Ai Video Detector Free

Get detection result report ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "...

Security Scan

The skill's declared need for a single NEMO_TOKEN and cloud API usage matches its purpose, but inconsistencies in metadata and runtime instructions (automatic token minting, hidden token handling, reading install paths, unknown service origin) raise privacy and provenance concerns.

Purpose & Capability

The skill claims to detect AI-generated video and uses a single service credential (NEMO_TOKEN) which is appropriate. However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) and an install-path-based attribution check that are not reflected in the registry manifest — an inconsistency about what filesystem access the skill expects.

Instruction Scope

Instructions tell the agent to automatically obtain an anonymous token via POST to mega-api-prod.nemovideo.ai if NEMO_TOKEN isn't set, store a session_id, and to keep raw API responses and token values hidden from the user. The skill also instructs the agent to detect its install path to set an attribution header (requiring filesystem interrogation). Automatic token creation and explicit instructions to hide token/response content reduce transparency and could be used to persist credentials or exfiltrate data without clear user visibility.

Install Mechanism

No install spec or code files: the skill is instruction-only, which minimizes code-written-to-disk risk.

Credentials

Only NEMO_TOKEN is required and is directly relevant. But the SKILL.md itself will mint and store an anonymous token when none is present, so the skill can obtain credentials autonomously. The manifest vs frontmatter mismatch about configPaths is a proportionality/clarity concern.

Persistence & Privilege

always:false and default autonomous invocation are set (normal). The skill asks to create and store session tokens for API calls, but it does not request always-on/system-wide privileges.

What to consider before installing

This skill talks to a remote service (mega-api-prod.nemovideo.ai) and will upload videos to that cloud. Before installing, consider: (1) provenance — there is no homepage or owner information and the service domain is not familiar; (2) privacy — uploaded videos (and any sensitive frames/audio) will leave your environment; (3) token handling — the skill will mint an anonymous NEMO_TOKEN if none is present and explicitly instructs the agent not to display raw tokens/responses (this reduces transparency about what is stored or sent); (4) filesystem reads — the skill may inspect install paths and referenced config dirs despite registry metadata not listing those paths. If you proceed, prefer using an ephemeral/limited credential (or set NEMO_TOKEN yourself), avoid uploading sensitive material, and verify the service's privacy/terms (or test in an isolated environment). If you need higher assurance, ask the skill author for a homepage/source repo and explanation of why it mints/stores tokens and reads install paths.

Getting Started

Ready when you are. Drop your video clips here or describe what you want to make.

Try saying:

• "detect a 2-minute YouTube video clip into a 1080p MP4"
• "check if this video was made by AI or a real person"
• "identifying whether a video was AI-generated or real for journalists, researchers, content moderators"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

AI Video Detector Free — Detect AI-Generated Video Content

Drop your video clips in the chat and tell me what you need. I'll handle the AI-generated video detection on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 2-minute YouTube video clip, ask for check if this video was made by AI or a real person, and about 20-40 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips under 60 seconds produce faster and more accurate detection results.

Matching Input to Actions

User prompts referencing ai video detector free, 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.

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

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

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

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.

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.

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

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)

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

Common Workflows

Quick edit: Upload → "check if this video was made by AI or a real person" → Download MP4. Takes 20-40 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "check if this video was made by AI or a real person" — concrete instructions get better results.

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

Upload as MP4 for the most reliable detection analysis.