Ai Generator

Skip the learning curve of professional editing software. Describe what you want — generate a 30-second video from my script idea about product launch — and...

Security Scan

The skill's instructions largely match its stated purpose (cloud video generation) and only request one credential (NEMO_TOKEN), but there are metadata inconsistencies and a few minor scope/visibility concerns you should review before installing.

Purpose & Capability

Name/description describe cloud video generation and the SKILL.md instructs only about calling a nemo-video API and uploading media — the single required env var (NEMO_TOKEN) is appropriate. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata above lists no required config paths — an inconsistency worth clarifying.

Instruction Scope

Runtime instructions direct the agent to: use NEMO_TOKEN (or obtain an anonymous token via a POST to the nemo API), create a session, upload user media (up to 500MB), drive SSE streams, poll render endpoints, and include attribution headers. All of these are consistent with a cloud-rendering video service. The instructions do not request unrelated system data (shell history, other creds) but they do instruct the agent to detect install path to set X-Skill-Platform, which implies reading local paths — confirm what exact path checks are performed and that no other local files are read.

Install Mechanism

Instruction-only skill with no install spec or code files — lowest install risk. There is no download/extract or third-party package installation described.

Credentials

Only NEMO_TOKEN is required (declared as primaryEnv). The SKILL.md also instructs obtaining an anonymous token when NEMO_TOKEN is absent. This is proportionate to the service. The only concern is the SKILL.md frontmatter listing a config path (~/.config/nemovideo/) that could enable reading local configuration; the top-level manifest lists no config paths — clarify which is authoritative.

Persistence & Privilege

always:false and no special persistent/system-wide privileges requested. The skill can be invoked autonomously by the agent (default) but does not ask for forced always-on presence or to modify other skills' configs.

What to consider before installing

This skill appears to do what its description says (call an external 'nemovideo' API and upload user media), but check the following before installing: 1) Confirm the authoritative metadata: SKILL.md frontmatter includes a config path (~/.config/nemovideo/) even though the registry summary lists none — ask the publisher whether the skill will read that directory. 2) Understand that the skill will contact https://mega-api-prod.nemovideo.ai and will upload any media you provide (up to 500MB); do not upload sensitive videos or private credentials. 3) NEMO_TOKEN is the only required credential; if you must provide it, prefer a scoped or ephemeral token rather than long-lived credentials. 4) The skill can obtain an anonymous token on its own if no NEMO_TOKEN is present — if you want to avoid auto-registration, block outbound calls or require explicit user consent. 5) Because the source and homepage are unknown, prefer to use this in a sandboxed environment or request publisher/source verification before granting access to sensitive data. If the publisher can explain the configPath discrepancy and confirm no other local files are read, confidence would increase.

Getting Started

Send me your text prompts or clips and I'll handle the AI video generation. Or just describe what you're after.

Try saying:

• "generate a short text description like 'a sunset timelapse over a city' into a 1080p MP4"
• "generate a 30-second video from my script idea about product launch"
• "generating videos from text prompts or source clips for content creators and marketers"

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.

AI Generator — Generate Videos from Text Prompts

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

Say you have a short text description like 'a sunset timelapse over a city' and want to generate a 30-second video from my script idea about product launch — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter and more specific prompts tend to produce more accurate results.

Matching Input to Actions

User prompts referencing ai 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 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-generator
• 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 field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

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 "generate a 30-second video from my script idea about product launch" — concrete instructions get better results.

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

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "generate a 30-second video from my script idea about product launch" → 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.