Image To Video Json Prompt

convert images into animated video clips with this skill. Works with JPG, PNG, WEBP, GIF files up to 200MB. developers and content creators use it for turnin...

Security Scan

The skill's requests and runtime instructions mostly match its stated image→video purpose, but it instructs filesystem probing (install-path detection), automatic anonymous token creation, and leaves session storage unspecified — small inconsistencies that warrant caution.

Purpose & Capability

Name/description align with required credential (NEMO_TOKEN) and declared config path (~/.config/nemovideo/). All declared requirements (NEMO_TOKEN, session handling) are coherent with a hosted video-rendering backend (mega-api-prod.nemovideo.ai).

Instruction Scope

SKILL.md instructs network calls to the nemovideo backend and to auto-generate an anonymous token when NEMO_TOKEN is absent — this is coherent but performs outbound network activity and credential creation without explicit user consent. It also tells the agent to derive an X-Skill-Platform header by detecting an install path (~/.clawhub/, ~/.cursor/skills/) which implies probing the user's home filesystem; that filesystem access is not declared in requires.configPaths and is not necessary for core image→video functionality. The doc also says to 'store' session_id but does not specify where (memory vs disk), producing ambiguity about persistence.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. All behavior is driven by SKILL.md runtime instructions; nothing is downloaded or written by an installer step in the package metadata.

Credentials

Only one credential (NEMO_TOKEN) is required and listed as primary, which fits a single external rendering service. However the skill also documents a fallback anonymous-token acquisition flow (POST to /api/auth/anonymous-token) that will create short-lived tokens on the service; this changes the threat model because the skill can operate (and upload user images) even if the user doesn't supply credentials.

Persistence & Privilege

always:false and no install-time persistence requested. The skill may retain session_id and tokens for the session (normal), but it does not request elevated/system-wide privileges or declare forced persistence. Autonomous invocation is allowed (platform default) — combine with other concerns when deciding.

What to consider before installing

This skill is mostly consistent with a hosted image→video service, but consider these points before installing or using it: - Data privacy: the skill uploads images and audio to https://mega-api-prod.nemovideo.ai (third-party service). Only proceed if you trust that endpoint and its privacy policy. - Token behavior: if you don't set NEMO_TOKEN, the skill will automatically request an anonymous token and proceed. If you prefer explicit consent, provide your own token and/or block the anonymous-token endpoint. - Filesystem probing: the instructions ask the agent to detect install paths (~/.clawhub, ~/.cursor/skills) to set a header. That requires checking parts of your home directory; if you want to prevent this, deny filesystem access or ask the maintainer to remove that behavior. - Session storage: the doc doesn't specify where session_id or anonymous tokens are stored. Ask the skill author how long tokens/sessions persist and whether anything is written to disk (~/.config/nemovideo/ was listed). If you need guarantees, require in-memory-only storage or clear documentation. If any of the above is unacceptable (privacy of uploaded content, automatic token creation, or filesystem probing), do not enable the skill or require the vendor provide a version that only runs when you explicitly supply NEMO_TOKEN.

Getting Started

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

Try saying:

• "convert my images"
• "export 1080p MP4"
• "convert these images into a smooth"

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.

Image to Video JSON Prompt — Convert Images into Videos via JSON

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

Here's a typical use: you send a three product photos in JPG format, ask for convert these images into a smooth video with transitions and motion effects, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — structuring your JSON prompt with clear motion and duration fields gives more predictable results.

Matching Input to Actions

User prompts referencing image to video json prompt, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is image-to-video-json-prompt, 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).

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

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

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.

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

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 → "convert these images into a smooth video with transitions and motion effects" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "convert these images into a smooth video with transitions and motion effects" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, WEBP, GIF for the smoothest experience.

Use PNG images for cleaner edges and better AI interpretation during video rendering.