Video Editing With Gpu

Get GPU-rendered MP4 ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, MKV, up to 500MB), say something like "cu...

Security Scan

The skill's behavior mostly matches a cloud GPU video-editing integration, but there are metadata inconsistencies and a few instructions that require agent environment/filesystem access that you should confirm before installing.

Purpose & Capability

As described, the skill routes uploads and edit requests to a cloud GPU video service and requires a service token (NEMO_TOKEN) — that is coherent. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata earlier reported no required config paths, a mismatch worth clarifying.

Instruction Scope

Runtime instructions are focused on API calls to the nemovideo backend (session creation, SSE chat, upload, export). They do not ask for unrelated system data. Minor scope creep: the skill expects to 'auto-detect' platform from the install path (which implies reading agent/FS context) and mandates specific attribution headers derived from frontmatter — both require access to agent environment or metadata.

Install Mechanism

Instruction-only skill with no install spec or downloaded code — lowest install risk. Nothing is written to disk by an installer step described here.

Credentials

Only NEMO_TOKEN is declared as required which aligns with a cloud video API. Caveats: SKILL.md also references a config path (~/.config/nemovideo/) and expects to auto-detect an install path for X-Skill-Platform; both imply filesystem/config access beyond a simple env var. Verify whether the skill actually reads that config path or only lists it.

Persistence & Privilege

Skill is not set to always:true and uses normal autonomous invocation defaults. It does not request writing or modifying other skills or system-wide agent settings in the instructions.

What to consider before installing

This skill appears to be a straightforward cloud video-editing wrapper, but the source is unknown and there are small inconsistencies to clear up before installing. Ask the publisher (or the registry) to confirm: (1) whether the skill actually reads ~/.config/nemovideo/ or any files on the agent — the registry and SKILL.md disagree; (2) what exact permissions the NEMO_TOKEN grants and whether it can be scoped or revoked; (3) why the skill needs to auto-detect an install path for X-Skill-Platform (that may require filesystem access). Also confirm you trust the endpoint domain (mega-api-prod.nemovideo.ai) before uploading sensitive footage. If you cannot verify these points, treat the skill conservatively (do not provide sensitive videos or long-lived credentials).

Getting Started

Share your raw video footage and I'll get started on GPU-accelerated video editing. Or just tell me what you're thinking.

Try saying:

• "edit my raw video footage"
• "export 4K MP4"
• "cut the slow parts, add transitions,"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Video Editing with GPU — Edit and Export Videos Fast

Drop your raw video footage in the chat and tell me what you need. I'll handle the GPU-accelerated video editing on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 3-minute raw 4K camera recording, ask for cut the slow parts, add transitions, and export in 4K using GPU rendering, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 4K by default.

One thing worth knowing — shorter clips under 2 minutes render significantly faster with GPU processing.

Matching Input to Actions

User prompts referencing video editing with gpu, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

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

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

Header	Value
X-Skill-Source	video-editing-with-gpu
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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)

Translating GUI Instructions

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

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool 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 stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

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

Common Workflows

Quick edit: Upload → "cut the slow parts, add transitions, and export in 4K using GPU rendering" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut the slow parts, add transitions, and export in 4K using GPU rendering" — concrete instructions get better results.

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

H.264 codec gives the best balance of quality and file size for GPU-rendered exports.