- Home
- Skills
- Workflow Automation
- QuickPeek Demo Videos
QuickPeek Demo Videos
Automated narrated product demo videos generated directly from a live web URL.
Free
Works with the AI Agents you already use
QuickPeek Demo Videos
Example session with this skill installed
Create a narrated demo video for https://example-app.com/dashboard showing the analytics tab using the 'alloy' voice. Use a custom script for the outro to avoid pricing claims.
- Read your context and instructions
- Compiled the quickpeek demo videos
I have initiated the browser automation for example-app.com. The agent is currently navigating the analytics dashboard, capturing the interaction, and generating narration using the 'alloy' voice. I have also bypassed the default pricing outro as requested to ensure no inaccurate claims are made.
Demo Video Generation Details
| Property | Value |
|---|---|
| Status | Rendering In Progress |
| Target URL | https://example-app.com/dashboard |
| Voice Selection | alloy (Neutral/Professional) |
| Workflow | Browser Crawler -> Analytics Tab -> Scripted Outro |
| Captions | Enabled (Burned-in) |
| Session State | Authenticated (Active) |
| Output Format | MP4 (1080p) |
Script Summary
- Navigation: Browser loads dashboard and clicks
[data-testid="analytics-nav"]. - Narration: "Here you can see your real-time performance metrics and user growth."
- Action: Hover over the primary growth chart to trigger tooltip data.
- Outro: "Explore the dashboard today to gain deeper insights into your data."
Next steps
- Download the generated
.mp4file once the render completes in the localoutputsdirectory. - Use
get_demo_configif you need to replicate this specific visual style for future videos. - Run
check_accountif you plan to generate more than three videos in this session to monitor usage limits.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual screen recording is tedious and often looks unprofessional due to varying resolutions and messy desktops. This skill automates the production of narrated product walkthroughs by driving a headless browser through a live URL to capture clean, high-quality video.
What it does
- Automated browser driving navigates through live web applications to capture clean interaction flows.
- Narrated voiceover generates spoken audio based on page content or provided scripts.
- Burned-in captions overlays text synchronized with the narration for accessibility and silent viewing.
- Scripted execution follows specific routes through an app for targeted feature demonstrations.
- Session management handles authentication states to record behind-the-login workflows.
How it works
- Use
check_accountto verify MCP server connectivity and plan limits. - Run
list_voicesto select a narration style suitable for the brand. - Execute
generate_demowith a target URL to let the crawler build a walkthrough automatically. - Alternatively, use
generate_demo_from_scriptto provide a precise list of steps for the browser to follow.
Frameworks & tools
This skill runs as a local MCP server using Node.js and npx. It utilizes headless browser automation for capture and SSML-compatible speech synthesis for narration.
Why this beats prompting it yourself
Standard LLMs cannot interact with live DOM elements or synchronize audio-visual assets into a rendered video file. This skill bridges the gap between text instructions and a final MP4 deliverable by managing the browser automation and rendering pipeline.
Use cases
- Generate landing page hero videos without manual screen capture.
- Create narrated onboarding walkthroughs for new feature releases.
- Produce clean product demos for sales decks and documentation.
- Batch record screenshots and clips of complex multi-step user flows.
Known limitations
The character & in captions breaks speech synthesis and must be replaced with "and". Saved browser sessions can go stale, requiring re-authentication to avoid capturing empty skeleton screens.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.
The symbol & must be replaced with 'and' to prevent silent audio. Stale browser sessions may capture empty screens, requiring fresh authentication for gated content.
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
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 22 days ago
- Free with an Agensi account