Video Object Ops

Skip the learning curve of professional editing software. Describe what you want — remove the background person and replace it with a solid color — and get o...

Security Scan

The skill's requests and runtime instructions are consistent with a remote video-editing service (it asks for a NEMO_TOKEN and describes uploading videos to nemovideo.ai), but there are minor metadata inconsistencies and expected privacy implications you should review before installing.

Purpose & Capability

Name/description (video object editing) align with the required credential (NEMO_TOKEN) and the SKILL.md instructions (upload video, create session, render). The requested environment variable is proportional to the stated purpose.

Instruction Scope

Instructions focus on authenticating, creating a session, uploading videos, sending SSE edit messages, and polling render status — all within the service domain. They explicitly tell the agent not to print tokens or raw JSON. They also instruct deriving attribution headers and detecting an install path to set X-Skill-Platform, which may require checking local paths; this is not strictly needed for core functionality but is low-risk. The SKILL.md frontmatter references a config path (~/.config/nemovideo/) which would imply reading/writing local config, but the registry metadata listed no required config paths — a small inconsistency.

Install Mechanism

Instruction-only skill with no install spec and no code files. Lowest-install risk; nothing is downloaded or written by an installer.

Credentials

Only NEMO_TOKEN is declared as required and is the primary credential, which matches the need to call the remote API. The skill also describes an anonymous-token flow (generate UUID and request a 7-day token) so a token can be obtained without pre-provisioning credentials. The SKILL.md frontmatter mentions a config path (~/.config/nemovideo/) which could permit local token storage — this is related to the skill's purpose but the registry metadata omitted it, creating an inconsistency to verify.

Persistence & Privilege

always is false and model invocation is not disabled (default). The skill does not request persistent system-wide privileges or modify other skills. Autonomous invocation is allowed by default; that is normal but increases blast radius if a malicious skill were present (no evidence of that here).

Assessment

This skill appears to do what it says: it uploads videos to a remote render service and returns edited clips. Before installing: 1) Confirm you trust the external host (https://mega-api-prod.nemovideo.ai) — videos and possibly sensitive visual content will be uploaded to their servers. 2) Prefer using the anonymous-token flow (ephemeral token) if you don't want to store a permanent NEMO_TOKEN in your environment. 3) Note the SKILL.md frontmatter references a local config path (~/.config/nemovideo/) but the registry metadata omitted it — ask the publisher whether the skill will read/write that directory. 4) If you must keep private footage local, do not use this skill; or check the service's privacy/retention policy. 5) If you want higher assurance, request a verified source/homepage or inspect a published package/release for the service before enabling the skill.

Getting Started

Send me your video clips and I'll handle the AI object manipulation. Or just describe what you're after.

Try saying:

• "edit a 30-second MP4 clip with a person walking in frame into a 1080p MP4"
• "remove the background person and replace it with a solid color"
• "removing, replacing, or isolating objects inside video frames 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 Object Ops — Manipulate and Export Object Edits

Send me your video clips and describe the result you want. The AI object manipulation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 30-second MP4 clip with a person walking in frame, type "remove the background person and replace it with a solid color", and you'll get a 1080p MP4 back in roughly 30-90 seconds. All rendering happens server-side.

Worth noting: shorter clips with less camera movement give cleaner object tracking results.

Matching Input to Actions

User prompts referencing video object ops, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is video-object-ops, 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).

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

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 "remove the background person and replace it with a solid color" — 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 compatibility across platforms.

Common Workflows

Quick edit: Upload → "remove the background person and replace it with a solid color" → Download MP4. Takes 30-90 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.