Professional Video Local Ai

Turn a 3-minute interview recorded on a DSLR into 4K polished edited videos just by typing what you need. Whether it's editing professional-grade video local...

Security Scan

The skill advertises

Purpose & Capability

The skill's public description (and displayName) implies local, offline AI video editing (“without cloud uploads”), but the SKILL.md explicitly describes a cloud rendering pipeline and numerous API endpoints at https://mega-api-prod.nemovideo.ai for session creation, upload, rendering and download. That is a direct contradiction: a user expecting purely local editing would be surprised to have large raw video files uploaded to a remote service. Also the SKILL.md metadata lists a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — an inconsistency in declared requirements.

Instruction Scope

The runtime instructions tell the agent to (a) use NEMO_TOKEN if present or generate an anonymous token by POSTing to the provider URL, (b) create sessions, (c) upload videos via /api/upload-video/..., (d) stream SSE, poll export endpoints and download results. These steps involve network requests and uploading potentially large and sensitive video files to a third-party cloud service. The instructions also tell the agent to read the install path to set X-Skill-Platform and to include attribution headers. The network upload/authorization behavior conflicts with the skill's 'local' claim and should be called out to users before use.

Install Mechanism

This is an instruction-only skill with no install spec or code files; nothing is written to disk by an installer. That minimizes filesystem installation risk. However, the SKILL.md instructs outgoing HTTP calls to an unverified domain, which is a runtime risk (data transmission) even though there's no install step.

Credentials

The only required env var is NEMO_TOKEN (declared as primaryEnv), which is appropriate for a service that requires auth. The SKILL.md adds that if NEMO_TOKEN is absent the agent should request an anonymous token from the remote API — meaning the skill will obtain/hold credentials automatically. The declared configPaths differ between registry metadata and SKILL.md (SKILL.md references ~/.config/nemovideo/), which is an unresolved inconsistency that affects what local state may be read.

Persistence & Privilege

The skill is not marked always:true and has no install behavior, it doesn't request persistent platform privileges, and it does not instruct modification of other skills/configurations. Autonomous invocation is allowed (platform default), but that alone is not a red flag here.

What to consider before installing

Key points to consider before installing or using this skill: - The skill's marketing says 'local' editing, but the runtime instructions upload your raw footage to a cloud service (https://mega-api-prod.nemovideo.ai). If you expected offline-only processing, this skill is not that. - The agent will use NEMO_TOKEN if present or automatically obtain an anonymous token by contacting the vendor and receiving 100 free credits; that means outbound network activity and creation of credentials on your behalf. - Do not upload sensitive or confidential video content unless you have verified the service provider, their privacy policy, and how long they retain uploaded media. - There is no source homepage or published vendor information. Ask the publisher for a privacy/security statement, source code, or a corporate identity before trusting large or sensitive uploads. - Verify billing/credit behavior and whether exported videos or thumbnails are stored long-term. The instructions mention credits/charges and job orphaning if you close the client. - If you need true local/offline editing, seek a skill or tool that guarantees local-only processing; this skill does not. - If you decide to proceed, prefer providing your own vetted NEMO_TOKEN (so the skill does not request an anonymous token on your behalf) and test with non-sensitive short clips first.

Getting Started

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

Try saying:

• "edit my raw video footage"
• "export 4K MP4"
• "cut silences, color grade the footage,"

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.

Professional Video Local AI — Edit and Export Pro Videos Locally

This tool takes your raw video footage and runs local AI video editing through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 3-minute interview recorded on a DSLR and want to cut silences, color grade the footage, and add lower-third titles — the backend processes it in about 1-3 minutes and hands you a 4K MP4.

Tip: keeping clips under 5 minutes significantly reduces local processing time.

Matching Input to Actions

User prompts referencing professional video local ai, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is professional-video-local-ai, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise 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.

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)

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut silences, color grade the footage, and add lower-third titles" — 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 delivery.

Common Workflows

Quick edit: Upload → "cut silences, color grade the footage, and add lower-third titles" → Download MP4. Takes 1-3 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.