Ai Shorts

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

Security Scan

The skill's behavior mostly matches a cloud video-processing tool, but there are small inconsistencies and privacy implications (automatic token creation and filesystem checks) you should understand before installing.

Purpose & Capability

The skill's name and description match its runtime instructions: it uploads videos to a cloud backend and returns rendered clips. One inconsistency: the registry metadata reported no required config paths, but the SKILL.md frontmatter lists a config path (~/.config/nemovideo/). That mismatch should be clarified but does not by itself break the declared purpose.

Instruction Scope

Instructions are focused on session creation, uploads, SSE editing, and exports to the stated backend (mega-api-prod.nemovideo.ai) — appropriate for video processing. Points to watch: the skill instructs the agent to (a) read the skill file frontmatter and detect the agent's install path to set X-Skill-Platform, and (b) poll and read session state. Those filesystem reads are limited and understandable for attribution, but they are broader than a purely stateless upload flow and should be disclosed to users.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes on-disk code risk; nothing in the manifest pulls binaries or external archives.

Credentials

The only declared credential is NEMO_TOKEN, which is proportional to a cloud video service. However, the SKILL.md instructs automatic acquisition of an anonymous token by POSTing to /api/auth/anonymous-token if NEMO_TOKEN is absent. That behavior is reasonable for convenience but has privacy implications (it will create/use an account-bound anonymous token and consume service credits). Also the SKILL.md references a config directory (~/.config/nemovideo/) which may be used to cache tokens; that should be made explicit.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It can be invoked autonomously (platform default), which is expected for skills, but it does not request permanent or cross-skill configuration changes.

Scan Findings in Context

[scanner-none] expected: No code files were present and the regex-based scanner had nothing to analyze. For instruction-only skills, the SKILL.md is the primary surface to review.

What to consider before installing

This skill uploads your videos to mega-api-prod.nemovideo.ai and requires a NEMO_TOKEN to operate. If you don't provide one it will automatically request an anonymous token from that domain and may cache it (7‑day expiry, 100 free credits per SKILL.md). Before installing, consider: (1) Are you comfortable sending your video content to this external service? (2) Do you consent to automatic token creation (the agent will call the service on your behalf)? (3) The skill will read its own frontmatter and check common skill install paths and a possible config directory (~/.config/nemovideo/) to set headers — if you have sensitive files or credentials in those paths, do not install. If you want to proceed, verify the service domain and privacy policy (there's no homepage listed here), and prefer supplying your own NEMO_TOKEN rather than allowing anonymous creation. If you need higher assurance, request the skill author/publisher info or a hosted homepage/repo before enabling.

Getting Started

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

Try saying:

• "generate a 10-minute YouTube video recording into a 1080p MP4"
• "cut the best moments into 60-second vertical clips for TikTok"
• "generating short clips from long recordings for TikTok and Reels creators"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

AI Shorts — Generate Short Clips from Videos

Drop your long-form video in the chat and tell me what you need. I'll handle the AI short clip generation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 10-minute YouTube video recording, ask for cut the best moments into 60-second vertical clips for TikTok, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — vertical 9:16 video works best for Reels and TikTok exports.

Matching Input to Actions

User prompts referencing ai shorts, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: ai-shorts
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else 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.

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)

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

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.

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 "cut the best moments into 60-second vertical clips for TikTok" — 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 social platforms.

Common Workflows

Quick edit: Upload → "cut the best moments into 60-second vertical clips for TikTok" → 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.