Getting Started
Welcome! Ready to turn your raw footage into something worth watching? Drop your video file and tell me what kind of edit you're going for — I'll handle the cuts, pacing, and polish so your best video editor experience starts right now.
Try saying:
- - "Trim this 8-minute interview down to the best 90 seconds, removing any long pauses and filler words."
- "Merge these three clips into one video with smooth transitions and add a title card at the beginning."
- "Color correct this outdoor footage — it looks washed out — and boost the audio so the speaker is easier to hear."
On first use, the skill connects to NemoVideo automatically:
- 1. Check for
NEMO_TOKEN env var, or acquire one via https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token (100 free credits) - Persist a Client-ID to
~/.config/nemovideo/client_id for rate-limit tracking (UUID only, no secrets) - Create a session and start working immediately
Edit Like a Pro Without Touching a Timeline
Most video editors put the burden on you — drag clips, hunt for the right tool, tweak settings you barely understand. This skill flips that. You describe what your video should look like, and the best-video-editor skill figures out how to get it there. Whether you're cutting a 30-second social reel from a 10-minute raw recording, blending multiple clips into a cohesive story, or cleaning up shaky footage with background noise, the work happens through conversation rather than menus.
Upload your footage in any common format — mp4, mov, avi, webm, or mkv — and tell the skill what you're going for. Want a punchy 15-second highlight with a fade-out? A product demo with clean cuts and on-screen text? A travel montage synced to a specific mood? Just say it.
This isn't a one-size-fits-all filter. The skill adapts to your footage, your style, and your goals. Creators making YouTube content, small business owners producing marketing videos, and filmmakers doing rough cuts all use it differently — and it meets each of them where they are.
Environment
| Variable | Default | Purpose |
|---|
| INLINECODE3 | Auto-acquired on first use (100 free credits, 7-day expiry) | API authentication |
| INLINECODE4 |
https://mega-api-prod.nemovideo.ai | API base URL |
Routing Your Edit Requests
Every prompt you send — whether it's a cut, color grade, transition, or AI enhancement — is parsed by intent and routed to the matching NemoVideo editing pipeline automatically.
| User says... | Action | Skip SSE? |
|---|
| "export" / "导出" / "download" / "send me the video" | → §3.5 Export | ✅ |
| "credits" / "积分" / "balance" / "余额" |
→ §3.3 Credits | ✅ |
| "status" / "状态" / "show tracks" | → §3.4 State | ✅ |
| "upload" / "上传" / user sends file | → §3.2 Upload | ✅ |
| Everything else (generate, edit, add BGM…) | → §3.1 SSE | ❌ |
NemoVideo API Reference
The NemoVideo backend processes your timeline instructions, AI upscaling, and render jobs through a dedicated media processing engine optimized for frame-accurate edits. Authentication tokens gate each API call, so your project assets and export settings remain session-scoped and secure.
Required headers on all requests: X-Skill-Source: $SKILL_NAME, X-Skill-Version: $SKILL_VERSION, INLINECODE8
Create session: POST $API/api/tasks/me/with-session/nemo_agent — returns task_id and INLINECODE11
Send message (SSE): POST $API/run_sse with session_id and user message. Stream responses; ~30% of edits return no text (query state to confirm changes).
Upload: POST $API/api/upload-video/nemo_agent/me/<sid> — file or URL upload. Supports: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.
Check credits: INLINECODE15
Query state: GET $API/api/state/nemo_agent/me/<sid>/latest — check draft, tracks, generated media
Export: POST $API/api/render/proxy/lambda — export does NOT cost credits. Poll GET $API/api/render/proxy/lambda/<id> until status: completed.
Task link: INLINECODE20
Common Errors
If your token expires mid-session, simply re-authenticate through the skill to restore full editing access without losing your timeline state. A 'session not found' error means your editing context was cleared — start a fresh session and reimport your project assets. Run out of credits? Head to nemovideo.ai to register or top up so your renders and AI effects keep rolling without interruption.
Troubleshooting
The output video looks different from what I described.
Try rephrasing your request with more specific details. Instead of 'make it better,' say 'increase brightness by 20% and sharpen the focus.' The more concrete your description, the more accurate the result.
My file won't upload.
Check that your file is under the size limit and in a supported format (mp4, mov, avi, webm, mkv). Very large raw files may need to be compressed first.
The audio and video are out of sync after editing.
Mention sync explicitly in your prompt — for example, 'keep the audio and video perfectly in sync after trimming.' This flags it as a priority during processing.
Transitions look abrupt or jarring.
Specify the transition style you want — 'use a 0.5-second crossfade between each clip' gives the skill clear guidance rather than leaving it to default behavior.
Best Practices
Start with clean source footage. The best-video-editor skill can enhance a lot, but severely overexposed, heavily pixelated, or corrupted files will limit what's achievable. Good source material always produces better output.
Be specific about duration and pacing. If you need a 60-second cut for Instagram, say so upfront. Knowing the target length and platform helps shape every editing decision from clip selection to transition speed.
Describe the feeling, not just the function. Saying 'make this feel urgent and fast-paced' gives as much useful direction as listing specific cuts. Combine both for the best results — 'fast-paced cuts every 2 seconds with no transitions, high energy feel.'
Review and iterate. Treat the first output as a strong draft. Note what's close and what needs adjusting, then give targeted feedback. Editing is iterative by nature, and the skill responds well to specific revision requests.
FAQ
What video formats does the best-video-editor skill support?
You can upload files in mp4, mov, avi, webm, and mkv. If your footage is in another format, convert it to one of these before uploading for the smoothest experience.
Can I edit multiple clips in one session?
Yes. You can upload several clips and ask the skill to merge them, reorder them, or edit each one individually before combining.
Does it support audio editing too?
Absolutely. You can request noise reduction, volume normalization, music syncing, or audio trimming alongside your video edits.
How specific do my instructions need to be?
As specific or as loose as you like. 'Make it look more cinematic' works just as well as 'add a teal-orange color grade and slow the final clip by 50%.'
开始使用
欢迎!准备好将你的原始素材剪辑成值得一看的作品了吗?上传你的视频文件,告诉我你想要什么样的剪辑效果——我来处理剪辑、节奏和润色,让你即刻开启最佳视频编辑体验。
试试这样说:
- - 将这段8分钟的采访剪辑成最精彩的90秒,去除所有长时间停顿和填充词。
- 将这三个片段合并成一个视频,添加平滑转场,并在开头加上标题卡片。
- 对这段户外素材进行色彩校正——画面看起来褪色了——并增强音频,让说话者更清晰可辨。
首次使用时,该技能会自动连接到NemoVideo:
- 1. 检查是否存在NEMOTOKEN环境变量,或通过https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token获取一个(100个免费积分)
- 将客户端ID持久化存储到~/.config/nemovideo/clientid,用于速率限制追踪(仅UUID,无敏感信息)
- 创建会话并立即开始工作
无需触碰时间线,也能专业剪辑
大多数视频编辑器将负担都压在你身上——拖拽片段、寻找合适的工具、调整你几乎不了解的设置。这个技能颠覆了这一切。你只需描述你想要的视频效果,best-video-editor技能就会自动找出实现方法。无论你是从10分钟的原始录音中剪辑出30秒的社交媒体短片,将多个片段融合成一个连贯的故事,还是清理带有背景噪音的抖动素材,所有工作都通过对话而非菜单完成。
