- Home
- Skills
- Image & Video
- Rtsp Camera Grabber
Works with the AI Agents you already use
Rtsp Camera Grabber
Capture frames or short clips from RTSP/ONVIF security cameras with ffmpeg: probe streams, snapshot JPEGs, record clips, build timelapses and motion-triggered c
Free
Rtsp Camera Grabber
Example session with this skill installed
Grab a 15-second clip from my Hikvision camera at 192.168.1.50 and save it as a mobile-friendly MP4.
- Read your context and instructions
- Compiled the rtsp camera grabber
Running ffprobe to verify stream...
Executing: ffmpeg -rtsp_transport tcp -i "rtsp://user:pass@192.168.1.50:554/Streaming/Channels/101" -t 15 -c:v libx264 -preset veryfast -pix_fmt yuv420p clip.mp4
Output saved to clip.mp4 (H.264, 15s).
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Manually extracting usable media from IP cameras is tedious, often requiring proprietary NVR software or clunky web interfaces. Developers frequently struggle with stream timeouts, UDP packet loss, and vendor-specific RTSP pathing when trying to automate security footage tasks.
What it does
- Probes RTSP/ONVIF streams to identify codecs, resolutions, and sub-stream availability.
- Captures high-quality JPEG snapshots using TCP transport to prevent image artifacts.
- Records time-limited MP4 clips with H.264 encoding for universal playback.
- Generates timelapses by sampling frames at specific intervals and stitching them into video.
- Implements motion-triggered captures using ffmpeg scene-detection filters.
Frameworks & tools
ffmpeg, ffprobe, RTSP, ONVIF, libx264, bash.
Why this beats prompting it yourself
Generic LLM prompts often fail to include critical flags like -rtsp_transport tcp or -vsync vfr, leading to corrupted files or hung processes. This skill provides the specific filter chains and timeout settings required for production-ready camera automation.
Use cases
- Automate parking lot monitoring with scheduled snapshots.
- Capture and archive doorbell clips triggered by external IoT sensors.
- Build construction site progress timelapses from fixed IP cameras.
- Implement lightweight motion detection without heavy AI processing.
Known limitations
Does not support cameras behind NAT without port forwarding or VPNs. Not intended for 24/7 continuous recording or advanced audio analysis.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.
Requires ffmpeg installed. No support for cameras behind NAT without port forwarding. Not designed for 24/7 NVR replacement or audio-only streams.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
3 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected