Generator Youtube

Skip the learning curve of professional editing software. Describe what you want — generate a YouTube-ready video with intro, cuts, and outro from my raw foo...

Security Scan

The skill's stated purpose (cloud video generation) matches most of its instructions, but there are inconsistencies and file-system detection behaviors that aren't justified by the description and could access unexpected local config or skill-installation paths.

Purpose & Capability

The skill is described as a cloud-based YouTube video generator and it requests a single service credential (NEMO_TOKEN), which is proportionate. However the SKILL.md frontmatter declares a configPaths entry (~/.config/nemovideo/) that is not reflected in the registry metadata (which lists no required config paths). This mismatch is unexplained and worth clarifying.

Instruction Scope

Runtime instructions correctly describe API flows (obtain token, create session, upload files, poll render status). But the instructions also tell the agent to derive request headers from the SKILL.md frontmatter and to detect the 'install path' (checking ~/.clawhub/, ~/.cursor/skills/, etc.) to populate X-Skill-Platform. Detecting install paths and reading local config directories requires filesystem access outside the declared requirements and is not necessary for basic upload/render flows — this is scope creep and a privacy/visibility risk.

Install Mechanism

There is no install spec and no code files; this is instruction-only, so nothing is written to disk by an installer. That's the lowest install-risk model.

Credentials

Declared required environment variable is just NEMO_TOKEN (reasonable for a service integration). But the SKILL.md also references reading a local config path (~/.config/nemovideo/) and probing install directories to derive headers; those accesses were not declared in the registry metadata and broaden the skill's scope to local files. That increases the amount of local data the skill may touch without justification.

Persistence & Privilege

The skill is not marked always:true and has no install hooks. It can be invoked autonomously per platform defaults, which is normal. It does not request permanent presence or modifications to other skills/configs.

What to consider before installing

This skill largely behaves like a cloud video-renderer and only needs a NEMO_TOKEN to work, which is reasonable. Before installing or enabling it: (1) Ask the author why the SKILL.md declares a local config path (~/.config/nemovideo/) and why the skill needs to detect install directories — those require filesystem reads and aren't necessary for uploading files to the service. (2) Only provide NEMO_TOKEN if you trust the nenovideo service; prefer a scoped or anonymous token if available. (3) If you are uncomfortable with filesystem probing, decline or request a version that omits detection of ~/.clawhub/ or ~/.cursor/ and does not read other local config directories. (4) Consider running first in a sandboxed agent or with network monitoring to confirm it only talks to the documented API host (mega-api-prod.nemovideo.ai) and does not access unexpected endpoints. Clarification from the developer about the configPath/install-path checks would likely move this to 'benign'; absent that, treat it cautiously.

Getting Started

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

Try saying:

• "generate my video clips"
• "export 1080p MP4"
• "generate a YouTube-ready video with intro,"

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.

Generator YouTube — Generate Upload-Ready YouTube Videos

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

Say you have a 10-minute raw screen recording and want to generate a YouTube-ready video with intro, cuts, and outro from my raw footage — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: trimming your clip to the key moments before uploading speeds up generation significantly.

Matching Input to Actions

User prompts referencing generator youtube, 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.

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is generator-youtube, 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

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

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 "generate a YouTube-ready video with intro, cuts, and outro from my raw footage" — concrete instructions get better results.

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

Export as MP4 for widest compatibility with YouTube's upload requirements.

Common Workflows

Quick edit: Upload → "generate a YouTube-ready video with intro, cuts, and outro from my raw footage" → 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.