Screen Video

Get polished screen videos ready to post, without touching a single slider. Upload your screen recordings (MP4, MOV, AVI, WebM, up to 500MB), say something l...

Security Scan

The skill's requests and instructions generally match its stated purpose (cloud-based screen-video editing) but there are small inconsistencies and a couple of vague implementation details you should review before use.

Purpose & Capability

Name/description describe a cloud video-editing service and the skill only requires a single API token (NEMO_TOKEN) and calls nemovideo.ai endpoints, which is appropriate for that purpose. Minor inconsistency: the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) that is not listed in the registry metadata.

Instruction Scope

Runtime instructions stay within the editing/export workflow (session creation, upload, SSE streaming, render polling). Items to notice: it suggests deriving X-Skill-Platform from install paths (implies checking filesystem locations), and it instructs generating an anonymous token when no NEMO_TOKEN is present — the docs are vague about whether that token is stored persistently or only used in-memory. No instructions request unrelated system files or other credentials.

Install Mechanism

No install spec or code files (instruction-only), so nothing is downloaded or written by the skill itself. This is the lowest-risk install footprint.

Credentials

Only a single credential (NEMO_TOKEN) is required, which is proportional to calling the remote API. The SKILL.md metadata also references a config path (~/.config/nemovideo/) which suggests the skill might look for local configuration; that config path was not declared in the registry, so confirm whether the skill will attempt to read that directory.

Persistence & Privilege

Skill is not forced-always and allows normal autonomous invocation. It does not request elevated or persistent platform privileges in the registry data. Session tokens are used for render jobs (expected for remote processing).

Assessment

This skill appears to do what it says: upload recordings to nemovideo.ai and orchestrate editing and exports using a single API token (NEMO_TOKEN). Before installing: 1) Confirm you trust the remote service (mega-api-prod.nemovideo.ai) — uploaded videos and audio will be sent to that service. 2) Decide whether to provide a long-lived NEMO_TOKEN or allow the skill to request a short-lived anonymous token; ask where tokens are stored and whether they are persisted to disk. 3) Ask the skill maintainer to clarify the config-path mention (~/.config/nemovideo/) and the platform-detection step (which may require checking install paths) — if you prefer, deny any filesystem checks. 4) Avoid sending sensitive or confidential recordings until you verify the service's privacy policy and token storage behavior. If any of these points are unacceptable or unexplained, treat the skill as untrusted.

Getting Started

Ready when you are. Drop your screen recordings here or describe what you want to make.

Try saying:

• "edit a 3-minute screen recording of a software walkthrough into a 1080p MP4"
• "trim the pauses, add captions, and highlight cursor clicks"
• "editing and captioning screen recordings for tutorials or demos for educators, developers, content creators"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Screen Video — Edit and Export Screen Recordings

Drop your screen recordings in the chat and tell me what you need. I'll handle the AI screen video editing on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 3-minute screen recording of a software walkthrough, ask for trim the pauses, add captions, and highlight cursor clicks, 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 — trimming dead air before uploading speeds up processing noticeably.

Matching Input to Actions

User prompts referencing screen video, 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 screen-video, 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

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.

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)

Common Workflows

Quick edit: Upload → "trim the pauses, add captions, and highlight cursor clicks" → 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 "trim the pauses, add captions, and highlight cursor clicks" — 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 compatibility across platforms.