Video Generator Ab2n

Skip the learning curve of professional editing software. Describe what you want — generate a 30-second promotional video from these images and this script —...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud video-generation service, but it contacts an external API and will create/use tokens so verify the service and data you send before installing.

Purpose & Capability

Name/description (AI video generation from images/text) aligns with the declared env var (NEMO_TOKEN), the listed config path (~/.config/nemovideo/) and the network endpoints in SKILL.md. No unrelated credentials or binaries are requested.

Instruction Scope

The SKILL.md instructs the agent to call nemovideo.ai endpoints for session creation, SSE chat, upload and export — expected for a cloud render service. It also tells the agent to generate an anonymous token if NEMO_TOKEN is missing and to include attribution headers derived from frontmatter and the agent's install path. These network calls and header builds are within scope, but they do mean user files and prompts will be uploaded to an external service and the skill may create/retain short-lived tokens.

Install Mechanism

No install spec or code is included (instruction-only), so nothing is written to disk by an installer. This is the lowest-risk install model.

Credentials

Only one credential (NEMO_TOKEN) is required, which is appropriate for a third-party API. Metadata also lists a config path (~/.config/nemovideo/) that implies reading/writing config or tokens locally — reasonable for this service but worth noting because it grants the skill access to a per-user config location.

Persistence & Privilege

The skill is not always-on and is user-invocable. It can be invoked autonomously (platform default), but there is no unusual persistent privilege requested. The SKILL.md's requirement to keep session_id and potentially write tokens to the config path is expected for a session-based cloud service.

Assessment

This skill will upload files and text to mega-api-prod.nemovideo.ai and either use a NEMO_TOKEN you supply or fetch an anonymous token for you. Before installing: (1) Verify the external domain and the vendor (there's no homepage listed here). (2) Only provide a NEMO_TOKEN if it comes from a trusted source; otherwise rely on the anonymous-token flow but understand that creates a short-lived token and transmits your data. (3) Avoid sending sensitive PII or confidential assets — uploads can be stored/processed on the provider's systems. (4) After use, check ~/.config/nemovideo/ (if created) for any stored tokens you may want to remove. (5) If you need stronger assurance, ask the publisher for a homepage, privacy/terms, and a documented API spec before proceeding.

Getting Started

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

Try saying:

• "generate a product description and three brand images into a 1080p MP4"
• "generate a 30-second promotional video from these images and this script"
• "generating videos from images and text prompts for marketers"

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.

Video Generator AB2N — Generate Videos from Images and Text

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

Say you have a product description and three brand images and want to generate a 30-second promotional video from these images and this script — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter scripts with clear scene descriptions produce more accurate results.

Matching Input to Actions

User prompts referencing video generator ab2n, 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: video-generator-ab2n
• 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

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 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

Common Workflows

Quick edit: Upload → "generate a 30-second promotional video from these images and this script" → 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 30-second promotional video from these images and this script" — concrete instructions get better results.

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

Export as MP4 for widest compatibility.