← 返回 Skills 市场
wuchhao

Qwen Wan 2.6 Video Generation

作者 wuchhao · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
372
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install qwen-wan-video
功能描述
直接调用通义万相2.6视频生成模型(Qwen Wan 2.6),支持文生视频和图生视频,无需中间API代理。适用于需要直接对接阿里云大模型的视频创作场景。
安全使用建议
This skill appears to implement direct calls to Aliyun DashScope for Qwen Wan 2.6 video generation, which is consistent with its description — but the package metadata omits a required secret and some packaging is sloppy. Before installing: (1) do not supply high-privilege or long-lived credentials — create a scoped/test DASHSCOPE_API_KEY with the minimal permissions. (2) Verify you trust the source (no homepage or author verification provided). (3) Run the code in an isolated environment (sandbox/container) and ensure the Python 'requests' library is available. (4) Expect the skill to fail unless you set DASHSCOPE_API_KEY; ask the publisher to update the registry metadata to declare the required environment variable and to provide clear dependency/install instructions. If you cannot verify the author or restrict the API key, treat this as risky and avoid providing production credentials.
功能分析
Type: OpenClaw Skill Name: qwen-wan-video Version: 1.0.0 The skill bundle provides a straightforward integration with the Alibaba DashScope API for Qwen Wan 2.6 video generation. The Python script (scripts/qwen_wan_client.py) correctly handles API authentication via environment variables and communicates only with the official Alibaba endpoint (dashscope.aliyuncs.com) to manage video generation tasks.
能力评估
Purpose & Capability
The SKILL.md and Python client both implement direct calls to Aliyun DashScope for video generation, which matches the skill name/description. However the registry metadata claims no required environment variables or primary credential while the code and docs clearly require DASHSCOPE_API_KEY; that mismatch is an integrity concern (likely sloppy packaging or metadata omission).
Instruction Scope
Runtime instructions and the Python client limit activity to creating/polling video tasks against https://dashscope.aliyuncs.com and returning task result URLs. There are no instructions to read unrelated local files or to transmit data to unexpected endpoints beyond the listed DashScope API and user-supplied image URLs.
Install Mechanism
This is instruction-only (no installer), so nothing is downloaded at install time. Minor packaging inconsistencies: a package.json (Node metadata) is present while the shipped client is Python; the Python script uses the 'requests' library but no Python dependency list or install spec is provided, which may lead to runtime failures.
Credentials
The Python client requires a DASHSCOPE_API_KEY (used as a Bearer token) and the SKILL.md shows how to set it, but the registry metadata does not declare any required env vars or primary credential. The omission hides that a secret token is needed; users should confirm the required key and restrict its scope before supplying it.
Persistence & Privilege
The skill does not request permanent/always-on inclusion, does not declare config paths, and does not modify other skills or system settings. Autonomous invocation is allowed by default (normal for skills) but is not combined with other privilege escalations here.
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 qwen-wan-video
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /qwen-wan-video 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 qwen-wan-video skill. - Supports direct use of Alibaba Cloud Qwen Wan 2.6 text-to-video and image-to-video generation, without a proxy API. - Enables creation of short, high-quality videos from text prompts or images, with professional controls for parameters like depth of field and camera movement. - Handles long-running tasks asynchronously, including automatic polling and result retrieval. - Includes clear environment configuration steps and usage examples in Python.
元数据
Slug qwen-wan-video
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Qwen Wan 2.6 Video Generation 是什么?

直接调用通义万相2.6视频生成模型(Qwen Wan 2.6),支持文生视频和图生视频,无需中间API代理。适用于需要直接对接阿里云大模型的视频创作场景。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 372 次。

如何安装 Qwen Wan 2.6 Video Generation?

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

Qwen Wan 2.6 Video Generation 是免费的吗?

是的,Qwen Wan 2.6 Video Generation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Qwen Wan 2.6 Video Generation 支持哪些平台?

Qwen Wan 2.6 Video Generation 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 Qwen Wan 2.6 Video Generation?

由 wuchhao(@wuchhao)开发并维护,当前版本 v1.0.0。

💬 留言讨论