Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Record Browser Demo Videos

ASecurity

Create product demo videos by automating browser interactions and capturing frames. Use when the user wants to record a demo, walkthrough, product showcase, or interactive video of a web application. Supports Playwright CDP screencast for high-quality capture and FFmpeg for vide…

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsjavascriptgojavabashnode

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill record-browser-demo-videos --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Record Browser Demo Videos?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Record Browser Demo Videos
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-record-browser-demo-videos/badge)](https://www.skillsdirectory.com/skills/rondoflow-record-browser-demo-videos)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: record-browser-demo-videos
description: "Create product demo videos by automating browser interactions and capturing frames. Use when the user wants to record a demo, walkthrough, product showcase, or interactive video of a web application. Supports Playwright CDP screencast for high-quality capture and FFmpeg for vide…"
category: "Media"
author: community
version: "1.0.0"
icon: image
---

# Demo Video Creator

Create polished product demo videos by automating browser interactions.

## Overview

1. **Plan** the demo sequence (pages, interactions, timing)
2. **Record** frames using Playwright CDP screencast
3. **Encode** to video with FFmpeg

## Quick Start

### Prerequisites

- Clawdbot browser running (`browser action=start profile=clawd`)
- App accessible via browser (localhost or remote)
- FFmpeg installed for encoding

### Recording Workflow

1. Start the Clawdbot browser if not running
2. Navigate to the app manually or via `browser action=open`
3. Customize `scripts/record-demo.js` for the target app
4. Run: `node scripts/record-demo.js`
5. Encode: `bash scripts/frames-to-video.sh`

## Planning a Demo

See `references/demo-planning.md` for guidance on:
- Structuring demo sequences
- Timing and pacing
- Interaction patterns
- What makes demos compelling

## Scripts

### `scripts/record-demo.js`

Template Playwright script that:
- Connects to Clawdbot browser via CDP
- Starts screencast capture (JPEG frames)
- Executes demo sequence (navigation, clicks, hovers, typing)
- Saves frames to output directory

**Customize for each demo:**
- `DEMO_SEQUENCES` array - define pages and interactions
- `OUTPUT_DIR` - where to save frames
- `FRAME_SKIP` - skip every Nth frame (lower = more frames)

### `scripts/frames-to-video.sh`

FFmpeg encoding script with presets:
- `mp4` - H.264, good quality/size balance (default)
- `gif` - Animated GIF for embedding
- `webm` - VP9, smaller files

Usage: `./frames-to-video.sh [input_dir] [output_name] [format]`

## Interaction Patterns

```javascript
// Navigation
await page.goto('http://localhost/dashboard');
await page.waitForTimeout(2000);

// Click element
await page.locator('button:has-text("Create")').click();
await page.waitForTimeout(500);

// Hover (show tooltips, hover states)
await page.locator('.card').first().hover();
await page.waitForTimeout(1000);

// Type text
await page.locator('input[placeholder="Search"]').fill('query');
await page.waitForTimeout(500);

// Press key
await page.keyboard.press('Enter');
await page.keyboard.press('Escape');

// Scroll
await page.evaluate(() => window.scrollBy(0, 300));
```

## Tips

- **Timing**: 2s on page load, 0.5-1s between interactions, 1.5s to show results
- **Frame skip**: Use 3-5 for smooth video, 8-10 for smaller files
- **Quality**: 85-90 JPEG quality balances size and clarity
- **Resolution**: Browser window size determines output resolution
- **Loops**: GIFs should loop seamlessly - end where you started

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →