To Generator Generator

Get generated video clips ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, MP4, up to 200MB), say something like "g...

Security Scan

The skill's declared requirements roughly match its stated purpose (video generation), but there are inconsistencies and a few operational details that raise caution before you hand over an auth token or local files.

Purpose & Capability

Name/description (generate videos from text) aligns with the single required credential (NEMO_TOKEN) and the API endpoints described. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths, and the skill has no listed homepage or source — making provenance unclear.

Instruction Scope

Runtime instructions tell the agent to use NEMO_TOKEN if present or obtain an anonymous token, create sessions, post SSE messages, and upload files via multipart (including local file paths like -F "files=@/path"). That implies the agent may read local files provided by the user and may attempt to access a config directory (frontmatter). The instructions also ask the agent to auto-detect an 'install path' for a header value, which could require inspecting local paths. These behaviors are plausible for the stated purpose but give the agent broad discretion to access files and environment values — the SKILL.md does not clearly limit which files are acceptable.

Install Mechanism

Instruction-only skill with no install spec or code files; nothing is written to disk by an installer. This minimizes install-time risk.

Credentials

Only NEMO_TOKEN is declared as required and is the primary credential — that fits the described API usage. But the SKILL.md also lists a config path (~/.config/nemovideo/) in its frontmatter (not reflected in registry metadata). If present, that path might contain tokens/credentials. Using a full account token (NEMO_TOKEN) will allow the skill to act on your account and consume credits; consider scope and lifetime. The skill also instructs obtaining an anonymous token from the service if no NEMO_TOKEN is present, which is expected but means the skill will talk to an external backend regardless.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request permanent/always-on inclusion or system-wide changes. Autonomous invocation is allowed by default; no evidence the skill modifies other skills or global settings.

What to consider before installing

This skill appears to do what it says (cloud video generation) but exercise caution before installing or setting NEMO_TOKEN in your environment. Key considerations: - Unknown source/no homepage: there is no public project page or author info to verify the backend domain (mega-api-prod.nemovideo.ai). Try to verify the service independently before trusting credentials. - Token scope and risk: NEMO_TOKEN grants the skill full bearer access to the remote service (and could use your credits). Prefer to use a limited or throwaway token, or let the skill use an anonymous token if that suits your needs. - Local files and config: the instructions indicate uploads via local file paths and reference a config directory in the SKILL.md. Don’t allow uploads of sensitive local files. If the platform exposes a sandboxed upload mechanism, prefer that rather than giving arbitrary filesystem paths. - Ask the maintainer: request a homepage, privacy/security docs, and explicit explanation of what is stored in ~/.config/nemovideo/ and what token scopes NEMO_TOKEN has. If you can’t verify provenance, avoid setting a long-lived NEMO_TOKEN in your environment. If you want, I can draft a short checklist or message you can send to the skill author to request these clarifications before installing.

Getting Started

Ready when you are. Drop your text prompts here or describe what you want to make.

Try saying:

• "generate a short text description of a scene or concept into a 1080p MP4"
• "generate a video from this prompt: 'a sunrise over a mountain range with cinematic panning'"
• "generating videos from text prompts for content creators"

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.

To Generator Generator — Generate Videos From Text Prompts

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

Here's a typical use: you send a a short text description of a scene or concept, ask for generate a video from this prompt: 'a sunrise over a mountain range with cinematic panning', and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter, more specific prompts tend to produce more accurate results.

Matching Input to Actions

User prompts referencing to 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.

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

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

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.

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.

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.

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

Common Workflows

Quick edit: Upload → "generate a video from this prompt: 'a sunrise over a mountain range with cinematic panning'" → 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 "generate a video from this prompt: 'a sunrise over a mountain range with cinematic panning'" — concrete instructions get better results.

Max file size is 200MB. Stick to TXT, DOCX, PDF, MP4 for the smoothest experience.

Export as MP4 for widest compatibility.