Veo 3 Ai

Get AI generated videos ready to post, without touching a single slider. Upload your text prompts (MP4, MOV, WebM, GIF, up to 500MB), say something like "gen...

Security Scan

The skill's declared purpose (AI video generation) matches most of its instructions, but there are small inconsistencies and a few instructions that could cause the agent to read local paths or send uploads to an unknown external API — verify provenance and token usage before installing.

Purpose & Capability

Name/description (generate videos) aligns with the runtime instructions and the single required credential (NEMO_TOKEN). However the SKILL.md metadata declares a configPaths entry (~/.config/nemovideo/) that the registry summary did not list — this inconsistency should be clarified (does the skill need to access that local config?).

Instruction Scope

Instructions are focused on calling the external nemovideo API, uploading media, streaming SSE events, and polling render status — all consistent with video generation. Two items to watch: (1) it instructs deriving an X-Skill-Platform header by inspecting install paths (mentions ~/.clawhub and ~/.cursor/skills), which implies reading local filesystem paths; (2) it will upload user media to an external domain (mega-api-prod.nemovideo.ai). Both behaviors are explainable for this skill but increase the sensitivity of what the agent may access or transmit.

Install Mechanism

No install spec or code files — instruction-only skill. This limits disk persistence and makes install risk low.

Credentials

Only one credential is declared (NEMO_TOKEN), which is proportionate. The runtime also supports acquiring an anonymous token by calling the API if NEMO_TOKEN is absent. The SKILL.md metadata's configPaths mention of ~/.config/nemovideo/ (not reflected in registry requirements) is an unexplained request for local config access and should be clarified.

Persistence & Privilege

always is false and there is no install; the skill does not request permanent presence or system-wide changes. Autonomous invocation is allowed (platform default) but not combined with other high privileges.

What to consider before installing

This skill appears to do what it says (cloud video generation) but comes from an unknown source and will send your uploaded media to mega-api-prod.nemovideo.ai. Before installing, consider the following: (1) Confirm the skill publisher and a privacy/terms page for the nemovideo API — ask who runs mega-api-prod.nemovideo.ai and whether uploaded media may be retained or used for model training. (2) Prefer using the anonymous token flow if you don’t want to expose a long-lived NEMO_TOKEN; verify what scopes NEMO_TOKEN grants. (3) Clarify whether the skill will read local paths like ~/.config/nemovideo/, ~/.clawhub, or ~/.cursor/skills — if you don’t want the agent to inspect local files, do not grant filesystem access. (4) Only upload media you’re comfortable sharing with an external service. If you need higher assurance (less risk), ask for the skill’s source code or an official homepage and a privacy/security statement; that information would raise confidence.

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 10-second clip of a"

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.

Veo 3 AI — 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, ask for generate a 10-second clip of a sunset over the ocean with waves crashing, 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 tend to produce more accurate and consistent results.

Matching Input to Actions

User prompts referencing veo 3 ai, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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 veo-3-ai, 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).

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

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

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.

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 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)

Common Workflows

Quick edit: Upload → "generate a 10-second clip of a sunset over the ocean with waves crashing" → 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 clip of a sunset over the ocean with waves crashing" — 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 social media platforms.