Video Compose

Skip the learning curve of professional editing software. Describe what you want — combine all clips into one video with transitions and background music — a...

Security Scan

The skill's requirements and runtime instructions are coherent with its stated purpose: it uses a NEMO_TOKEN (or an anonymous token) to talk to a single cloud video-composition API and return composed video files.

Purpose & Capability

Name/description describe cloud video composing; declared primary env var (NEMO_TOKEN), API endpoints, upload and render workflows all align with that purpose. Requesting a token and session state is expected for a cloud render service.

Instruction Scope

SKILL.md instructs the agent to authenticate, create sessions, upload files, stream SSE, poll render status, and save session_id — all within the video-compose domain. It also instructs to add attribution headers (reads frontmatter/version) and to detect install path for platform attribution; that requires checking the skill’s frontmatter and potentially probing typical install paths, which is minor but outside pure video-processing logic.

Install Mechanism

No install spec or code is provided (instruction-only). Nothing gets downloaded or written by an installer as part of this skill bundle.

Credentials

Only one credential is declared (NEMO_TOKEN) and the instructions explain an anonymous-token fallback if no token is set. No unrelated secrets or multiple external credentials are requested.

Persistence & Privilege

Skill is not always-enabled and does not request elevated system privileges. It asks the agent to save session_id from the API (normal). The only file/config path mentioned is an optional config dir (~/.config/nemovideo/) for config/attribution; no instructions to modify other skills or global agent settings.

Assessment

This skill appears consistent with its description, but it will upload whatever video/audio files you give it to mega-api-prod.nemovideo.ai for cloud processing. Before using it, consider: (1) Do you trust the nemo video provider and its privacy/retention policies for the content you will upload? (2) Only supply a NEMO_TOKEN you control and are comfortable using for uploads; if you don't have one, the skill will request an anonymous token automatically. (3) The skill may read its frontmatter and check common install paths to build attribution headers — no other local files are requested. If you handle sensitive footage, test with non-sensitive clips first or avoid installing.

Getting Started

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

Try saying:

• "create three 30-second video clips with a background music file into a 1080p MP4"
• "combine all clips into one video with transitions and background music"
• "assembling multiple clips into a single polished video for content creators"

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.

Video Compose — Combine Clips Into One Video

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

Say you have three 30-second video clips with a background music file and want to combine all clips into one video with transitions and background music — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter individual clips with consistent resolution compose faster and with fewer glitches.

Matching Input to Actions

User prompts referencing video compose, 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.

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

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

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 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.

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.

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 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 "combine all clips into one video with transitions and background music" — 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 platforms and devices.

Common Workflows

Quick edit: Upload → "combine all clips into one video with transitions and background music" → 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.