Video Ai App

Turn a 2-minute unedited phone recording into 1080p edited video clips just by typing what you need. Whether it's automatically editing and enhancing raw vid...

Security Scan

The skill's requirements and runtime instructions are coherent with a remote video-editing service: it only needs a single service token (NEMO_TOKEN), uploads user video files to the stated API, and has no install step or unrelated credential access.

Purpose & Capability

Name/description (AI video editing) match the declared requirement (NEMO_TOKEN) and the SKILL.md actions (create session, upload video, request render). There are no unrelated credentials or binaries requested.

Instruction Scope

Instructions focus on connecting to a remote API, creating or using a token, opening sessions, uploading media, and polling render status. They reference reading this skill's frontmatter and detecting install path to set an attribution header — this is unusual but not unrelated to the stated API attribution requirement. The skill does instruct uploading local files (expected for a video-uploading skill) and to persist session_id.

Install Mechanism

No install spec or third-party code is fetched. This is instruction-only, so no archives or remote installers are pulled by the skill itself.

Credentials

Only a single environment credential (NEMO_TOKEN) is required and is appropriate for the described remote API. The SKILL.md also documents generating an anonymous token via the same API if NEMO_TOKEN is absent (so the skill can operate without user-provided secrets). No unrelated env vars or secret stores are requested.

Persistence & Privilege

The skill does not request always:true and has no install-time persistence. It does instruct the agent to store session_id for ongoing jobs, which is expected for queued render workflows.

Assessment

This skill appears internally consistent, but it sends your video files and tokens to an external API (https://mega-api-prod.nemovideo.ai). Consider: only upload non-sensitive footage; verify you trust the service/operator and their privacy policy; understand that if NEMO_TOKEN is not set the agent will request an anonymous token from the same API (the skill can operate without you supplying secrets); the agent will store session IDs for render jobs; and the skill may attempt to detect install path to set an attribution header. If you are uncomfortable with automatic network calls or sending content off-device, do not install or disable autonomous invocation for this skill and/or avoid providing videos or a persistent NEMO_TOKEN.

Getting Started

Send me your raw video footage and I'll handle the AI video editing. Or just describe what you're after.

Try saying:

• "edit a 2-minute unedited phone recording into a 1080p MP4"
• "trim the silent parts, add captions, and export for Instagram"
• "automatically editing and enhancing raw video recordings for content creators"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Video AI App — Edit and Export AI Videos

Send me your raw video footage and describe the result you want. The AI video editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute unedited phone recording, type "trim the silent parts, add captions, and export for Instagram", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds process significantly faster.

Matching Input to Actions

User prompts referencing video ai app, 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 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.

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

• X-Skill-Source: video-ai-app
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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 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

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

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.

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)

Common Workflows

Quick edit: Upload → "trim the silent parts, add captions, and export for Instagram" → 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 "trim the silent parts, add captions, and export for Instagram" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across platforms.