Remover From Video

edit video clips into cleaned video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators, marketers, YouTubers use it fo...

Security Scan

The skill's behavior (uploading videos to a third‑party cloud API and auto‑generating tokens) is coherent with its stated purpose, but there are provenance and metadata inconsistencies and a few instructions that request access beyond a minimal, clearly-justified surface.

Purpose & Capability

The skill name/description (cloud-based object removal) matches the network endpoints and flows in SKILL.md (session creation, upload, render, export). Requesting a single service token (NEMO_TOKEN) is expected. However, the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry metadata lists no required config paths — this mismatch is an inconsistency in declared requirements. The SKILL.md also instructs deriving an X-Skill-Platform value by probing install paths in the user home, which suggests filesystem inspection that isn't justified by the stated capability.

Instruction Scope

The runtime instructions will cause the agent to: contact https://mega-api-prod.nemovideo.ai, exchange/obtain an anonymous token, create sessions, upload user video files (multipart file uploads or URLs), stream SSE, and poll for rendered output. Uploading user video content to an external service is intrinsic to the skill, but the instructions also ask the agent to detect install paths (~/.clawhub/, ~/.cursor/skills/) to set headers — this implies reading local filesystem paths. The doc emphasizes not to 'expose tokens' but also instructs extracting and using tokens programmatically. There are no instructions that read unrelated system files, but the platform-detection and mismatched configPaths raise scope creep concerns.

Install Mechanism

This is instruction-only with no install spec and no code files — nothing new is written to disk by an installer. That reduces supply-chain risk compared with arbitrary downloads.

Credentials

Only one environment variable is declared (NEMO_TOKEN / primaryEnv), which is proportionate for a cloud API skill. But SKILL.md describes obtaining an anonymous token automatically if NEMO_TOKEN is absent, and the frontmatter references a config path (~/.config/nemovideo/) that is not declared in the registry metadata — an inconsistency. The skill does not request other unrelated credentials, which is good.

Persistence & Privilege

always:false and no install hooks are present. The skill does not request permanent platform presence or permissions to modify other skills or global config. Session state (session_id) is expected to be kept only for in-session operations as described.

What to consider before installing

This skill will send your video files to a third‑party cloud service (mega-api-prod.nemovideo.ai) for processing and will programmatically obtain or use a NEMO_TOKEN. Before installing or using it: 1) Confirm you trust the endpoint and check its privacy/terms (there is no homepage or publisher info provided). 2) Do not upload sensitive or private footage unless you accept that it will be transmitted to and stored/processed by that service. 3) Ask the publisher why the SKILL.md frontmatter lists a config path and why the skill needs to probe local install paths — this reads local filesystem metadata and is not strictly necessary for video processing. 4) Prefer providing your own NEMO_TOKEN only if you trust the service; anonymous token creation is supported but still contacts the remote API. 5) If privacy is critical, consider local alternatives (ffmpeg + local inpainting models) instead of a cloud upload. If you want a firmer judgement, provide the skill publisher, a homepage/privacy policy, or network traces of the exact HTTP calls the agent will make.

Getting Started

Share your video clips and I'll get started on AI object removal. Or just tell me what you're thinking.

Try saying:

• "edit my video clips"
• "export 1080p MP4"
• "remove the logo in the bottom"

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.

Remover from Video — Remove Objects and Export Clean Video

This tool takes your video clips and runs AI object removal through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 60-second MP4 clip with an unwanted watermark or person in the background and want to remove the logo in the bottom right corner from my entire video — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter clips with a static background produce the cleanest removal results.

Matching Input to Actions

User prompts referencing remover from video, 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 remover-from-video, 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

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.

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 → "remove the logo in the bottom right corner from my entire video" → 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 "remove the logo in the bottom right corner from my entire video" — 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.