← 返回 Skills 市场
Wan Ai
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
95
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install wan-ai
功能描述
Turn your ideas into cinematic video clips with wan-ai, the powerful video generation model built for creators who need results fast. wan-ai transforms text...
安全使用建议
This skill behaves like a standard cloud video-generation integration: it needs a NEMO_TOKEN (or will obtain an anonymous short-lived token) and will send your prompts and any files you upload to the nemovideo API (mega-api-prod.nemovideo.ai). Before installing, consider whether you trust that third-party service and its privacy/terms; avoid uploading sensitive personal or proprietary files unless you accept they will be transmitted to that service. Note the SKILL.md frontmatter references a local config path (~/.config/nemovideo/) and asks the agent to detect its install path for attribution — this is a minor metadata inconsistency with the registry but not itself malicious. If you want tighter control, create a limited-purpose API token for this skill or refrain from providing sensitive uploads.
功能分析
Type: OpenClaw Skill
Name: wan-ai
Version: 1.0.0
The skill is a legitimate integration for the WAN AI video generation service via the nemovideo.ai API. It provides structured instructions for the agent to handle authentication (including an anonymous token flow), session management, and media uploads. The instructions include security best practices, such as advising the agent not to print raw tokens or JSON to the user, and there is no evidence of data exfiltration, malicious execution, or unauthorized access to sensitive local files.
能力评估
Purpose & Capability
Name/description (WAN AI video generation) align with the runtime instructions and API endpoints (nemovideo/mega-api-prod.nemovideo.ai). Requiring NEMO_TOKEN is appropriate for an API-backed generator and the skill documents session, SSE, upload, export, and credits endpoints that match the stated purpose.
Instruction Scope
SKILL.md instructs the agent to use NEMO_TOKEN (or obtain a short-lived anonymous token via the service), create sessions, send SSE messages, and upload user files — all consistent with a cloud video service. It also instructs the agent to detect install path for an attribution header and references a config path (~/.config/nemovideo/) in the frontmatter; this is a minor inconsistency with the registry metadata (the registry listed no required config paths). The instructions do involve sending user-provided files and prompts to an external API (expected), so users should expect their uploads and prompts to be transmitted to that third party.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk installation footprint. There is no download/execute/install step that would write arbitrary code to disk.
Credentials
Only one environment variable is declared (NEMO_TOKEN) and is used as the primary credential, which is proportional to the service. Note: if NEMO_TOKEN is missing the skill will request an anonymous token from the vendor (100 credits, 7-day expiry). The token grants access to the service and to actions like uploads, generation, export, and credit queries, so treat it like any API key.
Persistence & Privilege
always:false and no persistent installers or hooks are requested. The skill does direct the agent to store session_id locally during a session (expected) but does not request global agent configuration changes or permanent system 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 wan-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/wan-ai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
WAN AI Video Generator skill v1.0.0
- Initial release, enabling fast AI video generation from text prompts and image inputs.
- Supports seamless text-to-video, image-to-video, and style transfer workflows with automatic routing.
- Built-in session and authentication setup; handles token retrieval, session management, and connection status feedback.
- Integrated with WAN AI cloud API for distributed, high-quality video creation and media export.
- User-friendly error handling with clear status messages and re-authentication flow.
- Supports a wide range of video and audio formats, auto-summarizes editing changes, and provides credit and status tracking.
元数据
常见问题
Wan Ai 是什么？
Turn your ideas into cinematic video clips with wan-ai, the powerful video generation model built for creators who need results fast. wan-ai transforms text... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 95 次。
如何安装 Wan Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wan-ai」即可一键安装，无需额外配置。
Wan Ai 是免费的吗？
是的，Wan Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Wan Ai 支持哪些平台？
Wan Ai 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 Wan Ai？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills