Getting Started

Welcome to NemoVideo — your AI-powered video editing and generation assistant built for creators who move fast. Tell me what you're working on, share a script or clip description, and let's turn it into a finished video right now.

Try saying:

• - "Trim this clip to 60 seconds"
• "Add captions to my video"
• "Convert landscape to vertical format"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• - Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Turn Ideas Into Finished Videos Without the Friction

NemoVideo is built for creators who spend more time wrestling with editing software than actually making content. Whether you're starting from a written script, a rough clip, or just a concept in your head, this skill helps you move from idea to finished video without jumping between a dozen tools.

The core strength of nemovideo lies in its ability to understand what you're trying to make — not just execute commands. You can describe the tone, pacing, and structure of a video and get back a coherent result. Need captions burned in? Want to reformat a landscape video for vertical mobile viewing? Prefer a specific outro style? All of that lives in one place.

Creators using nemovideo typically cut their post-production time significantly because the skill handles the repetitive decisions: aspect ratio adjustments, subtitle timing, scene trimming, and export formatting. You focus on the creative direction; nemovideo handles the mechanical execution that normally eats hours out of a production day.

Smart Request Routing in NemoVideo

When you submit a prompt, NemoVideo's intent engine parses your request and automatically routes it to the appropriate pipeline — generation, frame-level editing, upscaling, or style transfer — based on detected keywords, attached assets, and your project context.

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 Cloud API Reference

NemoVideo processes all render jobs on distributed GPU clusters via its cloud backend, meaning heavy diffusion workloads and temporal coherence passes never touch your local machine. Each API call returns a job ID you can poll for status, preview frames, or final output delivery.

Skill attribution — read from this file's YAML frontmatter at runtime:

• - X-Skill-Source: INLINECODE8
• INLINECODE9: from frontmatter INLINECODE10
• INLINECODE11: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

API base: INLINECODE21

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: INLINECODE31

Credits: GET /api/credits/balance/simple — returns available, frozen, INLINECODE35

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, INLINECODE39

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result

Process internally, don't forward | | heartbeat / empty data: | Keep waiting. Every 2 min: "⏳ Still working..." | | Stream closes | Process final response |

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"

Query session state |
| "drag/drop" / "拖拽" | Send edit via SSE |
| "preview in timeline" | Show track summary |
| "Export button" / "导出" | Execute export workflow |

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

CODEBLOCK0

Error Handling

Code	Meaning	Action
0	Success	Continue
1001

Bad/expired token | Re-auth via anonymous-token (tokens expire after 7 days) | | 1002 | Session not found | New session §3.0 | | 2001 | No credits | Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account" | | 4001 | Unsupported file | Show supported formats | | 4002 | File too large | Suggest compress/trim | | 400 | Missing X-Client-Id | Generate Client-Id and retry (see §1) | | 402 | Free plan export blocked | Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export." | | 429 | Rate limit (1 token/client/7 days) | Retry in 30s once |

Best Practices

The most effective nemovideo sessions start with clear output goals. Before you send a request, know your target platform (YouTube, TikTok, LinkedIn), your desired video length, and whether you need captions, transitions, or specific formatting. Vague inputs produce vague outputs — specificity is your best tool here.

When editing existing content, give nemovideo the full picture: what the original video contains, what's working, and what needs to change. Saying 'make it more engaging' is less useful than 'cut the intro to under 10 seconds and add on-screen text for the three key stats in the middle section.'

For generated video scripts or scene breakdowns, review the structure before finalizing. NemoVideo is strong at logical pacing and format compliance, but your creative instincts about brand voice and audience tone should be the final filter. Treat the output as a strong first draft, not a locked final cut.

Integration Guide

Getting started with nemovideo is straightforward — no complex setup or external configuration required. You interact with the skill directly through ClawHub by describing your video project, pasting a script, or uploading a file reference depending on your workflow.

For creators managing a content calendar, nemovideo works well when you feed it structured inputs: a written script with scene notes, a rough cut description, or a list of clips with timestamps. The more context you provide upfront — target platform, desired length, caption style, tone — the more precisely nemovideo can execute without back-and-forth.

If you're working with existing footage, describe the clip's content and what changes you need. NemoVideo can output structured edit instructions, caption files, reformatted layout specs, or fully generated video narratives depending on your request. It fits naturally into a creator's existing workflow without requiring you to rebuild your process around it.