Sora Video Generator

generate text prompts into AI generated videos with this skill. Works with TXT, PNG, JPG, MP4 files up to 200MB. content creators use it for generating short...

Security Scan

The skill's behavior mostly matches a video-generation frontend, but it will upload user files and automatically obtain/store tokens with an external, unverified backend (no homepage/source) and there are minor metadata inconsistencies — proceed with caution and avoid sending sensitive data.

Purpose & Capability

Name/description match the runtime instructions: the SKILL.md drives a cloud-render backend (upload, SSE, export). Requesting NEMO_TOKEN is coherent for a service that requires auth. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata earlier indicated no required config paths — this inconsistency should be resolved. The skill asks for custom attribution headers and an install-path-derived platform header which is unusual but explainable for analytics/compatibility.

Instruction Scope

The instructions tell the agent to POST files and text to https://mega-api-prod.nemovideo.ai (uploads up to 200MB). They also instruct automatic anonymous-token creation (network call that mints a token if NEMO_TOKEN is not present). That means user-supplied content and generated auth tokens will be sent to an external third party. The instructions do not request unrelated local files or other environment secrets, but do implicitly require reading/deriving an install path value for X-Skill-Platform and reference a config directory in frontmatter (possible local persistence). If you plan to use private/sensitive media, this is risky.

Install Mechanism

No install spec and no code files (instruction-only), so nothing is written to disk by an installer. This is the lowest install risk. There is no downloaded binary or external archive referenced.

Credentials

Only NEMO_TOKEN is declared as required (primary credential), which is proportional for a cloud API. However the skill will automatically request an anonymous token from the service if NEMO_TOKEN is not present, which effectively creates credentials on the fly. The frontmatter also references a config path (~/.config/nemovideo/) which could imply writing tokens/config to disk; registry metadata did not declare this path — another inconsistency to clarify.

Persistence & Privilege

always:false and standard model invocation are used (no elevated persistent privilege). The skill does not request system-wide configuration changes or access to other skills' credentials. Potential local persistence (config path) is implied but not explicitly defined in registry metadata.

What to consider before installing

This skill will send your text and any uploaded media (up to 200MB) to an external service at mega-api-prod.nemovideo.ai and will mint an anonymous token if you don't provide NEMO_TOKEN. There is no source code or homepage listed for the service and the registry metadata has a small mismatch about config paths — so verify the service and its privacy/terms before sending sensitive content. If you decide to install or use it: (1) avoid uploading private or copyrighted media, (2) consider supplying your own NEMO_TOKEN (so the skill can't auto-create tokens on your behalf), (3) ask the publisher for a homepage or source repo and clarification about where/if tokens/configs are persisted, and (4) disable or limit autonomous invocation if your agent platform allows it to reduce accidental uploads.

Getting Started

Got text prompts to work with? Send it over and tell me what you need — I'll take care of the AI video creation.

Try saying:

• "generate a short text description of a scene into a 1080p MP4"
• "generate a 10-second video of a fox running through a snowy forest at sunset"
• "generating short videos from text prompts for content creators"

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.

Sora Video 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 creation 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, ask for generate a 10-second video of a fox running through a snowy forest at sunset, and about 1-3 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 produce more consistent results than vague long ones.

Matching Input to Actions

User prompts referencing sora video 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.

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

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

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

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

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

Common Workflows

Quick edit: Upload → "generate a 10-second video of a fox running through a snowy forest at sunset" → 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 10-second video of a fox running through a snowy forest at sunset" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.