Ai Youtube Video Maker

Turn three product images and a voiceover MP3 into 1080p ready-to-upload videos just by typing what you need. Whether it's generating polished YouTube videos...

Security Scan

The skill is mostly consistent with a cloud video-rendering tool (it uploads your media to nemovideo.ai and uses a NEMO_TOKEN), but provenance is unclear and there are metadata/instruction inconsistencies and privacy implications you should review before installing.

Purpose & Capability

Name and description match the instructions: the skill uploads media to a cloud backend (mega-api-prod.nemovideo.ai) and manages a session/token to render videos. Requesting a NEMO_TOKEN as the primary credential is coherent for a cloud service. However, the package has no listed homepage/source and the registry metadata in the listing omitted config paths while the SKILL.md frontmatter includes a config path (~/.config/nemovideo/), creating a provenance/information mismatch worth questioning.

Instruction Scope

Runtime instructions stay within the stated purpose: check/use NEMO_TOKEN, optionally obtain an anonymous token, create a session, upload files, stream SSE events, and start renders. It will upload user-supplied media to the remote service (expected for cloud rendering). The SKILL.md also instructs deriving an X-Skill-Platform header from an install path and references a config path in its frontmatter — it's not explicit whether the agent will read local config files or probe install paths, which should be clarified.

Install Mechanism

Instruction-only skill (no install spec, no code files). No download/extract or third-party packages are declared, so there is no installation-time code execution risk listed.

Credentials

Only NEMO_TOKEN is declared as required, which fits a cloud API. But SKILL.md also includes a configPaths entry (~/.config/nemovideo/) in its metadata (contradicting the registry's 'no config paths' listing), implying possible local config access. The skill will also generate an anonymous token if NEMO_TOKEN is absent — this is functional but means the agent will call the remote auth endpoint and store/use that token. You should confirm whether local config files will be read/written and be aware that providing a NEMO_TOKEN (or allowing the skill to obtain one) grants the remote service full access to uploaded media and render operations.

Persistence & Privilege

The skill is not marked always:true and does not request system-wide changes or modifications to other skills. It uses an API session model and appears to keep session_id scoped to its operations; autonomous invocation is allowed (platform default) but not by itself a red flag here.

What to consider before installing

This skill uploads whatever media you provide to a remote service (mega-api-prod.nemovideo.ai) and uses a NEMO_TOKEN for authentication. Before installing: 1) Confirm you trust nemovideo.ai and are comfortable with your media being uploaded to their servers (privacy, copyright, and retention implications). 2) Ask the publisher for source code or a homepage—there is no homepage/source listed and that reduces provenance. 3) Clarify the config path discrepancy: SKILL.md frontmatter lists ~/.config/nemovideo/ but the registry showed no config paths—ask whether the skill will read or write local config files. 4) If you have an account, prefer supplying your own NEMO_TOKEN instead of relying on anonymous token creation if you want predictable billing/credits. 5) If you need stronger assurance, request the exact runtime behavior around token storage and any filesystem accesses (install-path detection, config reads).

Getting Started

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

Try saying:

• "create my video clips or images"
• "export 1080p MP4"
• "create a 60-second YouTube video with"

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.

AI YouTube Video Maker — Create and Export YouTube Videos

Drop your video clips or images 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 three product images and a voiceover MP3, ask for create a 60-second YouTube video with transitions, background music, and captions, 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 source clips under 2 minutes process significantly faster and give the AI more focused content to work with.

Matching Input to Actions

User prompts referencing ai youtube video maker, 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 ai-youtube-video-maker, 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

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)

Common Workflows

Quick edit: Upload → "create a 60-second YouTube video with transitions, background music, and captions" → 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 "create a 60-second YouTube video with transitions, background music, and captions" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for the best compatibility with YouTube's upload requirements.