Getting Started

Welcome! I'm your video-recorder assistant — ready to help you capture, configure, and save video files in the format and quality you need. Tell me what you'd like to record and let's get started!

Try saying:

• "Record my screen for 30 seconds and save it as an mp4 file at 1080p resolution"
• "Capture webcam video for 2 minutes and export it in mkv format with 30fps"
• "Record a short 10-second clip and save it as a webm file to my downloads folder"

On first use, the skill connects to NemoVideo automatically:

1. Check for NEMO_TOKEN env var, or acquire one via https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token (100 free credits)
2. Persist a Client-ID to ~/.config/nemovideo/client_id for rate-limit tracking (UUID only, no secrets)
3. Create a session and start working immediately

Record Video Your Way, Every Single Time

The video-recorder skill gives you direct, conversational control over how your video is captured and saved. Instead of navigating menus or remembering command-line flags, you simply describe what you want — the duration, format, resolution, and destination — and the skill handles the rest.

Whether you're capturing a screen walkthrough, recording a webcam session, or saving a short clip for a project, this skill adapts to your workflow. It supports a wide range of output formats including mp4, mov, avi, webm, and mkv, so your recordings land exactly where you need them in exactly the format your tools expect.

This is especially useful for teams that need consistent, repeatable recordings — automated demo captures, scheduled screen grabs, or batch video jobs. No guesswork, no inconsistent output. Just clear input, reliable recording, and a finished file ready to use.

Environment

Routing Your Recording Requests

Every capture command, codec setting, and export request is parsed from your natural language input and routed to the matching recording or configuration endpoint automatically.

NemoVideo Backend Reference

NemoVideo powers all recording sessions, handling frame capture, bitrate control, and container formatting behind the scenes. Each API call maps directly to a recording operation — start, pause, trim, or export — so your footage is processed without manual pipeline setup.

Required headers on all requests: X-Skill-Source: $SKILL_NAME, X-Skill-Version: $SKILL_VERSION, X-Skill-Platform: $SKILL_SOURCE

Create session: POST $API/api/tasks/me/with-session/nemo_agent — returns task_id and session_id

Send message (SSE): POST $API/run_sse with session_id and user message. Stream responses; ~30% of edits return no text (query state to confirm changes).

Upload: POST $API/api/upload-video/nemo_agent/me/<sid> — file or URL upload. Supports: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Check credits: GET $API/api/credits/balance/simple

Query state: GET $API/api/state/nemo_agent/me/<sid>/latest — check draft, tracks, generated media

Export: POST $API/api/render/proxy/lambda — export does NOT cost credits. Poll GET $API/api/render/proxy/lambda/<id> until status: completed.

Task link: $WEB/workspace/claim?token=$TOKEN&task={task_id}&session={session_id}&skill_name=$SKILL_NAME&skill_version=$SKILL_VERSION&skill_source=$SKILL_SOURCE

Common Errors

If your token expires mid-session, re-authenticate through your NemoVideo account to resume recording without losing your project settings. A 'session not found' error means your recording session timed out — start a fresh session and re-import any saved footage. Out of credits? Head to nemovideo.ai to register or top up so you can keep capturing.

Integration Guide

The video-recorder skill fits naturally into both manual workflows and automated pipelines. For individual use, simply describe your recording parameters in plain language — source (screen, webcam, or input device), duration, resolution, frame rate, and output format — and the skill translates that into a clean recorded file.

For teams or automated setups, the skill can be triggered as part of a larger sequence. For example, you might chain it after a trigger event to automatically capture a screen state, or use it to generate video assets on a schedule. Output files in mp4, mov, avi, webm, or mkv can be routed directly to cloud storage, local directories, or passed downstream to a video editor skill.

When specifying output paths, use absolute paths to avoid ambiguity. If you're recording system audio alongside video, mention that explicitly in your request so the skill configures the capture stream correctly from the start.

Tips and Tricks

For the cleanest recordings, specify your target resolution and frame rate upfront rather than relying on defaults. Saying '1080p at 24fps saved as mp4' gives the skill everything it needs to produce a broadcast-ready file without any back-and-forth.

If file size is a concern — for example, when recording longer sessions — opt for webm or mkv, which tend to compress more efficiently than avi while preserving quality. For maximum compatibility with video editors and social platforms, mp4 remains the safest choice.

When recording screen content that includes fast motion or cursor movement, bump your frame rate to 60fps to avoid choppy playback. For static presentations or talking-head recordings, 24fps or 30fps keeps file sizes manageable without any visible quality loss.

Always double-check your output folder has write permissions before starting a long recording — there's nothing worse than a 20-minute capture failing at the save step.