Create Ai Videos

generate text or images into AI-generated videos with this create-ai-videos skill. Works with MP4, MOV, PNG, JPG files up to 500MB. marketers, social media c...

Security Scan

The skill's requests and instructions are consistent with a cloud-based AI video service: it only needs a single service token, no install, and its runtime steps match the described purpose.

Purpose & Capability

The skill is a cloud video-generation connector and only requires a NEMO_TOKEN and an optional nemovideo config path, both of which align with the described API interactions and upload/export flows. No unrelated credentials or binaries are requested.

Instruction Scope

Runtime instructions direct the agent to create sessions, stream SSE, upload user-provided files, and poll a render endpoint — all appropriate for a video-rendering service. The skill also instructs reading the SKILL.md frontmatter for attribution and probing common install paths (~/.clawhub, ~/.cursor/skills/) to set X-Skill-Platform; this local path probing is minor but worth noting as it touches the agent's filesystem for platform detection. The instructions do not ask for broad system data or unrelated secrets.

Install Mechanism

There is no install spec and no code files; this is instruction-only, so nothing is downloaded or written to disk by an installer. This is the lowest-risk install model.

Credentials

Only a single credential (NEMO_TOKEN) is declared as required and is the primary credential used for API calls. The skill documents a fallback anonymous-token flow if NEMO_TOKEN is absent, which is coherent for anonymous usage. No unrelated environment variables are requested.

Persistence & Privilege

The skill does not request always:true and contains no instructions to modify other skills or system-wide settings. It creates ephemeral sessions/tokens for the service; there is no instruction to persist credentials system-wide.

Assessment

This skill appears to do what it says: it uploads user-provided media and talks to the nemo API to render videos. Before installing or using it: (1) only provide media you are willing to upload to an external service; (2) if you prefer not to use the anonymous token flow, set NEMO_TOKEN yourself so the skill won't request one; (3) be aware the skill may probe specific install/config paths (e.g., ~/.config/nemovideo/, ~/.clawhub/) to set attribution headers — if that concerns you, run the skill in an environment where those paths are absent or contain only expected data; and (4) verify you trust the external domain (mega-api-prod.nemovideo.ai) and the service's privacy policy for handling uploaded content and generated tokens.

Getting Started

Share your text or images and I'll get started on AI video creation. Or just tell me what you're thinking.

Try saying:

• "generate my text or images"
• "export 1080p MP4"
• "create a 30-second promotional video from"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Create AI Videos — Generate Videos from Text or Images

Send me your text or images and describe the result you want. The AI video creation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a short product description and three brand images, type "create a 30-second promotional video from my product photos and description", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter scripts with clear scenes generate more accurate results.

Matching Input to Actions

User prompts referencing create ai videos, 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.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

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

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.

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

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

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.

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)

Common Workflows

Quick edit: Upload → "create a 30-second promotional video from my product photos and description" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "create a 30-second promotional video from my product photos and description" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across all platforms.