Video Letter Maker Online

Get personalized video letters ready to post, without touching a single slider. Upload your photos, text, audio (JPG, PNG, MP4, MP3, up to 200MB), say someth...

Security Scan

The skill generally matches its stated purpose (uploading media to a cloud rendering API) but contains a few inconsistencies and vague instructions about credential handling and filesystem access that you should understand before installing.

Purpose & Capability

The name/description match the runtime instructions: the skill talks to a single external service (mega-api-prod.nemovideo.ai) to create video letters and uses a single credential (NEMO_TOKEN). The declared API endpoints and actions (session creation, upload, SSE, render/export) are coherent with a cloud render pipeline.

Instruction Scope

Instructions include expected operations (check env, create anonymous token if absent, create session, upload files, poll render). They also instruct the agent to detect install paths (~/.clawhub/, ~/.cursor/skills/) to set an attribution header and to store session tokens for subsequent requests. Detecting install paths and storing session state is slightly outside pure 'upload/convert' scope but can be justified for attribution and session handling; the instructions are otherwise explicit about what API calls to make. The skill will send user files (photos/audio) to a third-party API — users should be aware of privacy implications.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing will be downloaded or written by an installer. That minimizes install-time risk.

Credentials

Only one credential (NEMO_TOKEN) is required, which is proportionate to the described cloud API. However there is an inconsistency: registry metadata listed no required config paths, while the SKILL.md frontmatter includes a config path (~/.config/nemovideo/) and the skill both declares NEMO_TOKEN as required and gives instructions to auto-generate an anonymous token when one is not present. It's unclear whether the skill expects a pre-provisioned token or will create and persist one automatically — this ambiguity affects where credentials might be stored and for how long.

Persistence & Privilege

always:false (normal) and there's no installer, so the skill does not request permanent platform-wide presence. It does ask the agent to store a session_id and (implicitly) the anonymous token for later requests, and the frontmatter references a config path (~/.config/nemovideo/) where it may persist data. Confirm where tokens/sessions are stored if you require them to be ephemeral.

What to consider before installing

This skill sends your uploaded photos, text, and audio to a third-party API (mega-api-prod.nemovideo.ai) for cloud rendering and uses a single credential named NEMO_TOKEN. Before installing: (1) Decide whether you are comfortable uploading personal media to that external service and review its privacy/retention policy; (2) Clarify the credential behavior — the SKILL.md both lists NEMO_TOKEN as required and describes auto-generating an anonymous token (100 free credits, 7 days) and storing a session_id. Ask the publisher how/where tokens and session IDs are persisted (memory vs ~/.config/nemovideo/ vs environment); if you require tokens not be persisted, refuse automatic token creation; (3) Note the skill may read typical install paths to set an attribution header — this is low-risk but you should confirm it will not read unrelated files; (4) If you need stronger guarantees, request the skill source code or a privacy policy, and avoid uploading sensitive media until you verify storage/retention and token handling. The inconsistencies described above are why I rate this "suspicious" rather than "benign."

Getting Started

Send me your photos, text, audio and I'll handle the AI video letter creation. Or just describe what you're after.

Try saying:

• "create a personal photo and a typed heartfelt message into a 1080p MP4"
• "turn my written message and photos into a video letter I can send to my friend"
• "creating heartfelt video messages to send to friends and family for everyday users, gift senders, long-distance couples"

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.

Video Letter Maker Online — Create and Send Video Letters

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

Say you have a personal photo and a typed heartfelt message and want to turn my written message and photos into a video letter I can send to my friend — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: adding a voiceover or background music makes the video letter feel more personal.

Matching Input to Actions

User prompts referencing video letter maker online, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is video-letter-maker-online, 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).

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.

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 → "turn my written message and photos into a video letter I can send to my friend" → 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 my written message and photos into a video letter I can send to my friend" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, MP4, MP3 for the smoothest experience.

Export as MP4 for widest compatibility across devices and messaging apps.