Shorts Automation

convert long-form video into vertical short clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. TikTok creators use it for generating sh...

Security Scan

The skill's declared purpose (video-to-shorts) matches its runtime behavior (calls a remote rendering API), but there are metadata inconsistencies and privacy-sensitive instructions (automatic token creation, hiding token values, uploading user videos to an unknown third-party domain) that warrant caution.

Purpose & Capability

The skill's stated purpose—server-side conversion of long videos into vertical shorts—lines up with the runtime instructions that upload files and request renders from a remote API (mega-api-prod.nemovideo.ai). However the registry metadata and the SKILL.md disagree: registry lists no config paths while the skill frontmatter references ~/.config/nemovideo/, and the registry marks NEMO_TOKEN as required even though the instructions describe auto-generating a token if it's not present. Those mismatches are incoherent and should be clarified.

Instruction Scope

The SKILL.md instructs the agent to (a) POST to an external API to obtain an anonymous token, (b) upload user video files (or fetch via URL) to that external domain, and (c) keep API tokens and raw responses hidden from the user. Uploading potentially large and sensitive user videos to an external service is expected for a cloud-rendering skill, but the explicit guidance to conceal API responses/tokens reduces transparency and is concerning. The instructions also require specific attribution headers and persistent session storage, which increases the amount of data retained server-side.

Install Mechanism

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

Credentials

The only credential in requires.env is NEMO_TOKEN, which is proportionate to calling a remote API. However, the skill both marks NEMO_TOKEN as required in registry metadata and documents a path to auto-create and use an anonymous token if it is absent. That inconsistency (required vs auto-create) and the frontmatter mention of a config path (~/.config/nemovideo/) that the registry didn't list are unexplained.

Persistence & Privilege

always:false and default autonomous invocation settings are normal. The skill asks to store a session_id for subsequent requests and to include that ID in API calls; this is expected for a remote-render workflow. There is no instruction to modify other skills or system-wide settings.

What to consider before installing

This skill sends your videos and session data to a third-party API (mega-api-prod.nemovideo.ai) for cloud rendering; that's consistent with its purpose but has privacy implications. Before installing, consider: (1) Do you trust this unknown service? There's no homepage or source listed. (2) Avoid uploading sensitive or private videos unless you verify the provider's privacy/retention policy. (3) Prefer providing your own NEMO_TOKEN if you can (so you control the credential) — the SKILL.md both marks NEMO_TOKEN as required and describes auto-creating an anonymous token, which should be clarified. (4) Ask the publisher how and where session tokens and uploaded files are stored and for how long. (5) Because the SKILL.md instructs the agent to hide raw API responses and token values from users, be extra cautious: request clear, auditable logs or use a vetted alternative. If you need higher assurance, only install skills from a known author or with a verifiable homepage/privacy policy.

Getting Started

Ready when you are. Drop your long-form video here or describe what you want to make.

Try saying:

• "convert a 10-minute YouTube video recording into a 1080p MP4"
• "automatically cut this video into 5 vertical shorts with captions"
• "generating short clips from long recordings for TikTok 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.

Shorts Automation — Convert Long Videos Into Shorts

Send me your long-form video and describe the result you want. The AI shorts generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 10-minute YouTube video recording, type "automatically cut this video into 5 vertical shorts with captions", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: videos under 15 minutes produce the most accurate clip selections.

Matching Input to Actions

User prompts referencing shorts automation, 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	shorts-automation
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 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)

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "automatically cut this video into 5 vertical shorts with captions" — concrete instructions get better results.

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

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

Common Workflows

Quick edit: Upload → "automatically cut this video into 5 vertical shorts with captions" → Download MP4. Takes 1-2 minutes 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.