Video Object

Skip the learning curve of professional editing software. Describe what you want — track and highlight the moving car in the background throughout the clip —...

Security Scan

The skill's claimed purpose (server-side object tracking and export) matches the actions described (uploading videos, calling the remote NEMO API, managing a session token), but there are a few small inconsistencies and privacy considerations you should review before use.

Purpose & Capability

Name/description (object tracking and export) lines up with the runtime instructions: upload video files, create/use a NEMO_TOKEN, create a session, send SSE and render requests to the listed nemo API endpoints. The primary credential requested (NEMO_TOKEN) is appropriate for a hosted processing service.

Instruction Scope

Instructions ask the agent to upload local video files (multipart/form-data or URL uploads), create/use an anonymous token if NEMO_TOKEN is missing, and persist session_id for job polling. They also instruct the agent to derive attribution headers (X-Skill-Source, X-Skill-Version, X-Skill-Platform) including detecting the skill install path. These behaviors are coherent for this kind of remote-service skill but mean the agent will read files you provide and may examine its install path and save session IDs; the doc explicitly warns not to print tokens/raw JSON.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. All network interactions are explicit in SKILL.md; nothing is downloaded or executed on the user's machine by an installer.

Credentials

Only NEMO_TOKEN is declared as required (primary credential), which is proportional. However, the SKILL.md frontmatter references a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — an inconsistency worth clarifying. The skill can also generate an anonymous token itself if NEMO_TOKEN is not set, so it does not strictly require pre-provisioned credentials.

Persistence & Privilege

always:false and normal autonomous invocation settings. The skill will create and store a session_id (to poll render jobs) and uses bearer tokens for API calls; it does not request elevated system-wide privileges or modify other skills' configuration in the provided instructions.

Assessment

This skill uploads your video files to a third-party API (mega-api-prod.nemovideo.ai) and uses a bearer token (NEMO_TOKEN) or an anonymous token it can obtain for you. Before installing or invoking it, consider: 1) Privacy: do you want these videos sent to an external service? Confirm the vendor, retention and deletion policy for uploaded media. 2) Credentials: you can set a specific NEMO_TOKEN or let the skill generate an anonymous token (temporary credits); avoid reusing sensitive credentials. 3) Local access: the skill will read files you provide and may inspect its install path and save session IDs locally — confirm you’re comfortable with that. 4) Metadata mismatch: the SKILL.md mentions a config path (~/.config/nemovideo/) that the registry metadata did not list; ask the author to clarify whether any config files are read or written. If you need stronger assurance, request the skill owner/publisher information, a privacy statement, or an explicit list of headers and local storage behavior before using it with sensitive videos.

Getting Started

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

Try saying:

• "track my video clips"
• "export 1080p MP4"
• "track and highlight the moving car"

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 — Track and Export Object Videos

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

A quick example: upload a 2-minute product demo video, type "track and highlight the moving car in the background throughout the clip", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: high-contrast objects with clear edges are tracked most accurately.

Matching Input to Actions

User prompts referencing video object, 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.

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

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

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 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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "track and highlight the moving car in the background throughout the clip" — 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 balance of quality and file size.

Common Workflows

Quick edit: Upload → "track and highlight the moving car in the background throughout the clip" → Download MP4. Takes 30-60 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.