Video Generator Generator

Turn a text description of a product demo scene into 1080p AI generated videos just by typing what you need. Whether it's generating videos from text prompts...

Security Scan

The skill's network calls and token handling mostly match its stated video-generation purpose, but there are inconsistencies and surprising behaviors (automatic anonymous token creation, hidden API responses, and a mismatch about config paths) that merit caution before installing.

Purpose & Capability

The skill's declared single credential (NEMO_TOKEN) and API endpoints are coherent with a cloud video-generation service. However, the registry metadata says "Required config paths: none" while the skill frontmatter and instructions reference a config path (~/.config/nemovideo/). That mismatch is unexplained and suggests the skill expects to read/write a local config directory even though the top-level metadata does not list it.

Instruction Scope

SKILL.md instructs the agent to automatically connect to an external backend on first open, generate an anonymous token (POST to an external domain) if NEMO_TOKEN is missing, and persist a session_id. It also instructs the agent not to display raw API responses or token values to the user. Automatic outbound network calls and opaque handling of tokens are reasonable for a cloud rendering service but are surprising behaviors that should be made explicit to users.

Install Mechanism

This is an instruction-only skill with no install spec or code files, so nothing is written to disk by an installer. That lowers the risk from the install mechanism itself.

Credentials

Only NEMO_TOKEN is requested (primary credential), which matches the described API usage. However, the skill will create an anonymous NEMO_TOKEN itself if none is present and appears to expect storing session/token data locally (per frontmatter configPaths). Confirm where tokens/session IDs are stored and for how long.

Persistence & Privilege

always:false (good). The skill does instruct itself to auto-connect on first open and to persist session state, which is normal for a cloud integration but could lead to unexpected outbound traffic or stored credentials. The skill does not request permissions to change other skills or system-wide settings.

What to consider before installing

Before installing, consider the following: the skill will make automatic outbound requests to https://mega-api-prod.nemovideo.ai and will generate and persist an anonymous token/session if NEMO_TOKEN is not provided. Ask the publisher (or decline if unknown) for: a privacy/data-retention statement, where exactly session/token data are stored (~/.config/nemovideo/ is referenced in the SKILL.md but not in the registry metadata), and whether uploaded media or prompt text are retained, logged, or used to train models. The instruction to "not display raw API responses or token values" is ambiguous—verify that this is for security (hiding tokens) and not to conceal errors or unexpected behavior. If you do not trust nemovideo.ai or cannot get clarifying info (source code, homepage, publisher identity), avoid installing or running the skill with sensitive data or on devices you care about.

Getting Started

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

Try saying:

• "generate my text prompts"
• "export 1080p MP4"
• "generate a 30-second video from this"

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 Generator Generator — Create Videos From Text Prompts

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

Say you have a text description of a product demo scene and want to generate a 30-second video from this script about a coffee brand launch — the backend processes it in about 1-3 minutes and hands you a 1080p MP4.

Tip: shorter, more specific prompts produce more accurate video results.

Matching Input to Actions

User prompts referencing video generator generator, 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 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	video-generator-generator
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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.

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 → "generate a 30-second video from this script about a coffee brand launch" → Download MP4. Takes 1-3 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 "generate a 30-second video from this script about a coffee brand launch" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across platforms and devices.