Video Generator Best

Skip the learning curve of professional editing software. Describe what you want — generate a 30-second promotional video from my product photos and descript...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud-based video rendering service: it only asks for a single service token, uploads user media to that service, and uses that service's API endpoints to create and return videos.

Purpose & Capability

The name/description describe a cloud video-generator and the skill's runtime steps (session creation, upload, render, export) all target a single third‑party API (mega-api-prod.nemovideo.ai). The required credential (NEMO_TOKEN) matches the service. Minor metadata inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata showed no required config paths.

Instruction Scope

SKILL.md confines actions to the nemovideo API (session, SSE chat, upload, state, export) and describes expected headers and formats. It does not instruct the agent to read unrelated system files or exfiltrate data to other endpoints. It does instruct detecting an install path to set an attribution header (X-Skill-Platform), which is a narrow, explainable action.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — lowest risk for arbitrary code installation or disk writes.

Credentials

Only one credential is declared (NEMO_TOKEN), which is appropriate. The instructions also describe an automatic anonymous-token acquisition flow when NEMO_TOKEN is absent (POST to /api/auth/anonymous-token and using data.token as NEMO_TOKEN). This is coherent but worth noting: the skill both accepts a user-provided token and can create a short‑lived anonymous token itself. Also note the frontmatter references a config path which suggests the token might be persisted there — the registry did not list this path, so persistence behavior is unclear.

Persistence & Privilege

The skill does not request always: true or other elevated privileges. It can be invoked autonomously (default), which is expected for skills, and there is no instruction to modify other skills or global agent configuration.

Assessment

This skill appears to do what it claims, but before installing consider: (1) All media you upload (images, video, audio) will be sent to a third‑party service (mega-api-prod.nemovideo.ai). Do not upload sensitive or confidential content unless you trust that service and have reviewed its privacy/storage policies. (2) The skill will use or obtain a NEMO_TOKEN: you can supply your own token or allow the skill to request an anonymous token (100 free credits, 7‑day expiry). Confirm whether tokens are persisted (SKILL.md references ~/.config/nemovideo/) and whether you are comfortable with that. (3) Check billing/credit implications (exports can fail with 402 if headers/credits are missing). (4) The skill source and homepage are unknown; if you need stronger assurance, verify the service domain and operator, review privacy/terms, or prefer a skill from a known publisher.

Getting Started

Share your text or images and I'll get started on AI video creation. Or just tell me what you're thinking.

Try saying:

• "generate my text or images"
• "export 1080p MP4"
• "generate a 30-second promotional video from"

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 Best — Generate and Export Finished Videos

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

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

Tip: shorter prompts with clear visual descriptions produce more accurate results.

Matching Input to Actions

User prompts referencing video generator best, 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 video-generator-best, 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.

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)

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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

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 my product photos and description" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across platforms and devices.

Common Workflows

Quick edit: Upload → "generate a 30-second promotional video from my product photos and description" → 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.