Video Editing Ai Gpt

Turn a 3-minute unedited screen recording into 1080p edited MP4 videos just by typing what you need. Whether it's using GPT-powered commands to edit videos h...

Security Scan

The skill's behavior (uploading user videos to an external cloud service and auto-obtaining tokens) matches its description, but missing provenance, a metadata inconsistency, and the fact it will transmit possibly sensitive videos to a third-party backend are reasons to be cautious.

Purpose & Capability

The name/description (AI cloud video editing) align with the instructions: the SKILL.md describes session creation, upload, SSE-based editing, and export endpoints on mega-api-prod.nemovideo.ai and requires a NEMO_TOKEN. However there is a metadata mismatch: the registry reported no required config paths while the SKILL.md frontmatter lists a config path (~/.config/nemovideo/). Also the skill has no homepage or source repository, which reduces provenance and makes it harder to verify legitimacy.

Instruction Scope

Runtime instructions direct the agent to accept user video files and upload them to a third-party API, create sessions, handle SSE streams, poll exports, and include attribution headers. This is coherent with the stated purpose but entails automatic transmission of potentially sensitive user data and automatic token acquisition if NEMO_TOKEN is absent — both are significant privacy/security behaviors. The instructions also require detection of install path for an attribution header (may require access to runtime paths). The SKILL.md explicitly tells the agent to not print tokens, but it still instructs network calls that will carry tokens.

Install Mechanism

Instruction-only skill with no install script or code files; nothing written to disk by an installer. This is the lowest install risk modality.

Credentials

Only one declared environment credential (NEMO_TOKEN) and it is plausible for a cloud API. The skill also supports anonymously acquiring a short-lived token by POSTing to the provider's auth endpoint if no token exists — which is coherent but increases the skill's autonomy in obtaining credentials. The inconsistency between registry metadata (no config paths) and the SKILL.md frontmatter (configPaths: ~/.config/nemovideo/) should be resolved.

Persistence & Privilege

always is false and the skill has no install-time persistence. It may be invoked autonomously by the agent (default behavior), which is expected; that combined with network access is normal but increases the blast radius compared with a purely local tool.

What to consider before installing

This skill will upload whatever video you drop into chat to a third-party cloud service (mega-api-prod.nemovideo.ai) and will use a NEMO_TOKEN or automatically request an anonymous token for you. Before installing or using it: 1) Consider the sensitivity of any videos you would upload — do not send confidential or private footage unless you trust the destination and have a documented privacy/data-retention policy. 2) Ask the skill author/vendor for provenance: a homepage, source repo, privacy policy, company identity, and retention/deletion guarantees. 3) Resolve the metadata mismatch: confirm whether the skill needs the config path (~/.config/nemovideo/) and why. 4) Prefer using a disposable NEMO_TOKEN or test with short, non-sensitive clips first. 5) If you must proceed, verify how long anonymous tokens last and how the backend stores uploaded files; request a way to delete your data. If the author provides authoritative documentation and a trustworthy operator identity, this assessment could shift toward benign.

Getting Started

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

Try saying:

• "edit my raw video footage"
• "export 1080p MP4"
• "cut the pauses, add transitions, and"

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.

Video Editing AI GPT — Edit Videos With AI Prompts

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

Here's a typical use: you send a a 3-minute unedited screen recording, ask for cut the pauses, add transitions, and generate subtitles, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips under 2 minutes process significantly faster and give more accurate AI results.

Matching Input to Actions

User prompts referencing video editing ai gpt, 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-ai-gpt
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 field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

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

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.

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

Common Workflows

Quick edit: Upload → "cut the pauses, add transitions, and generate subtitles" → Download MP4. Takes 1-2 minutes 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 pauses, add transitions, and generate subtitles" — 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 widest compatibility across platforms.