Video Explainer

Turn a 2-minute screen recording of a software walkthrough into 1080p narrated explainer video just by typing what you need. Whether it's turning raw recordi...

Security Scan

The skill mostly does what it says (cloud video processing) but has a few inconsistencies and a small privacy surface (automatic token acquisition and filesystem probing) that warrant caution before installing.

Purpose & Capability

Name and instructions align with a cloud-based video processing service and the single required credential (NEMO_TOKEN) is appropriate. However the SKILL.md frontmatter requests a config path (~/.config/nemovideo/) while the registry metadata above stated no required config paths — this mismatch is incoherent and could indicate the skill expects local config files not declared elsewhere.

Instruction Scope

Runtime instructions tell the agent to upload user-provided video files and to call external API endpoints (session creation, SSE, upload, render, credits, state). That is expected for the stated purpose. Concerns: (1) the skill instructs detecting install paths (~/.clawhub/, ~/.cursor/skills/) to set X-Skill-Platform header — that requires probing specific filesystem locations; (2) it will POST to an anonymous-token endpoint and treat the returned token as NEMO_TOKEN if none is present. Both behaviors expand what the agent will read/access beyond just in-chat file uploads and should be noted. The SKILL.md also instructs to not expose tokens, but the agent will still handle and transmit them to the external API.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is written to disk by an installer in the skill package itself.

Credentials

Only NEMO_TOKEN is declared as required (primaryEnv). That fits the cloud API workflow. The skill will also obtain an anonymous token from the remote API if NEMO_TOKEN is absent. No other unrelated secrets are requested. Still, a token grants the backend permission to process uploaded media, so the privacy/credential impact is real and should be considered.

Persistence & Privilege

always:false and no install hooks — good. But the skill instructs probing common install/config paths (~/.clawhub/, ~/.cursor/skills/, and a possible ~/.config/nemovideo/) to determine X-Skill-Platform and possibly read local config. Probing these paths is more intrusive than strictly necessary for a single-use cloud upload and could leak information about local environment layout.

What to consider before installing

This skill appears to be a cloud-based explainer-video frontend and requires a NEMO_TOKEN (it can also obtain a short-lived anonymous token from https://mega-api-prod.nemovideo.ai). Before installing: (1) confirm you are comfortable uploading potentially sensitive video/audio to the external domain mega-api-prod.nemovideo.ai and review that service's privacy/terms; (2) avoid providing long-lived or unrelated credentials — NEMO_TOKEN is the only required credential; (3) ask the publisher why the frontmatter lists a local config path (~/.config/nemovideo/) and why the skill probes install/config directories — if you don't want filesystem probing, decline installation; (4) prefer ephemeral/anonymous tokens rather than putting a persistent NEMO_TOKEN in your environment; (5) if you need stronger assurance, request the service's homepage, privacy policy, and code or host provenance before using with sensitive footage.

Getting Started

Got raw footage or slides to work with? Send it over and tell me what you need — I'll take care of the AI explainer video creation.

Try saying:

• "turn a 2-minute screen recording of a software walkthrough into a 1080p MP4"
• "turn this recording into a clear explainer video with voiceover and chapter titles"
• "turning raw recordings or slides into structured explainer videos for educators, marketers, product teams"

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 Explainer — Turn Footage Into Explainer Videos

Drop your raw footage or slides in the chat and tell me what you need. I'll handle the AI explainer video creation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 2-minute screen recording of a software walkthrough, ask for turn this recording into a clear explainer video with voiceover and chapter titles, 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 — breaking your content into short logical sections helps the AI generate cleaner chapter markers.

Matching Input to Actions

User prompts referencing video explainer, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: video-explainer
• 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.

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.

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 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)

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

Common Workflows

Quick edit: Upload → "turn this recording into a clear explainer video with voiceover and chapter titles" → 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 "turn this recording into a clear explainer video with voiceover and chapter titles" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across YouTube, LinkedIn, and embedding.