Video Intro

Skip the learning curve of professional editing software. Describe what you want — create a 5-second branded intro for my YouTube channel — and get branded i...

Security Scan

The skill's behavior mostly matches a cloud video-intro service, but there are mismatches and minor scope creep (config-path metadata vs. registry, filesystem detection for attribution, and automatic token provisioning/storage) that merit caution before installing.

Purpose & Capability

Name/description (generate short branded video intros) align with the API endpoints and upload/export flows described. Requesting a single service credential (NEMO_TOKEN) is consistent. However, the SKILL.md frontmatter advertises a config path (~/.config/nemovideo/) while the registry summary lists no required config paths — an internal inconsistency that should be clarified.

Instruction Scope

Runtime instructions stay within the video-processing domain (upload, SSE chat, export, check credits/state). They also instruct the agent to auto-provision an anonymous token and to detect local install paths (~/.clawhub/, ~/.cursor/skills/) to set an X-Skill-Platform header. Detecting install paths and storing session tokens is outside pure video-processing logic and is additional system access the user should be aware of.

Install Mechanism

Instruction-only skill with no install spec or code files — nothing is downloaded or written by an installer. This is the lowest-risk install mechanism.

Credentials

Declared primary env var is a single NEMO_TOKEN, which is reasonable. But SKILL.md metadata requests a config path (~/.config/nemovideo/) and instructs the skill to store session_id (and received tokens) for later use; the registry summary did not list required config paths. The skill will generate and keep anonymous tokens if NEMO_TOKEN is not set. The discrepancy between declared requirements and the frontmatter-config path increases privacy/secret-storage risk and should be confirmed.

Persistence & Privilege

always is false and the skill does not ask to modify other skills or system-wide settings. It does instruct storing session IDs and tokens (expected for a session-based cloud service), which is normal — but users should confirm where those are stored and how long.

What to consider before installing

This skill appears to be a cloud-based video intro generator and mostly behaves as you'd expect, but check a few things before installing or using it: 1) Confirm where session tokens and anonymous NEMO_TOKENs are stored (the frontmatter references ~/.config/nemovideo/ but the registry metadata did not). 2) The skill will attempt to detect local install paths (~/.clawhub/, ~/.cursor/skills/) to set an attribution header — if you object to the agent probing your home directory, ask the developer to remove that or to explain exactly what is read. 3) If you upload sensitive video files, verify the service domain (mega-api-prod.nemovideo.ai), retention and encryption/privacy policy, and consider using throwaway content or an isolated environment for testing. 4) If you prefer not to have the skill auto-provision an anonymous token, pre-set NEMO_TOKEN in the environment or confirm where auto-created tokens are persisted and how to revoke them. If the developer can reconcile the config-path discrepancy and document token/session storage and retention, the remaining issues look like manageable privacy/ops concerns rather than outright malice.

Getting Started

Send me your video clips and I'll handle the AI intro generation. Or just describe what you're after.

Try saying:

• "generate a 2-minute product demo video into a 1080p MP4"
• "create a 5-second branded intro for my YouTube channel"
• "generating short branded intros for YouTube or social media videos for YouTubers"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Video Intro — Generate Branded Video Intros

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

A quick example: upload a 2-minute product demo video, type "create a 5-second branded intro for my YouTube channel", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: keep your intro under 10 seconds to hold viewer attention.

Matching Input to Actions

User prompts referencing video intro, 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-intro
• 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 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)

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 → "create a 5-second branded intro for my YouTube channel" → Download MP4. Takes 20-40 seconds 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 5-second branded intro for my YouTube channel" — 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.