Split Screen Video Editor

Skip the learning curve of professional editing software. Describe what you want — place both clips side by side in a 50/50 split screen layout — and get spl...

Security Scan

The skill's instructions, required token, and network calls are consistent with a cloud-based video composition service — nothing in the package appears to be trying to do something unrelated, but it will upload your video files and use a service token so review privacy before use.

Purpose & Capability

The skill name/description (cloud split-screen video rendering) matches the runtime instructions and the single required credential (NEMO_TOKEN). Minor inconsistency: the metadata lists a config path (~/.config/nemovideo/) even though the SKILL.md does not instruct reading or writing that path; this is plausibly for local config but is not used in the instructions.

Instruction Scope

SKILL.md confines actions to creating/refreshing an anonymous token, creating a session, uploading user-provided video files, sending SSE edit commands, polling export status, and returning a download URL. All network calls are to the declared API host (mega-api-prod.nemovideo.ai). The skill does not instruct reading unrelated local files or other environment variables, but it will upload user videos to an external service — expected for this purpose.

Install Mechanism

No install steps or downloaded code are present (instruction-only). This minimizes install risk; all execution is via API calls to the remote backend.

Credentials

Only one credential is declared (NEMO_TOKEN) and is the primary credential used for API Authorization — appropriate for a cloud render service. The skill also offers to obtain an anonymous token automatically if none is present, which is consistent with its functionality. Minor note: metadata lists a config path (~/.config/nemovideo/) that is not referenced in SKILL.md; this is not a large red flag but should be clarified.

Persistence & Privilege

The skill is not forced-always, and it does not declare any system-wide modifications. It requests no elevated privileges or edits to other skills. It does use networked, stateful sessions (session_id) which the agent must retain for job operations — normal for this kind of service.

Assessment

This skill will upload any videos you give it to mega-api-prod.nemovideo.ai and use a service token (NEMO_TOKEN) to authorize requests. If you care about privacy or intellectual property, verify the service's reputation and privacy/retention policy before uploading sensitive footage. The skill can automatically request a 7-day anonymous token if none is provided — consider using a throwaway account/token for sensitive content. Note the metadata mentions a local config path (~/.config/nemovideo/) though the instructions do not use it — ask the publisher what (if anything) is stored there. Finally, confirm that your agent environment does not log or expose the acquired token/session IDs, since these values grant access to your render jobs.

Getting Started

Send me your video clips and I'll handle the split screen layout. Or just describe what you're after.

Try saying:

• "create two 30-second reaction clips into a 1080p MP4"
• "place both clips side by side in a 50/50 split screen layout"
• "displaying two or more video clips simultaneously side by side for YouTubers, TikTok creators, content creators"

First-Time Connection

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

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Split Screen Video Editor — Combine Clips Into One Video

Send me your video clips and describe the result you want. The split screen layout runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload two 30-second reaction clips, type "place both clips side by side in a 50/50 split screen layout", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: keep all clips the same length to avoid blank panels in the final output.

Matching Input to Actions

User prompts referencing split screen video editor, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

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	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	split-screen-video-editor
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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: {"urls":["<url>"],"source_type":"url"}

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

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

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.

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

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

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.

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

Example timeline summary:

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "place both clips side by side in a 50/50 split screen layout" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 with H.264 codec for the best balance of quality and file size.

Common Workflows

Quick edit: Upload → "place both clips side by side in a 50/50 split screen layout" → Download MP4. Takes 30-60 seconds for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.