以任何常见格式上传你的素材——mp4、mov、avi、webm或mkv——然后告诉技能你想要的效果。想要一个带有淡出效果的15秒精彩片段?一个带有干净剪辑和屏幕文字的产品演示?一个与特定情绪同步的旅行混剪?只需说出来即可。
这不是一刀切的滤镜。该技能会根据你的素材、风格和目标进行调整。制作YouTube内容的创作者、制作营销视频的小企业主以及进行粗剪的电影制作人,都以不同的方式使用它——而它能够满足每个人的需求。
环境变量
| 变量 | 默认值 | 用途 |
|---|
| NEMOTOKEN | 首次使用时自动获取(100个免费积分,7天有效期) | API身份验证 |
| NEMOAPI_URL |
https://mega-api-prod.nemovideo.ai | API基础URL |
路由你的编辑请求
你发送的每个提示——无论是剪辑、色彩分级、转场还是AI增强——都会按意图进行解析,并自动路由到匹配的NemoVideo编辑管道。
| 用户说... | 操作 | 跳过SSE? |
|---|
| export / 导出 / download / send me the video | → §3.5 导出 | ✅ |
| credits / 积分 / balance / 余额 |
→ §3.3 积分 | ✅ |
| status / 状态 / show tracks | → §3.4 状态 | ✅ |
| upload / 上传 / 用户发送文件 | → §3.2 上传 | ✅ |
| 其他所有内容(生成、编辑、添加背景音乐等) | → §3.1 SSE | ❌ |
NemoVideo API参考
NemoVideo后端通过专为帧精确编辑优化的专用媒体处理引擎,处理你的时间线指令、AI超分辨率放大和渲染任务。每个API调用都需要身份验证令牌,因此你的项目资源和导出设置保持会话范围内的安全性。
所有请求必需的请求头:X-Skill-Source: $SKILLNAME、X-Skill-Version: $SKILLVERSION、X-Skill-Platform: $SKILL_SOURCE
创建会话:POST $API/api/tasks/me/with-session/nemoagent — 返回taskid和session_id
发送消息(SSE):POST $API/runsse,包含sessionid和用户消息。流式响应;约30%的编辑不返回文本(查询状态以确认更改)。
上传:POST $API/api/upload-video/nemo_agent/me/ — 文件或URL上传。支持格式:mp4、mov、avi、webm、mkv、jpg、png、gif、webp、mp3、wav、m4a、aac。
检查积分:GET $API/api/credits/balance/simple
查询状态:GET $API/api/state/nemo_agent/me//latest — 检查草稿、轨道、生成的媒体
导出:POST $API/api/render/proxy/lambda — 导出不消耗积分。轮询GET $API/api/render/proxy/lambda/,直到status: completed。
任务链接:$WEB/workspace/claim?token=$TOKEN&task={taskid}&session={sessionid}&skillname=$SKILLNAME&skillversion=$SKILLVERSION&skillsource=$SKILLSOURCE
常见错误
如果令牌在会话期间过期,只需通过技能重新进行身份验证,即可恢复完整的编辑访问权限,而不会丢失时间线状态。出现会话未找到错误意味着你的编辑上下文已被清除——启动新会话并重新导入项目资源。积分用完了?前往nemovideo.ai注册或充值,让你的渲染和AI效果持续运行,不受中断。
故障排除
输出的视频与我的描述看起来不同。
尝试用更具体的细节重新表述你的请求。不要只说让它更好,而是说将亮度提高20%并锐化焦点。描述越具体,结果越准确。
我的文件无法上传。
检查文件是否在大小限制内,并且是支持的格式(mp4、mov、avi、webm、mkv)。非常大的原始文件可能需要先进行压缩。
编辑后音频和视频不同步。
在提示中明确提到同步——例如在剪辑后保持音频和视频完美同步。这会在处理过程中将其标记为优先级。
转场看起来突兀或不协调。
指定你想要的转场风格——在每个片段之间使用0.5秒的交叉淡入淡出为技能提供了清晰的指导,而不是让它采用默认行为。
最佳实践
从干净的原始素材开始。 best-video-editor技能可以增强很多内容,但严重过曝、高度像素化或损坏的文件会限制可实现的效果。好的原始素材总能产生更好的输出。
明确指定时长和节奏。 如果你需要为Instagram制作60秒的剪辑,请提前说明。了解目标时长和平台有助于从片段选择到转场速度的每个编辑决策。
描述感觉,而不仅仅是功能。 说让这个感觉紧迫且快节奏与列出具体剪辑一样能提供有用的指导。将两者结合以获得最佳效果——每2秒快速剪辑,无转场,高能量感。
审阅并迭代。 将第一个输出视为一个强有力的草稿。注意哪些接近目标,哪些需要调整,然后给出有针对性的反馈。编辑本质上是迭代的,该技能对具体的修改请求反应良好。
常见问题
best-video-editor技能支持哪些视频格式?
你可以上传mp4、mov、avi、webm和mkv格式的文件。如果你的素材是其他格式,在上传前将其转换为这些格式之一,以获得最流畅的体验。
我可以在一个会话中编辑多个片段吗?
可以。你可以上传多个片段,并要求技能将它们合并、重新排序,或在合并前单独编辑每个片段。
它也支持音频编辑吗?
当然。你可以请求降噪、音量标准化、音乐同步或音频修剪,与视频编辑同时进行。
我的指令需要多具体?
可以根据你的喜好,具体或宽松都可以。让它看起来更像电影和添加青橙色调分级并将最后一个片段放慢50%同样有效。