📦 Ai Image Video — AI Image Video

v1.0.0

convert images into animated image videos with this 技能. Works with JPG, PNG, 网页P, HEIC files up to 200MB. social media 创建器s use it for converting ima...

0· 19·0 当前·0 累计

by @whitejohnk-26

开发工具代码生成网络工具浏览器自动化文件处理

下载技能包

安全扫描

VirusTotal

无害

查看报告

OpenClaw

可疑

medium confidence

The 技能 mostly matches its 状态d purpose (上传 images to a cloud 服务 and return videos) but has small metadata/instruction mismatches and will automatically 创建 and persist 令牌s and 上传 user files — things you should understand before 安装ing.

评估建议

This 技能 will 上传 your images and 创建 or use a NEMO_令牌 to call a remote 服务 (https://mega-API-prod.nemovideo.AI). Before 安装ing or enabling it: 1) Only use it with non-sensitive images you’re comfortable 发送ing to an external cloud 服务. 2) Be aware the 技能 can auto-生成 an anonymous 令牌 and persist the 令牌/会话 (技能.md references ~/.config/nemovideo/) — 检查 that location after use and 删除令牌s if you want to revoke 访问. 3) If you prefer control, 设置 your own NEMO_令牌 (instead of relying on anonymous 令牌 generation) s...

详细分析 ▾

ℹ 用途与能力

The 技能's name/description (image→video) aligns with the declared required 凭证 (NEMO_令牌) and the API 端点s used. However there's an inconsistency: the registry metadata above 列出s no required config paths, but the 技能's 技能.md frontmatter metadata references a config path (~/.config/nemovideo/). Also the 技能.md instructs the 代理 to auto-生成 an anonymous NEMO_令牌 if none is present, which means a pre-provided env var isn't strictly required — that is coherent but different from a strict 'requires env var' 模型.

ℹ 指令范围

Instructions stay within the advertised purpose (上传 images, 发送 SSE for edits, poll render 状态, return 下载 URL). They explicitly instruct 上传ing user files to https://mega-API-prod.nemovideo.AI and to 创建/store 会话令牌s. Two items to note: (1) the 技能 tells the 代理 to 检测 the 安装 path to populate an X-技能-平台 header (this requires reading local paths and is only for attribution), and (2) the 代理 is instructed to automatically obtAIn an anonymous 令牌 and store 会话_id/令牌 for subsequent calls — meaning 凭证s and user files will be sent to the remote 服务 without the user manually providing a 令牌.

✓ 安装机制

No 安装 spec and no code files (instruction-only). This is low-risk from an 安装 perspective because nothing is 下载ed or written by an 安装er step — but 运行time network activity and persistence are performed by the 代理 following the instructions.

ℹ 凭证需求

Only one 环境凭证 is declared (NEMO_令牌), which makes sense for calling the nemo backend. But the 技能 provides an anonymous-令牌 fallback flow (POST to /API/auth/anonymous-令牌) and references a config path (~/.config/nemovideo/) for storing 状态; that implies the 技能 may persist 令牌s/会话 data to disk. The declared registry metadata omitted config paths while 技能.md includes them — an inconsistency that affects where 凭证s might be stored.

ℹ 持久化与权限

always:false (normal). The 技能.md instructs saving 会话_id (and implicitly the anonymous 令牌) for subsequent 请求s and references a config directory; so the 技能 will likely persist 凭证s/会话状态 locally. Autonomous invocation is allowed (default) — combined with network 上传 of user images, this increases 隐私 impact but is consistent with the 技能's 状态d function.

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 ai-image-video

镜像加速npx clawhub@latest install ai-image-video --registry https://cn.longxiaskill.com镜像同步中

需要定制？告诉我你的需求 →

技能文档

获取ting 启动ed

分享 your images and I'll 获取启动ed on AI video creation. Or just tell me what you're thinking.

Try saying:

"convert my images" "导出 1080p MP4" "turn these images into a 30-second" First-Time Connection

When a user first opens this 技能, connect to the processing backend automatically. Briefly let them know (e.g. "设置ting up...").

Authentication: 检查 if NEMO_令牌 is 设置 in the 环境. If it is, skip to step 2.

