/feature-video
Record a video walkthrough of a feature and add it to the PR description
From beads-compoundnpx claudepluginhub roberto-mello/lavra --plugin beads-compound[PR number or 'current'] [optional: base URL, default localhost:3000]<execution_context>
Arguments: $ARGUMENTS
Parse the input:
- First argument: PR number or "current" (defaults to current branch's PR)
- Second argument: Base URL (defaults to
http://localhost:3000)
# Get PR number for current branch if needed
gh pr view --json number -q '.number'
</execution_context>
<context>Prerequisites
- Local development server running (e.g.,
bin/dev,rails server) - agent-browser CLI installed
- Git repository with a PR to document
ffmpeginstalled (for video conversion)rcloneconfigured (optional, for cloud upload - see rclone skill)
Setup
Check installation:
command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED"
Install if needed:
npm install -g agent-browser && agent-browser install
See the agent-browser skill for detailed usage.
1. Gather Feature Context
Get PR details:
gh pr view [number] --json title,body,files,headRefName -q '.'
Get changed files:
gh pr view [number] --json files -q '.files[].path'
Map files to testable routes:
| File Pattern | Route(s) |
|---|---|
app/views/users/* | /users, /users/:id, /users/new |
app/controllers/settings_controller.rb | /settings |
app/javascript/controllers/*_controller.js | Pages using that Stimulus controller |
app/components/*_component.rb | Pages rendering that component |
2. Plan the Video Flow
Before recording, create a shot list:
- Opening shot: Homepage or starting point (2-3 seconds)
- Navigation: How user gets to the feature
- Feature demonstration: Core functionality (main focus)
- Edge cases: Error states, validation, etc. (if applicable)
- Success state: Completed action/result
Ask user to confirm or adjust the flow:
**Proposed Video Flow**
Based on PR #[number]: [title]
1. Start at: /[starting-route]
2. Navigate to: /[feature-route]
3. Demonstrate:
- [Action 1]
- [Action 2]
- [Action 3]
4. Show result: [success state]
Estimated duration: ~[X] seconds
Does this look right?
1. Yes, start recording
2. Modify the flow (describe changes)
3. Add specific interactions to demonstrate
3. Setup Video Recording
Create videos directory:
mkdir -p tmp/videos
Recording approach: Use browser screenshots as frames
agent-browser captures screenshots at key moments, then combine into video using ffmpeg:
ffmpeg -framerate 2 -pattern_type glob -i 'tmp/screenshots/*.png' -vf "scale=1280:-1" tmp/videos/feature-demo.gif
4. Record the Walkthrough
Execute the planned flow, capturing each step:
Step 1: Navigate to starting point
agent-browser open "[base-url]/[start-route]"
agent-browser wait 2000
agent-browser screenshot tmp/screenshots/01-start.png
Step 2: Perform navigation/interactions
agent-browser snapshot -i # Get refs
agent-browser click @e1 # Click navigation element
agent-browser wait 1000
agent-browser screenshot tmp/screenshots/02-navigate.png
Step 3: Demonstrate feature
agent-browser snapshot -i # Get refs for feature elements
agent-browser click @e2 # Click feature element
agent-browser wait 1000
agent-browser screenshot tmp/screenshots/03-feature.png
Step 4: Capture result
agent-browser wait 2000
agent-browser screenshot tmp/screenshots/04-result.png
Create video/GIF from screenshots:
# Create directories
mkdir -p tmp/videos tmp/screenshots
# Create MP4 video (RECOMMENDED - better quality, smaller size)
# -framerate 0.5 = 2 seconds per frame (slower playback)
# -framerate 1 = 1 second per frame
ffmpeg -y -framerate 0.5 -pattern_type glob -i 'tmp/screenshots/*.png' \
-c:v libx264 -pix_fmt yuv420p -vf "scale=1280:-2" \
tmp/videos/feature-demo.mp4
# Create low-quality GIF for preview (small file, for GitHub embed)
ffmpeg -y -framerate 0.5 -pattern_type glob -i 'tmp/screenshots/*.png' \
-vf "scale=640:-1:flags=lanczos,split[s0][s1];[s0]palettegen=max_colors=128[p];[s1][p]paletteuse" \
-loop 0 tmp/videos/feature-demo-preview.gif
Note:
- The
-2in MP4 scale ensures height is divisible by 2 (required for H.264) - Preview GIF uses 640px width and 128 colors to keep file size small (~100-200KB)
5. Upload the Video
Upload with rclone:
# Check rclone is configured
rclone listremotes
# Upload video, preview GIF, and screenshots to cloud storage
# Use --s3-no-check-bucket to avoid permission errors
rclone copy tmp/videos/ r2:your-bucket/pr-videos/pr-[number]/ --s3-no-check-bucket --progress
rclone copy tmp/screenshots/ r2:your-bucket/pr-videos/pr-[number]/screenshots/ --s3-no-check-bucket --progress
# List uploaded files
rclone ls r2:your-bucket/pr-videos/pr-[number]/
6. Update PR Description
Get current PR body:
gh pr view [number] --json body -q '.body'
Add video section to PR description:
If the PR already has a video section, replace it. Otherwise, append:
IMPORTANT: GitHub cannot embed external MP4s directly. Use a clickable GIF that links to the video:
## Demo
[]([video-mp4-url])
*Click to view full video*
Update the PR:
gh pr edit [number] --body "[updated body with video section]"
Or add as a comment if preferred:
gh pr comment [number] --body "## Feature Demo

_Automated walkthrough of the changes in this PR_"
7. Cleanup
# Optional: Clean up screenshots
rm -rf tmp/screenshots
# Keep videos for reference
echo "Video retained at: tmp/videos/feature-demo.gif"
</process>
<success_criteria>
- Video/GIF captures the complete user flow for the feature
- PR description updated with embedded video section
- Video uploaded to cloud storage (or local path noted)
- All shots from the planned flow are captured </success_criteria>