Table of Contents

• Overview
• Required TodoWrite Items
• Manifest Format
• Manifest Schema
• Step-by-Step Process
• 1. Parse Manifest File
• 2. Validate Component Outputs
• 3. Execute FFmpeg Composition
• 4. Verify Combined Output
• FFmpeg Composition Commands
• Vertical Stacking
• Horizontal Stacking
• Sequential Concatenation
• Grid Layout (2x2)
• With Background Color
• Layout Options
• Layout Option Details
• Example Compositions
• Terminal + Browser Tutorial
• Side-by-Side Comparison
• Picture-in-Picture
• Exit Criteria

Media Composition Skill

Combine multiple media assets (GIFs, videos, images) into composite outputs for detailed tutorials and documentation.

Overview

This skill orchestrates the combination of separately generated media assets into unified outputs. It reads manifest files that define components and their composition rules, validates all inputs exist, and executes FFmpeg commands to produce the final composite media.

Required TodoWrite Items

- Parse composition manifest file
- Validate all component outputs exist
- Determine composition layout and parameters
- Execute FFmpeg composition command
- Verify combined output file created
- Report composition metrics (file size, dimensions)

Verification: Run the command with

--help

Manifest Format

Manifests define the components to combine and how to arrange them:

# Example manifest: tutorials/mcp.manifest.yaml
name: mcp
title: "MCP Server Integration"
components:
  - type: tape
    source: mcp.tape
    output: assets/gifs/mcp-terminal.gif
  - type: playwright
    source: browser/mcp-browser.spec.ts
    output: assets/gifs/mcp-browser.gif
    requires:
      - "skrills serve"
combine:
  output: assets/gifs/mcp-combined.gif
  layout: vertical
  options:
    padding: 10
    background: "#1a1a2e"

Verification: Run the command with

--help

Manifest Schema

name

title

components

components[].type

tape

playwright

static

components[].source

components[].output

components[].requires

combine.output

combine.layout

combine.options

Step-by-Step Process

1. Parse Manifest File

# Read and validate manifest structure
yq eval '.' manifest.yaml

# Extract component outputs
yq eval '.components[].output' manifest.yaml

Verification: Run the command with

--help

2. Validate Component Outputs

# Check all required files exist
for output in $(yq eval '.components[].output' manifest.yaml); do
  if [[ ! -f "$output" ]]; then
    echo "ERROR: Missing component: $output"
    exit 1
  fi
done

Verification: Run the command with

--help

3. Execute FFmpeg Composition

Based on the layout specified in the manifest, execute the appropriate FFmpeg command.

4. Verify Combined Output

# Verify output exists and has content
if [[ -f "$output" && -s "$output" ]]; then
  echo "Composition successful: $output"
  ls -lh "$output"
else
  echo "ERROR: Composition failed"
  exit 1
fi

Verification: Run the command with

--help

FFmpeg Composition Commands

Vertical Stacking

Stack GIFs/videos top to bottom:

ffmpeg -i top.gif -i bottom.gif \
  -filter_complex "[0:v][1:v]vstack=inputs=2" \
  -y output.gif

Verification: Run the command with

--help

With padding between:

ffmpeg -i top.gif -i bottom.gif \
  -filter_complex "[0:v]pad=iw:ih+10:0:0:color=black[top];[top][1:v]vstack=inputs=2" \
  -y output.gif

Verification: Run the command with

--help

Horizontal Stacking

Stack GIFs/videos side by side:

ffmpeg -i left.gif -i right.gif \
  -filter_complex "[0:v][1:v]hstack=inputs=2" \
  -y output.gif

Verification: Run the command with

--help

Sequential Concatenation

Play GIFs/videos one after another:

# Create concat list file
cat > concat_list.txt << EOF
file 'first.gif'
file 'second.gif'
file 'third.gif'
EOF

# Concatenate
ffmpeg -f concat -safe 0 -i concat_list.txt \
  -y output.gif

Verification: Run the command with

--help

Grid Layout (2x2)

ffmpeg -i tl.gif -i tr.gif -i bl.gif -i br.gif \
  -filter_complex "[0:v][1:v]hstack=inputs=2[top];[2:v][3:v]hstack=inputs=2[bottom];[top][bottom]vstack=inputs=2" \
  -y output.gif

Verification: Run the command with

--help

With Background Color

ffmpeg -i top.gif -i bottom.gif \
  -filter_complex "color=c=#1a1a2e:s=800x600[bg];[bg][0:v]overlay=0:0[tmp];[tmp][1:v]overlay=0:300" \
  -y output.gif

Verification: Run the command with

--help

Layout Options

vertical

padding

background

align

horizontal

padding

background

align

sequential

transition

duration

grid

rows

cols

padding

overlay

position

opacity

pip

corner

scale

margin

Layout Option Details

padding

background

align

transition

scale

corner

Example Compositions

Terminal + Browser Tutorial

name: plugin-demo
components:
  - type: tape
    source: demo.tape
    output: terminal.gif
  - type: playwright
    source: browser.spec.ts
    output: browser.gif
combine:
  output: demo-combined.gif
  layout: vertical
  options:
    padding: 5
    background: "#0d1117"

Verification: Run the command with

--help

Side-by-Side Comparison

name: before-after
components:
  - type: static
    source: before.gif
    output: before.gif
  - type: static
    source: after.gif
    output: after.gif
combine:
  output: comparison.gif
  layout: horizontal
  options:
    padding: 10

Verification: Run the command with

--help

Picture-in-Picture

name: pip-demo
components:
  - type: tape
    source: main.tape
    output: main.gif
  - type: playwright
    source: overlay.spec.ts
    output: overlay.gif
combine:
  output: pip-demo.gif
  layout: pip
  options:
    corner: br
    scale: 0.3
    margin: 20

Verification: Run the command with

--help

Exit Criteria

• Manifest file parsed successfully
• All component outputs validated as existing
• FFmpeg composition command executed without errors
• Combined output file exists and has non-zero size
• Output dimensions and duration logged
• Temporary files cleaned up

Troubleshooting

Common Issues

Command not found Ensure all dependencies are installed and in PATH

Permission errors Check file permissions and run with appropriate privileges

Unexpected behavior Enable verbose logging with

--verbose