← 返回 Skills 市场
Photo Maker
作者
susan4731-wilfordf
· GitHub ↗
· v1.0.0
· MIT-0
100
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install photo-maker
功能描述
Skip the learning curve of professional editing software. Describe what you want — turn my photos into a slideshow video with music and transitions — and get...
安全使用建议
What to consider before installing:
- This skill uploads your photos to a third-party service (mega-api-prod.nemovideo.ai). Do not use it for private or sensitive images unless you trust the service and its retention/privacy policies.
- You can supply your own NEMO_TOKEN (preferred). If you don't, the skill will automatically request an anonymous token on your behalf (100 free credits, 7-day expiry), which creates network traffic to that API and results in a short-lived credential being used.
- The skill's instructions tell the agent to probe certain filesystem locations to detect the platform and to read the skill's YAML frontmatter; this is not essential for core functionality and expands the set of files the agent will examine. If you want to limit file access, ask for clarification or deny filesystem probing.
- There is a metadata inconsistency: the registry summary lists no required config paths but the SKILL.md frontmatter references ~/.config/nemovideo/. Ask the author to confirm whether the skill needs access to that path.
- If you decide to use it, prefer creating/using an account token you control (NEMO_TOKEN) rather than relying on anonymous token generation, and verify the service's privacy/retention policy for uploaded media. If you need higher assurance, request source or a vetted official integration before sending sensitive material.
功能分析
Type: OpenClaw Skill
Name: photo-maker
Version: 1.0.0
The photo-maker skill is a legitimate integration for the nemovideo.ai cloud video rendering service. The SKILL.md file provides detailed instructions for the AI agent to manage authentication (including fetching anonymous tokens), handle file uploads, and poll for video rendering status via a cloud API. While it instructs the agent to detect its installation path for telemetry headers (X-Skill-Platform), this behavior is transparently documented and aligned with the tool's stated purpose of providing a simplified video creation interface.
能力评估
Purpose & Capability
The name/description (turn photos into videos) aligns with the instructions: calls to a cloud render API, upload endpoints, export and status endpoints, and a single service token (NEMO_TOKEN) are expected for this purpose.
Instruction Scope
The SKILL.md instructs the agent to upload user files and exchange SSE messages with the external API — expected. It also instructs the agent to read this file's YAML frontmatter and to detect the agent install path (~/.clawhub/, ~/.cursor/skills/) at runtime to set an X-Skill-Platform header. That file-system probing is not strictly necessary for core function and expands the skill's runtime scope (it may require reading agent paths). The doc also contains an automated anonymous-token flow (POST to /api/auth/anonymous-token) if NEMO_TOKEN is absent, which will cause outbound network traffic and issuance/storage of short-lived tokens.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only. This minimizes install-time risk because nothing is downloaded or written by an installer.
Credentials
Declared primary credential is NEMO_TOKEN which is proportionate to a cloud rendering service. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) and instructs reading install paths for platform detection; the registry metadata summary provided earlier said 'Required config paths: none'. This mismatch (declared vs. frontmatter) is an inconsistency to clarify. Otherwise the skill does not request unrelated credentials.
Persistence & Privilege
always:false (default) and no install-time persistence is requested. The skill does not request to modify other skills or system-wide agent settings. It will, however, create session state on the remote service and may store short-lived tokens client-side during the session, per the anonymous-token flow described.
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-maker - 安装完成后，直接呼叫该 Skill 的名称或使用
/photo-maker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 Maker — instantly turn your photos into slideshow videos with music and transitions.
- Simple upload: supports JPG, PNG, WEBP, HEIC images up to 200MB each.
- No editing software required; describe your vision and get a 1080p MP4 back in 30–60 seconds.
- Automatic token and session handling for seamless cloud video processing.
- Export, status, credits, and other commands via natural prompts in multiple languages.
- Ideal for social creators wanting quick, polished photo videos without a learning curve.
元数据
常见问题
Photo Maker 是什么？
Skip the learning curve of professional editing software. Describe what you want — turn my photos into a slideshow video with music and transitions — and get... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 100 次。
如何安装 Photo Maker？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install photo-maker」即可一键安装，无需额外配置。
Photo Maker 是免费的吗？
是的，Photo Maker 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Photo Maker 支持哪些平台？
Photo Maker 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 Maker？
由 susan4731-wilfordf（@susan4731-wilfordf）开发并维护，当前版本 v1.0.0。
推荐 Skills