← 返回 Skills 市场
Photo Video Maker Arabic
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 photo-video-maker-arabic
功能描述
turn photos and images into Arabic slideshow video with this photo-video-maker-arabic skill. Works with JPG, PNG, HEIC, WebP files up to 200MB. Arabic-speaki...
安全使用建议
This skill appears to be what it claims (a cloud photo-to-video service) but has a few inconsistencies to clarify before use: 1) Confirm whether the skill will read/write ~/.config/nemovideo/ (frontmatter mentions it but registry metadata did not). 2) Understand token handling: the skill can create an anonymous NEMO_TOKEN itself, so you should avoid pasting a long-lived or privileged token unless you trust nemovideo.ai. 3) Ask where session_id and any persisted tokens are stored and whether they are protected. 4) Review their privacy/terms for uploading images to an external service — uploaded images and generated tokens will be sent to mega-api-prod.nemovideo.ai. If these answers are satisfactory, the skill's behavior is coherent enough to use; if not, treat it as untrusted and do not supply existing credentials or sensitive images.
功能分析
Type: OpenClaw Skill
Name: photo-video-maker-arabic
Version: 1.0.0
The skill is a functional API wrapper for the Nemo Video service (nemovideo.ai), designed to convert images into Arabic slideshow videos. It follows standard integration patterns, including authentication via the NEMO_TOKEN environment variable, session management, and file uploads to mega-api-prod.nemovideo.ai. The instructions in SKILL.md are consistent with the stated purpose, include proper error handling, and explicitly advise the agent not to expose sensitive tokens or raw API output.
能力评估
Purpose & Capability
Name/description align with the runtime instructions: it talks to a nemovideo cloud API to render Arabic slideshow videos and accepts image uploads. Requesting a NEMO_TOKEN credential is expected for that backend. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — this mismatch is unexplained and worth confirming.
Instruction Scope
SKILL.md gives precise API calls (auth, session creation, SSE, upload, export). It instructs the agent to look for NEMO_TOKEN or otherwise call the anonymous-token endpoint to obtain one, to generate/store session_id, and to upload files (multipart or URL). These steps are within the skill's purpose. Two scope items to double-check: (1) the skill expects to auto-detect an install path to set X-Skill-Platform (may require reading agent or filesystem paths), and (2) the frontmatter's config path suggests the skill might read/write ~/.config/nemovideo/, but the instructions do not explicitly say where session tokens are persisted — confirm whether the skill will read/write that path.
Install Mechanism
This is instruction-only with no install spec and no code files, so nothing will be downloaded or written by an installer step. That is the lowest install risk.
Credentials
The only declared credential is NEMO_TOKEN, which is appropriate for a cloud-rendering backend. However: (a) SKILL.md will generate an anonymous token itself if NEMO_TOKEN is absent, so requiring NEMO_TOKEN as 'required' is inconsistent with the behavior described; (b) frontmatter lists a user config path (~/.config/nemovideo/) which would grant access to local config and possibly persisted tokens — this was not declared in the registry metadata and is not justified in the instructions. Both points should be clarified before trusting the skill with existing tokens or allowing it to access that config folder.
Persistence & Privilege
always:false (default) and no install script — good. The skill instructs keeping session_id for operations and may persist session state (implied by config path). This is reasonable for a session-based cloud service, but you should confirm where and how session or token data are stored and whether the skill will write into ~/.config/nemovideo/ or other locations.
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 photo-video-maker-arabic - 安装完成后，直接呼叫该 Skill 的名称或使用
/photo-video-maker-arabic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 Photo Video Maker Arabic — Turn Photos into Arabic Videos:
- Allows users to turn JPG, PNG, HEIC, and WebP images into 1080p Arabic-captioned slideshow videos.
- Cloud-based processing with easy upload and automated setup—no local installation required.
- Session and authentication handled transparently; guides users through token generation if needed.
- Supports exporting videos as MP4, plus project management, status tracking, and credits check.
- Error handling for common scenarios (token expiry, file issues, export limitations, etc.).
- Designed for Arabic-speaking content creators on social media.
元数据
常见问题
Photo Video Maker Arabic 是什么？
turn photos and images into Arabic slideshow video with this photo-video-maker-arabic skill. Works with JPG, PNG, HEIC, WebP files up to 200MB. Arabic-speaki... 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 Photo Video Maker Arabic？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install photo-video-maker-arabic」即可一键安装，无需额外配置。
Photo Video Maker Arabic 是免费的吗？
是的，Photo Video Maker Arabic 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Photo Video Maker Arabic 支持哪些平台？
Photo Video Maker Arabic 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 Photo Video Maker Arabic？
由 vcarolxhberger（@vcarolxhberger）开发并维护，当前版本 v1.0.0。
推荐 Skills