Image To Video Magic Hour

Turn a single golden hour landscape photo into 1080p animated magic hour video just by typing what you need. Whether it's converting golden hour photos into...

Security Scan

The skill's requests and instructions are coherent with a remote image→video rendering service: it needs one API token (NEMO_TOKEN), uploads images to the specified API, and uses session tokens — but the publisher is unknown, so verify the remote service before use.

Purpose & Capability

Name/description match the actions in SKILL.md: all calls and env access relate to the nemo video rendering API. The only minor inconsistency is that the frontmatter metadata lists a config path (~/.config/nemovideo/) that was not declared in the registry metadata, but this does not contradict the stated purpose.

Instruction Scope

Runtime instructions are narrowly scoped to creating/using a session token, uploading user images, streaming SSE messages, and exporting renders. The skill instructs the agent to POST files (or URLs) to the service and to save session_id/token. It does not request unrelated system files or additional credentials. Note: uploading user images sends them off-platform to the external API (expected for this use-case).

Install Mechanism

No install spec and no code files — instruction-only. Nothing is downloaded or written by an installer, which minimizes local install risk.

Credentials

Only NEMO_TOKEN is required (and the SKILL.md provides a flow to generate an anonymous token if none is set). This is proportionate to calling the remote API. No unrelated credentials are requested.

Persistence & Privilege

The skill runs normally (always:false) and can be invoked autonomously. It asks the agent to keep session_id and to treat data.token as NEMO_TOKEN; it does not explicitly instruct writing system-wide settings or modifying other skills. Users should be aware the skill will create/hold short-lived auth tokens (7-day anonymous tokens) and may orphan server-side render jobs if a session is closed.

Assessment

This skill appears to do what it says: it uploads your images to a remote nemo-video API, renders video server-side, and returns a download URL. Before installing or using it, verify you trust the remote domain (mega-api-prod.nemovideo.ai) and the publisher (no homepage or clear owner info was provided). Ask about privacy/data retention and billing (the skill mentions a 100-credit anonymous token and 7-day expiry). If you are concerned about data/exposure: (1) use a throwaway/ephemeral token or an account created just for testing, (2) avoid uploading highly sensitive images, and (3) confirm where tokens/session IDs are stored and for how long server-side renders persist. The frontmatter notes a config path (~/.config/nemovideo/) that wasn't declared elsewhere — this is a minor inconsistency but worth confirming whether any local config will be written.

Getting Started

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

Try saying:

• "convert my still images"
• "export 1080p MP4"
• "turn this sunset photo into a"

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.

Image to Video Magic Hour — Turn Photos into Cinematic Videos

Send me your still images and describe the result you want. The AI video creation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a single golden hour landscape photo, type "turn this sunset photo into a cinematic magic hour video with warm light animation", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: high-contrast golden hour images with clear skies produce the most dramatic lighting animations.

Matching Input to Actions

User prompts referencing image to video magic hour, 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	image-to-video-magic-hour
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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 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

Common Workflows

Quick edit: Upload → "turn this sunset photo into a cinematic magic hour video with warm light animation" → 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 "turn this sunset photo into a cinematic magic hour video with warm light animation" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across Instagram, TikTok, and YouTube.