← 返回 Skills 市场
tk8544-b

Video Leonardo

作者 tk8544-b · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
54
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-leonardo
功能描述
Turn a product photo or text description into 1080p AI-generated video clips just by typing what you need. Whether it's generating short video clips from ima...
安全使用建议
This skill appears to do what it says: it uploads images/audio to the nemovideo service and returns rendered video URLs. Before installing or using it, consider: (1) Privacy — any media you send will be uploaded to https://mega-api-prod.nemovideo.ai; do not send private secrets or sensitive files. (2) Token provenance — only provide a NEMO_TOKEN you obtained from the legitimate service; if you don’t have one the skill will generate an anonymous token for you (7-day expiry). (3) Transparency — the skill asks to "keep technical details out of the chat," so verify where tokens are stored (the frontmatter mentions ~/.config/nemovideo/) and whether the agent will persist tokens or write files; confirm this behavior if you care about local storage. (4) Domain verification — the instructions target mega-api-prod.nemovideo.ai; if you plan to use this in production, verify that domain and API behavior with the vendor. (5) No install-time code is present to inspect, so behaviour is determined entirely by the SKILL.md; if you need stronger assurance, request a skill version that includes an auditable implementation or more explicit statements about token storage and telemetry.
功能分析
Type: OpenClaw Skill Name: video-leonardo Version: 1.0.0 The video-leonardo skill is a legitimate integration for generating AI videos using the nemovideo.ai API. The SKILL.md file provides clear instructions for the agent to manage sessions, handle file uploads, and poll for rendering status. It includes standard authentication logic, such as using an environment variable (NEMO_TOKEN) or fetching an anonymous starter token. There are no indicators of data exfiltration, malicious code execution, or harmful prompt injection; the requested permissions and network calls are strictly aligned with the stated purpose of video generation.
能力评估
Purpose & Capability
Name/description indicate remote AI video generation and the skill only requires a single API token (NEMO_TOKEN) and calls nemovideo API endpoints. The requested credential and network calls are consistent with the described purpose.
Instruction Scope
SKILL.md instructs establishing sessions, uploading user media, streaming SSE messages, starting renders, and polling status — all within the expected scope. Two items to note: (1) the frontmatter metadata includes a configPaths entry (~/.config/nemovideo/) even though the registry metadata listed no required config paths, which is an inconsistency to verify; (2) the instructions explicitly say to "keep the technical details out of the chat," which reduces visibility into authentication/communication steps and may make it harder for users to audit what the agent actually sends. Functionally, instructions do not request unrelated files or unrelated environment variables.
Install Mechanism
No install spec and no code files (instruction-only). This is low-risk from an install standpoint because nothing is written to disk by a packaged installer.
Credentials
Only a single service credential (NEMO_TOKEN) is required, which is proportional to a remote video-generation API. The skill will also create an anonymous token if none is present; this behavior is documented. There are no additional unrelated secrets requested.
Persistence & Privilege
The skill is not always-enabled, does not request persistent system privileges, and has no install-time operations. It does not request modification of other skills or system-wide settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install video-leonardo
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /video-leonardo 触发
  4. 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 Leonardo — generate 1080p video clips from product photos or text prompts in seconds. - Instantly turn images or text descriptions into server-rendered 1080p MP4 video clips. - Handles uploads of common media file types (images, video, audio). - Automatic backend session setup, with free trial credits if no API token is present. - Simple workflows for generating, editing, previewing, and exporting video. - Clear error handling and status updates throughout the pipeline. - Built-in support for querying credits, timeline state, and export status.
元数据
Slug video-leonardo
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Video Leonardo 是什么?

Turn a product photo or text description into 1080p AI-generated video clips just by typing what you need. Whether it's generating short video clips from ima... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 54 次。

如何安装 Video Leonardo?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-leonardo」即可一键安装,无需额外配置。

Video Leonardo 是免费的吗?

是的,Video Leonardo 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Video Leonardo 支持哪些平台?

Video Leonardo 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 Leonardo?

由 tk8544-b(@tk8544-b)开发并维护,当前版本 v1.0.0。

💬 留言讨论