Youtube Online Video Editor

Skip the learning curve of professional editing software. Describe what you want — trim the intro, add transitions, and export ready for YouTube upload — and...

Security Scan

The skill mostly behaves like a cloud video editor, but there are mismatches between declared requirements and the runtime instructions and it will upload your video files (and potentially generate anonymous auth tokens) to a third‑party backend — review before use.

Purpose & Capability

The skill's stated purpose (cloud AI video editing) matches the API calls and upload flows in SKILL.md. However the registry metadata and the SKILL.md disagree: the registry reported no required config paths while the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) and lists NEMO_TOKEN as required even though the instructions include an anonymous-token fallback. This is inconsistent but plausibly explained as preferring a user-supplied token while allowing anonymous use.

Instruction Scope

The instructions stay within the editor's domain (create session, upload files, run render, poll status). They explicitly send user video files to https://mega-api-prod.nemovideo.ai and instruct generating or extracting tokens from the auth endpoint. This is expected for a cloud editor, but it is privacy-sensitive: user media and session data are transmitted to a third party. The skill also uses local environment and install-path detection to populate headers (minor filesystem probing). There are no instructions to read arbitrary system files or unrelated credentials.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes on-disk risk because nothing is downloaded or executed locally by an installer.

Credentials

The skill declares NEMO_TOKEN as the primary required credential (and frontmatter lists a config path), but the runtime instructions will POST to an anonymous-token endpoint and use the returned token if NEMO_TOKEN is absent. The discrepancy between declared 'required' env/config and the actual anonymous fallback is inconsistent. Otherwise the skill does not request unrelated secrets — only the service token is involved.

Persistence & Privilege

The skill is not always-enabled and is user-invocable. It stores session tokens for its own operations (normal). It does not request elevated platform privileges or change other skills' configurations in the instructions.

What to consider before installing

This skill will upload any video files you give it to a third‑party cloud (mega-api-prod.nemovideo.ai) for processing and will create an anonymous token automatically if you don't provide NEMO_TOKEN. Things to consider before installing: only upload content you are comfortable sharing; prefer using a disposable or dedicated service token if you must provide one; the registry metadata and the skill's own frontmatter disagree about required config paths and tokens — treat that as a sign of sloppy metadata and verify the service independently (homepage/source unknown). If you want to test it, try with non-sensitive clips first and confirm the service's privacy/terms externally before sending private or copyrighted material.

Getting Started

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

Try saying:

• "edit my video clips"
• "export 1080p MP4"
• "trim the intro, add transitions, and"

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.

YouTube Online Video Editor — Edit and Export YouTube Videos

Send me your video clips and describe the result you want. The AI video editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 3-minute YouTube vlog recording, type "trim the intro, add transitions, and export ready for YouTube upload", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 5 minutes process significantly faster.

Matching Input to Actions

User prompts referencing youtube online video editor, 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 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is youtube-online-video-editor, 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).

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

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

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

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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim the intro, add transitions, and export ready for YouTube upload" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for widest YouTube compatibility.

Common Workflows

Quick edit: Upload → "trim the intro, add transitions, and export ready for YouTube upload" → 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.