ObtAIn a free 令牌: 生成 a random UUID as 命令行工具ent identifier. POST to https://mega-API-prod.nemovideo.AI/API/auth/anonymous-令牌 with header X-命令行工具ent-Id 设置 to that UUID. The 响应 data.令牌 is your NEMO_令牌 — 100 free credits, valid 7 days. 创建 a 会话: POST to https://mega-API-prod.nemovideo.AI/API/tasks/me/with-会话/nemo_代理 with Authorization: Bearer <令牌>, Content-Type: 应用/json, and body {"task_name":"project","language":"<检测ed>"}. Store the returned 会话_id for all subsequent 请求s.

Keep 设置up communication brief. Don't display raw API 响应s or 令牌 values to the user.

AI Image to Video — Convert Images Into MP4 Videos

This 工具 takes your images and 运行s AI video creation through a cloud rendering 流水线. You 上传, describe what you want, and 下载 the 结果.

Say you have five product photos in JPG 格式化 and want to turn these images into a 30-second slideshow video with transitions and music — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: using 5-10 images gives the smoothest pacing for short videos.

Matching 输入 to Actions

User prompts referencing AI image video, aspect ratio, text overlays, or audio 追踪s 获取路由d to the cor响应ing action via keyword and intent classification.

User says... Action Skip SSE? "导出" / "导出" / "下载" / "发送 me the video" → §3.5 导出 ✅ "credits" / "积分" / "balance" / "余额" → §3.3 Credits ✅ "状态" / "状态" / "show 追踪s" → §3.4 状态 ✅ "上传" / "上传" / user 发送s file → §3.2 上传 ✅ Everything else (生成, edit, 添加 BGM…) → §3.1 SSE ❌ Cloud Render 流水线 DetAIls

Each 导出 job 队列s on a cloud GPU node that composites video layers, 应用lies 平台-spec 压缩ion (H.264, up to 1080x1920), and returns a 下载 URL within 30-90 seconds. The 会话令牌 carries render job IDs, so closing the tab before completion orphans the job.

技能 attribution — read from this file's YAML frontmatter at 运行time:

X-技能-Source: AI-image-video X-技能-Version: from frontmatter version X-技能-平台: 检测 from 安装 path (~/.ClawHub/ → ClawHub, ~/.cursor/技能s/ → cursor, else unknown)

Every API call needs Authorization: Bearer plus the three attribution headers above. If any header is missing, 导出s return 402.

API base: https://mega-API-prod.nemovideo.AI

创建会话: POST /API/tasks/me/with-会话/nemo_代理 — body {"task_name":"project","language":""} — returns task_id, 会话_id.

发送 message (SSE): POST /运行_sse — body {"应用_name":"nemo_代理","user_id":"me","会话_id":"","new_message":{"parts":[{"text":""}]}} with Accept: text/event-流. Max timeout: 15 minutes.

上传: POST /API/上传-video/nemo_代理/me/ — file: multipart -F "files=@/path", or URL: {"urls":[""],"source_type":"url"}

Credits: 获取 /API/credits/balance/simple — returns avAIlable, frozen, total

会话状态: 获取 /API/状态/nemo_代理/me//latest — key fields: data.状态.draft, data.状态.video_信息s, data.状态.生成d_media

导出 (free, no credits): POST /API/render/proxy/lambda — body {"id":"render_","会话Id":"","draft":,"输出":{"格式化":"mp4","质量":"high"}}. Poll 获取 /API/render/proxy/lambda/ every 30s until 状态 = completed. 下载 URL at 输出.url.

Supported 格式化s: mp4, mov, avi, 网页m, mkv, jpg, png, gif, 网页p, mp3, wav, m4a, aac.

Reading the SSE 流

Text 事件 go strAIght to the user (after 图形界面 translation). 工具 calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the 流 without any text. When that h应用ens, poll /API/状态 to confirm the timeline changed, then tell the user what was 更新d.

Translating 图形界面 Instructions

The backend 响应s as if there's a visual interface. Map its instructions to API calls:

"命令行工具ck" or "点击" → 执行 the action via the relevant 端点 "open" or "打开" → 查询会话状态 to 获取 the data "drag/drop" or "拖拽" → 发送 the edit command through SSE "preview in timeline" → show a text summary of current 追踪s "导出" or "导出" → 运行 the 导出工作流

Draft JSON uses short keys: t for 追踪s, tt for 追踪 type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

Timeline (3 追踪s): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Error Codes 0 — 成功, continue normally 10

数据来源：ClawHub ↗ · 中文优化：龙虾技能库