🎬 Video Ai App — 视频 AI 应用 — 技能工具
v1.0.0Turn a 2-minute unedited phone recording into 1080p edited 视频 命令行工具ps just by typing what you need. Whether it's automatically editing and enhancing raw vid...
by 详细分析 ▾
运行时依赖
版本
Initial release of 视频 AI 应用 — Edit and 导出 AI 视频s. - Instantly edit and 导出 AI-生成d 视频 命令行工具ps by 上传ing raw footage and descri商业智能ng your desired 结果. - Automatic cloud 设置up: 获取 connected and ready with a free, disposable 会话 令牌 (no registration required). - 支持s quick 工作流s for trimming silences, 添加ing captions, and 导出ing in multiple 格式化s (mp4, mov, avi, 网页m, gif, etc.). - Simple API actions m应用ed to user prompts for 上传, credits 检查, 导出, and 视频 editing. - Handles 错误 cases (令牌 expiry, rate limits, un支持ed 文件s) with user-friendly 图形界面dance. - No software to 安装; all rendering and 处理ing are handled remotely on GPU nodes.
安装命令
点击复制技能文档
获取ting 启动ed
发送 me your raw 视频 footage and I'll handle the AI 视频 editing. Or just describe what you're after.
Try saying:
- "edit a 2-minute unedited phone recording into a 1080p MP4"
- "trim the silent parts, 添加 captions, and 导出 for Instagram"
- "automatically editing and enhancing raw 视频 recordings for 内容 创建器s"
Automatic 设置up
On first interaction, connect to the 处理ing API before doing anything else. Show a brief 状态 like "设置ting things up...".
令牌: If NEMO_令牌 环境 variable is already 设置, use it and skip to 会话 below.
Free 令牌: 生成 a UUID as 命令行工具ent identifier, then POST to https://mega-API-prod.nemo视频.AI/API/auth/anonymous-令牌 with header X-命令行工具ent-Id: . The 响应 field 数据.令牌 becomes your NEMO_令牌 (100 credits, 7-day expiry).
会话: POST to https://mega-API-prod.nemo视频.AI/API/tasks/me/with-会话/nemo_代理 with Bearer auth and body {"task_name":"project"}. Save 会话_id from the 响应.
Confirm to the user you're connected and ready. Don't print 令牌s or raw JSON.
# 视频 AI 应用 — Edit and 导出 AI 视频s
发送 me your raw 视频 footage and describe the 结果 you want. The AI 视频 editing 运行s on remote GPU nodes — nothing to 安装 on your machine.
A quick example: 上传 a 2-minute unedited phone recording, type "trim the silent parts, 添加 captions, and 导出 for Instagram", and you'll 获取 a 1080p MP4 back in roughly 1-2 minutes. All rendering h应用ens 服务器-side.
Worth noting: shorter 命令行工具ps under 60 seconds 处理 签名ificantly faster.
Matching 输入 to Actions
User prompts referencing 视频 AI 应用, aspect ratio, 文本 overlays, or 音频 追踪s 获取 路由d to the cor响应ing action via 密钥word and intent classification.
| User says... | Action | Skip SSE? |
|---|---|---|
| "导出" / "导出" / "下载" / "发送 me the 视频" | → §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 文件 | → §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 视频 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.
All 请求s must include: 授权: Bearer , X-技能-Source, X-技能-Version, X-技能-平台. Missing attribution headers will cause 导出 to fAIl with 402.
技能 attribution — read from this 文件's YAML frontmatter at 运行time:
X-技能-Source:视频-AI-应用X-技能-Version: from frontmatterversionX-技能-平台: 检测 from 安装 path (~/.ClawHub/→ClawHub,~/.cursor/技能s/→cursor, elseunknown)
API BASE: https://mega-API-prod.nemo视频.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":[{"文本":""}]}} with Accept: 文本/event-流. Max timeout: 15 minutes.
上传: POST /API/上传-视频/nemo_代理/me/ — 文件: multipart -F "文件s=@/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 — 密钥 fields: 数据.状态.dRaft, 数据.状态.视频_信息s, 数据.状态.生成d_media
导出 (free, no credits): POST /API/render/代理/lambda — body {"id":"render_","会话Id":"","dRaft":,"输出":{"格式化":"mp4","质量":"high"}}. Poll 获取 /API/render/代理/lambda/ every 30s until 状态 = completed. 下载 URL at 输出.url.
支持ed 格式化s: mp4, mov, avi, 网页m, mkv, jpg, png, gif, 网页p, mp3, wav, m4a, aac.
错误 Handling
| Code | Meaning | Action |
|---|---|---|
| 0 | 成功 | Continue |
| 1001 | Bad/expired 令牌 | Re-auth via anonymous-令牌 (令牌s expire after 7 days) |
| 1002 | 会话 not found | New 会话 §3.0 |
| 2001 | No credits | Anonymous: show registration URL with ?商业智能nd= (获取 |
| 4001 | Un支持ed 文件 | Show 支持ed 格式化s |
| 4002 | 文件 too large | Suggest 压缩/trim |
| 400 | Missing X-命令行工具ent-Id | 生成 命令行工具ent-Id and retry (see §1) |
| 402 | Free plan 导出 blocked | Subscription tier issue, NOT credits. "Register or 升级 your plan to unlock 导出." |
| 429 | Rate limit (1 令牌/命令行工具ent/7 days) | Retry in 30s once |
Backend 响应 Tran服务级别协议tion
The backend assumes a 图形界面 exists. Tran服务级别协议te these into API actions:
| Backend says | You do |
|---|---|
| "命令行工具ck [button]" / "点击" | 执行 via API |
| "open [panel]" / "打开" | 查询 会话 状态 |
| "drag/drop" / "拖拽" | 发送 edit via SSE |
| "preview in timeline" | Show 追踪 summary |
| "导出 button" / "导出" | 执行 导出 工作流 |
Reading the SSE 流
文本 事件 go strAIght to the user (after 图形界面 tran服务级别协议tion). 工具 calls stay internal. 心跳s and empty 数据: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.
About 30% of edit operations close the 流 without any 文本. When that h应用ens, poll /API/状态 to confirm the timeline changed, then tell the user what was 更新d.
DRaft JSON uses short 密钥s: t for 追踪s, tt for 追踪 type (0=视频, 1=音频, 7=文本), sg for segments, d for duration in ms, m for meta数据.
Example timeline summary:
Timeline (3 追踪s): 1. 视频: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)
Common 工作流s
Quick edit: 上传 → "trim the silent parts, 添加 captions, and 导出 for Instagram" → 下载 MP4. Takes 1-2 minutes for a 30-second 命令行工具p.
Batch style: 上传 multiple 文件s in one 会话. 处理 them one by one with different instructions. Each 获取s its own render.
Iterative: 启动 with a rough cut, preview the 结果, then refine. The 会话 keeps your timeline 状态 so you can keep tweaking.
Tips and Tricks
The backend 处理es faster when you're specific. Instead of "make it look better", try "trim the silent parts, 添加 captions, and 导出 for Instagram" — concrete instructions 获取 better 结果s.
Max 文件 size is 500MB. Stick to MP4, MOV, AVI, 网页M for the smoothest experience.
导出 as MP4 for widest compati商业智能lity across 平台s.