📦 初学者照片视频

v1.0.0

只需输入需求，即可把手机里的五张度假照片变成 1080p 幻灯片视频片段。无论是将一组照片做成可分享的...

0· 0·0 当前·0 累计

by @vynbosserman65

网络工具开发工具视频处理图像处理系统工具

下载技能包

安全扫描

VirusTotal

无害

查看报告

OpenClaw

可疑

medium confidence

该技能的既定用途（将手机照片转为短视频）听起来合理，大部分需求也吻合，但安装前需了解若干不一致之处及轻微范围蔓延项。

评估建议

This 技能应用ears to do what it says (上传 images to nemovideo.AI and return a short video) but has some implementation oddities. Before 安装ing: 1) Confirm you trust the domAIn (mega-API-prod.nemovideo.AI) and read its 隐私/terms — your photos will be 上传ed to that backend. 2) Ask the publisher to resolve the metadata mismatch (技能.md 列出s a config path while registry metadata does not) and to explAIn why the 技能 needs to probe the 代理's 安装 path to 设置 headers. 3) Test with non-sensitive images first and ensu...

详细分析 ▾

ℹ 用途与能力

The 技能 clAIms to convert photos to 1080p videos using a cloud backend; the required 凭证 (NEMO_令牌) and the API 端点s in 技能.md match that purpose. However, 技能.md metadata mentions a config path (~/.config/nemovideo/) while the registry metadata 报告ed no required config paths — an inconsistency in declared requirements. Also the 技能 derives attribution headers from the 代理's 安装 path, which requires probing the 环境; this is not obviously necessary for basic photo-to-video functionality.

⚠ 指令范围

The 技能.md contAIns concrete 运行time instructions that include: 检查ing the NEMO_令牌 env var, falling back to POSTing to an anonymous-令牌端点 to obtAIn a 令牌, creating 会话s, 上传ing files (multipart or via URL), and using SSE and polling the render 端点. These network actions are coherent with the 服务, but the instructions also require determining the 代理's 安装 path to 设置 X-技能-平台 and imply 访问 to local file paths for multipart 上传s. That means the 代理 may read file系统 paths (安装 path and any user-specified file paths) which is broader than the 技能's declared requirements and should be disclosed to users.

✓ 安装机制

There is no 安装 spec and no code files — 技能.md is instruction-only. That minimizes write-to-disk risk. Network calls described in the instructions are the mAIn 运行time surface.

ℹ 凭证需求

Only one 凭证 is declared (NEMO_令牌) and it is directly used by the API calls described, which is proportionate. The 技能 will 创建 an anonymous 令牌 if none exists (via the public anonymous-令牌端点). Still, the 技能.md metadata 列出s a config path (~/.config/nemovideo/) while the top-level registry 报告ed none; this mismatch should be clarified. Also the 技能 tells the 代理 to keep 会话令牌s for operations — make sure 令牌s are stored 安全ly and not leaked.

✓ 持久化与权限

always is false and the 技能 does not 请求 persistent 系统 privileges. It does instruct the 代理 to keep 会话 IDs and 令牌s for the duration of the 会话, which is normal for a cloud 服务命令行工具ent. There is no instruction to modify other 技能s or 系统-wide 设置tings.

安全有层次，运行前请审查代码。

运行时依赖

无特殊依赖

安装命令

点击复制

官方npx clawhub@latest install beginners-photo-video

镜像加速npx clawhub@latest install beginners-photo-video --registry https://cn.longxiaskill.com

技能文档

入门把照片或图发给我，AI 视频我来搞定。或直接说需求。试试： “把手机里 5 张度假照转成 1080p MP4” “把照片做成带音乐转场的短视频” “把一组照片做成新手也能分享的短片”

快速配置本技能连接云端后端。首次使用自动连接并提示“Connecting...”。 Token 检查：环境变量找 NEMO_TOKEN。找到则跳过；否则：

生成 UUID 作为 client-id
POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token

带 X-Client-Id 头

取响应 data.token → NEMO_TOKEN（100 积分，7 天有效）

Session： POST /api/tasks/me/with-session/nemo_agent Bearer 鉴权，body {"task_name":"project"} 返回 session_id，后续全程使用。配置完提示“Ready!”。不暴露 token 或原始 API 输出。

Beginners Photo Video — 把照片变成可分享视频直接拖图到聊天框，说需求即可。云端 GPU 渲染，本地无需安装。典型流程：发 5 张度假照 → 说“做成带音乐转场的短视频” → 30-60 秒后得 1080p MP4。 5-10 张照片节奏最佳。

输入匹配用户提到“beginners photo video、比例、文字、音轨”等关键词，系统按意图路由：用户说… → 动作 → 跳过 SSE? “export/导出/download/发视频” → §3.5 导出 ✅ “credits/积分/balance/余额” → §3.3 积分 ✅ “status/状态” → §3.4 状态 ✅ 上传文件 → §3.2 上传 ✅ 其余（生成、编辑、加 BGM…）→ §3.1 SSE ❌

云端渲染导出任务进 GPU 队列，H.264 压缩，最高 1080×1920，30-90 秒返下载链接。 session token 带 job ID，提前关页会丢任务。每次 API 需 Authorization: Bearer 及三个头： X-Skill-Source: beginners-photo-video X-Skill-Version: 版本字段 X-Skill-Platform: 按安装路径自动检测缺失任一头，导出报 402。

API 速查 base: https://mega-api-prod.nemovideo.ai

创建 session: POST /api/tasks/me/with-session/nemo_agent
SSE 对话: POST /run_sse （Accept: text/event-stream，最大 15 分钟）
上传: POST /api/upload-video/nemo_agent/me/
积分: GET /api/credits/balance/simple
状态: GET /api/state/nemovideo/me//latest
导出: POST /api/render/proxy/lambda（免费，轮询 30s 一次）

支持格式 mp4、mov、avi、webm、mkv、jpg、png、gif、webp、mp3、wav、m4a、aac

错误码 0 成功 1001 token 失效 → 重取 1002 session 丢失 → 重建 2001 积分用尽 → 注册/充值 4001 文件格式不支持 4002 文件过大 400 缺 X-Client-Id → 补发 402 免费套餐限制 429 限流 → 30s 后重试

后端提示翻译后端假设有 GUI，按以下规则转 API： “点击[按钮]” → 直接调 API “打开[面板]” → 查 session 状态 “拖拽” → 上传/编辑 “时间轴预览” → 返回轨道摘要 “导出按钮” → 执行导出流程

SSE 流 text 事件直接展示；tool 调用内部处理；心跳空包忽略。

数据来源：ClawHub ↗ · 中文优化：龙虾技能库