config paths, but the SKILL.md frontmatter declares a configPaths entry (~/.config/nemovideo/). This is likely a metadata mismatch but not a functional mismatch with the stated purpose.
Instruction Scope
Instructions are concrete and scoped to cloud rendering: check NEMO_TOKEN, optionally obtain an anonymous token via an API call, create sessions, handle SSE, upload files, poll export status, and return download links. The skill will read/derive an install path to set an X-Skill-Platform header and references a user config directory. It does not instruct reading unrelated system files or other credentials. It will upload user-provided media to the remote service — expected for this functionality but a privacy consideration.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk or fetched by an installer. Lowest install risk.
Credentials
Only NEMO_TOKEN is declared as required and used as a Bearer token for API calls. The SKILL.md also supports generating an anonymous token if NEMO_TOKEN is absent (via a POST to the service). No unrelated secrets or multiple credentials are requested. The configPaths entry in the frontmatter (not reflected in registry metadata) suggests the skill may look in ~/.config/nemovideo/ for local state, which is plausible for this service but should be noted.
Persistence & Privilege
always is false and the skill is user-invocable; it does not demand forced inclusion or elevated platform privileges. The skill manages its own session and tokens for the remote service, which is normal for this type of integration.
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-ki - 安装完成后,直接呼叫该 Skill 的名称或使用
/text-to-video-ki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-ki, enabling users to generate 1080p AI videos from text prompts.
- Automatic cloud backend setup with support for anonymous session creation and free trial credits.
- Simple, chat-driven workflow to convert product launch or social content descriptions into ready-to-download MP4 videos.
- Supports video, audio, and text tracks, with intuitive handling of user prompts for export, credits, status, and uploads.
- Includes robust error handling, session management, and tips for best results.
元数据
常见问题
Text To Video Ki 是什么?
Turn a short paragraph describing a product launch scene into 1080p AI generated videos just by typing what you need. Whether it's generating videos from wri... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 92 次。
如何安装 Text To Video Ki?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-ki」即可一键安装,无需额外配置。
Text To Video Ki 是免费的吗?
是的,Text To Video Ki 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Text To Video Ki 支持哪些平台?
Text To Video Ki 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 Ki?
由 vcarolxhberger(@vcarolxhberger)开发并维护,当前版本 v1.0.0。
推荐 Skills