screen-monitorDual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL).
Install via ClawdBot CLI:
clawdbot install emasoudy/screen-monitorThis skill provides two ways for the agent to see and interact with your screen.
Best for: Quick visual checks, restricted browsers, or non-technical environments.
screen_share_link: Generates a local WebRTC portal URL.screen_analyze: Captures the current frame from the portal and analyzes it with vision.Usage:
# Get the link
bash command:"{baseDir}/references/get-share-url.sh"
# Analyze
bash command:"{baseDir}/references/screen-analyze.sh"
Best for: Deep debugging, UI automation, and clicking/typing in tabs.
clawdbot browser extension install.clawdbot browser extension path.browser action:snapshot: Take a precise screenshot of the attached tab.browser action:click: Interact with elements (requires profile="chrome").web/screen-share.html: The sharing portal.references/backend-endpoint.js: Frame storage server.Generated Mar 1, 2026
Support agents use Fast Share to quickly view a user's screen for troubleshooting without requiring software installation. This is ideal for diagnosing display issues or guiding users through settings in restricted environments like corporate browsers.
Developers employ Full Control to automate browser interactions, take precise screenshots, and test web applications. This enables deep debugging of UI elements and validation of user flows in development or QA cycles.
Trainers use Fast Share to broadcast their screen to learners for visual demonstrations in real-time. This is effective for software tutorials or product walkthroughs in educational or sales environments.
Accessibility specialists leverage Full Control to analyze web pages for compliance, clicking through elements to test screen reader compatibility and visual contrast. This aids in ensuring websites meet standards like WCAG.
Moderators utilize Fast Share to monitor user screens for inappropriate content during live sessions or support calls. This helps enforce community guidelines in platforms like gaming or social media.
Offer the skill as a cloud-based service with tiered plans based on usage (e.g., number of screen captures or automation minutes). This model targets businesses needing regular screen analysis, such as support teams or developers, with recurring revenue from monthly fees.
Provide basic screen sharing for free to attract users, while charging for advanced features like Full Control automation, higher-resolution captures, or team collaboration tools. This encourages adoption and upsells to power users in industries like tech support.
Sell customized licenses to large organizations for integration into their internal workflows, such as IT helpdesks or QA departments. This includes dedicated support, security compliance, and bulk usage allowances, generating high-value contracts.
đŹ Integration Tip
Ensure the WebRTC backend port 18795 is open and accessible, and test the browser extension installation in a controlled environment before deployment.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
äœżçšć çœź image_generate.py èæŹçæćŸç, ć〿ž æ°ć ·äœç `prompt`ă
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.