Generator To Generator

Turn a 30-second AI-generated product clip into 1080p regenerated video output just by typing what you need. Whether it's converting one AI-generated video i...

Security Scan

The skill's requirements and runtime instructions are internally consistent with a cloud-based AI video regeneration service, but it will upload your videos and create/use an external token so review the service and privacy implications before use.

Purpose & Capability

The skill claims to regenerate AI videos on cloud GPUs and the SKILL.md describes API endpoints, upload and export workflows, and a single API credential (NEMO_TOKEN). The requested env var and described endpoints align with that purpose. The declared config path (~/.config/nemovideo/) and X-Skill-* header behaviour are plausible helpers for attribution/session management.

Instruction Scope

Instructions direct the agent to read NEMO_TOKEN (if present), create an anonymous token via the vendor's anonymous-token endpoint if not, create sessions, stream SSE events, and upload user-supplied video files to mega-api-prod.nemovideo.ai. This stays within the expected scope for a cloud render service, but it explicitly sends user media and session data to an external third party and instructs automatic token creation — important privacy/security implications to consider.

Install Mechanism

No install spec and no code files — instruction-only skill. Nothing is written to disk by an installer step here.

Credentials

Only one required environment variable (NEMO_TOKEN) is declared and used as the primary credential. The config path entry is reasonable (likely to look for previously saved tokens) and not disproportionate. No unrelated credentials or broad filesystem access are requested.

Persistence & Privilege

always is false and the skill does not request elevated or persistent platform-wide privileges. The SKILL.md suggests creating/using a token and a session for the service, which is normal for an API-backed skill.

Assessment

This skill uploads whatever video you drop into the chat to an external service (mega-api-prod.nemovideo.ai) and will create/use an anonymous NEMO_TOKEN if none is provided. Before installing or using it: verify the vendor/domain and privacy policy, avoid uploading sensitive or private videos, consider creating and supplying your own account token (so you control revocation), and confirm how/where the token is stored by your agent (session-only vs persistent config). Because this is an instruction-only skill with no install, the main risk is data exfiltration to the third-party API rather than local changes.

Getting Started

Share your AI-generated video and I'll get started on AI video regeneration. Or just tell me what you're thinking.

Try saying:

• "convert my AI-generated video"
• "export 1080p MP4"
• "take this AI-generated video and re-generate"

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.

Generator to Generator — Regenerate AI Videos Instantly

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

Here's a typical use: you send a a 30-second AI-generated product clip, ask for take this AI-generated video and re-generate it with a different style or variation, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter source clips produce faster and more consistent regenerated results.

Matching Input to Actions

User prompts referencing generator to 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is generator-to-generator, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise 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

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.

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 "take this AI-generated video and re-generate it with a different style or variation" — 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 → "take this AI-generated video and re-generate it with a different style or variation" → Download MP4. Takes 30-60 seconds 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.