Video Json Ai

Skip the learning curve of professional editing software. Describe what you want — extract video metadata and scene data as structured JSON — and get structu...

Security Scan

The skill's requirements and runtime instructions are coherent with a remote video-processing API: it asks for a single API token and instructs uploads and API calls; nothing obviously unrelated or excessive was requested, but there are small metadata inconsistencies and privacy risks to consider before use.

Purpose & Capability

The skill claims to extract video metadata/scene data and its runtime instructions call a remote video-processing API and ask for a single API token (NEMO_TOKEN). That is consistent. Minor inconsistency: the registry metadata earlier listed no required config paths, while the SKILL.md YAML frontmatter references a config path (~/.config/nemovideo/) and runtime header heuristics that derive an install path. This mismatch is likely benign but worth noting.

Instruction Scope

The SKILL.md instructs the agent to authenticate (use NEMO_TOKEN or obtain an anonymous token), create a session, upload video files or URLs, and poll/export results. All instructions relate to the stated purpose (uploading videos and getting JSON/exports). It does not instruct reading unrelated system files, secrets, or printing tokens (it explicitly says not to).

Install Mechanism

There is no install spec and no code files (instruction-only), so nothing is written to disk by an installer. This is the lowest-risk install model.

Credentials

The skill requires a single primary env var, NEMO_TOKEN, which matches a service API token and is proportionate. Note the YAML frontmatter also mentions a config path (~/.config/nemovideo/) and the SKILL.md describes deriving platform headers from an install path; those are minor additional local assumptions that weren't declared in the registry requirements and create a small inconsistency.

Persistence & Privilege

The skill is not always-enabled and does not request elevated or persistent system-wide privileges. It stores a session_id for the remote service (normal) and does not modify other skills or system configs.

Assessment

This skill appears to do what it says: it uploads videos to a remote API (mega-api-prod.nemovideo.ai) and returns structured JSON or exported video files. Before installing or using it, consider: 1) privacy — your videos are sent to a third-party service; avoid uploading sensitive content unless you trust the provider and have reviewed their privacy/retention policy; 2) credentials — NEMO_TOKEN grants API access (rotate or revoke it if exposed); provide only tokens/accounts you control for this service; 3) test with non-sensitive/sample videos first to confirm behavior and costs; 4) note the small metadata mismatch (declared vs. SKILL.md config paths) — ask the publisher whether the skill reads/writes ~/.config/nemovideo/ or install-paths if that matters to you. If you need stronger assurance about the vendor or data handling, request the skill's homepage or source and a privacy/security disclosure from the publisher before using it.

Getting Started

Got video clips to work with? Send it over and tell me what you need — I'll take care of the AI JSON data extraction.

Try saying:

• "convert a 2-minute product demo video into a 1080p MP4"
• "extract video metadata and scene data as structured JSON"
• "extracting structured JSON metadata from video files for developers for developers and marketers"

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 JSON AI — Extract Video Data as JSON

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

A quick example: upload a 2-minute product demo video, type "extract video metadata and scene data as structured JSON", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds produce cleaner JSON output with fewer parsing errors.

Matching Input to Actions

User prompts referencing video json 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.

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-json-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).

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 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)

Common Workflows

Quick edit: Upload → "extract video metadata and scene data as structured JSON" → 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 "extract video metadata and scene data as structured JSON" — concrete instructions get better results.

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

Export source video as MP4 with H.264 codec for fastest AI processing.