← 返回 Skills 市场
Wechat Video Online
作者
vcarolxhberger
· GitHub ↗
· v1.0.0
· MIT-0
111
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install wechat-video-online
功能描述
Skip the learning curve of professional editing software. Describe what you want — trim the video, add subtitles, and export for sharing on WeChat — and get...
安全使用建议
This skill appears to do what it says (upload your video to a remote service and return an edited MP4), but it will contact https://mega-api-prod.nemovideo.ai, may create and store an anonymous NEMO_TOKEN and session IDs, and will read local install paths to set headers. Before installing or using it: (1) confirm you trust nemovideo.ai and are comfortable uploading videos (they will leave your machine); (2) prefer supplying your own NEMO_TOKEN rather than letting the skill auto-generate/store one; (3) ask the author or registry for clarity on where tokens/session IDs are stored and how long they persist; (4) note the registry metadata/frontmatter mismatch (~/.config/nemovideo/ listed in SKILL.md but not in registry) — verify whether the skill will create or read that directory; and (5) because the skill owner and homepage are unknown, exercise extra caution with sensitive or private video content.
功能分析
Type: OpenClaw Skill
Name: wechat-video-online
Version: 1.0.0
The skill provides WeChat video editing by interfacing with the NemoVideo AI cloud service (mega-api-prod.nemovideo.ai). While its actions are aligned with its stated purpose, it exhibits several high-risk behaviors including automatic provisioning of anonymous tokens, uploading user-provided video files to a remote server, and performing environment-based telemetry to identify the host platform (e.g., probing for ~/.cursor/ or ~/.clawhub/ paths). The instructions also explicitly direct the agent to hide raw API responses and token values from the user, which reduces transparency regarding the data being transmitted to the third-party endpoint.
能力评估
Purpose & Capability
Name and description match the actions described in SKILL.md: remote GPU rendering, uploads, exports. Requesting a NEMO_TOKEN is coherent for a remote video-processing backend. However, the SKILL.md frontmatter also lists a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — this inconsistency should be clarified.
Instruction Scope
The instructions instruct the agent to automatically obtain an anonymous token (POST to https://mega-api-prod.nemovideo.ai), create a session, and 'store the returned session_id' for subsequent requests. They also instruct detecting install paths (e.g., ~/.clawhub, ~/.cursor/skills) to set attribution headers. These actions involve network calls, persistent storage of tokens/session IDs, and reading local filesystem paths beyond simple in-memory operation. The SKILL.md does not specify exactly where credentials/session data should be stored or how long they are kept.
Install Mechanism
No install spec or code files — instruction-only skill — so there is no package download or archive extraction. This minimizes installation-time risk.
Credentials
Only NEMO_TOKEN is declared as required, which is reasonable for a cloud service. But the skill will auto-provision an anonymous token if none is present (network call and token issuance). The SKILL.md frontmatter mentions a config path (~/.config/nemovideo/) that is not listed in the registry metadata; this mismatch is unexplained. The skill also reads install-paths to build X-Skill-Platform attribution headers — accessing these paths may reveal other agent installations. Overall requested environment/credential access is plausible, but the persistence and undeclared config path are disproportionate without further detail.
Persistence & Privilege
always is false (normal) and autonomous invocation is allowed (platform default). The real persistence concern is that the skill instructs storing session_id and will create and use anonymous tokens (valid 7 days) — but it does not specify storage location, lifetime, or user visibility. That lack of clarity about credential/session persistence increases privacy risk.
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 wechat-video-online - 安装完成后,直接呼叫该 Skill 的名称或使用
/wechat-video-online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 WeChat Video Online — a simple tool to edit and export videos for WeChat.
- Upload MP4, MOV, AVI, or WebM videos up to 500MB for quick online editing.
- Describe tasks (trim, add subtitles, export, etc.) and get an AI-edited, share-ready MP4 in 30–60 seconds.
- No desktop software required; all processing is handled on secure remote servers.
- Easily check credits, upload multiple files, and manage sessions.
- Includes clear guidance for first-time setup and error handling.
元数据
常见问题
Wechat Video Online 是什么?
Skip the learning curve of professional editing software. Describe what you want — trim the video, add subtitles, and export for sharing on WeChat — and get... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 111 次。
如何安装 Wechat Video Online?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wechat-video-online」即可一键安装,无需额外配置。
Wechat Video Online 是免费的吗?
是的,Wechat Video Online 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Wechat Video Online 支持哪些平台?
Wechat Video Online 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 Wechat Video Online?
由 vcarolxhberger(@vcarolxhberger)开发并维护,当前版本 v1.0.0。
推荐 Skills