Japanese Photo Video Maker

Japanese content creators create Japanese photos into photo slideshow video using this skill. Accepts JPG, PNG, HEIC, WebP up to 200MB, renders on cloud GPUs...

Security Scan

The skill's actions (uploading photos to a third‑party rendering backend and using a NEMO_TOKEN) match its stated purpose, but inconsistencies about where it stores session data and automatic token generation plus the lack of source/homepage mean you should be cautious before installing.

Purpose & Capability

The skill's name and description (turn photos into slideshow videos) align with the runtime instructions (upload photos, request renders from a cloud GPU backend). Requiring NEMO_TOKEN and calls to nemovideo.ai are coherent with the stated purpose. Note: the registry metadata earlier listed no config paths but the SKILL.md frontmatter declares a config path (~/.config/nemovideo/), an inconsistency that should be resolved.

Instruction Scope

Instructions direct the agent to upload user photos and metadata to https://mega-api-prod.nemovideo.ai, obtain or reuse a bearer token (NEMO_TOKEN), open SSE streams, poll render status, and persist a session_id for subsequent requests. Uploading user media to an external service is expected for this functionality, but the skill also instructs automatic anonymous-token creation when NEMO_TOKEN is absent and to 'store the returned session_id' without specifying storage scope or retention—this may lead to persistent credentials/config being written to disk or retained across sessions. The SKILL.md also instructs not to display raw API responses or tokens to the user, which could hide sensitive values if stored.

Install Mechanism

Instruction-only skill with no install spec and no code files: nothing is written to disk by an install step. This is the lowest install risk.

Credentials

Only NEMO_TOKEN is declared as a required environment variable (primary credential), which is appropriate for a service that authenticates requests. However, the SKILL.md frontmatter also declares a config path (~/.config/nemovideo/) not present in the registry metadata—this mismatch is unexplained. The skill will generate an anonymous token if none exists, which is reasonable but means credentials may be created and used transparently.

Persistence & Privilege

The skill is not always-enabled and uses normal autonomous invocation, which is expected. The concern is that it instructs persisting a session_id and the frontmatter lists a config directory; storing session tokens or config on disk would increase the blast radius if those files are accessible to other processes or skills. There is no justification in metadata for persistent config beyond the SKILL.md, and no guidance on how long tokens/sessions are retained or how a user can revoke them.

What to consider before installing

This skill appears to do what it says (upload photos to a cloud renderer) but you should be careful before installing: 1) Understand privacy: your photos and any metadata will be sent to mega-api-prod.nemovideo.ai — only upload content you are comfortable sharing with a third party. 2) Ask the publisher for source/homepage and clarify where session tokens are stored (in-memory vs ~/.config/nemovideo/) and how to delete/revoke them. 3) If you don't want persistent credentials/files, do not set NEMO_TOKEN and verify the agent does not write tokens to disk; consider running in an environment where written config is ephemeral. 4) If you are concerned about autonomous use, restrict or monitor the skill's permissions and network activity. 5) If you need higher assurance, request an official endpoint description, privacy policy, and verify the domain/owner before providing real content.

Getting Started

Got Japanese photos to work with? Send it over and tell me what you need — I'll take care of the AI video creation.

Try saying:

• "create ten Japanese travel or family photos into a 1080p MP4"
• "turn my Japanese photos into a slideshow video with music and transitions"
• "creating videos from Japanese photo collections for Japanese content creators"

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.

Japanese Photo Video Maker — Turn Photos Into Shareable Videos

This tool takes your Japanese photos and runs AI video creation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have ten Japanese travel or family photos and want to turn my Japanese photos into a slideshow video with music and transitions — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: organizing photos in numbered order before upload keeps the sequence intact.

Matching Input to Actions

User prompts referencing japanese photo video maker, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

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

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

Header	Value
X-Skill-Source	japanese-photo-video-maker
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

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)

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

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.

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn my Japanese photos into a slideshow video with music and transitions" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.

Common Workflows

Quick edit: Upload → "turn my Japanese photos into a slideshow video with music and transitions" → 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.