Comic Transcriber

An agent skill that converts comic book page images into structured, play-script-style markdown transcripts.

Use when

• User uploads a comic page image (JPG, PNG, or GIF) and wants it transcribed
• User asks for "comic transcript", "comic script", or "panel description"
• User wants dialogue and action extracted from a comic page
• User mentions "comic to text", "transcribe this comic", or "comic page to markdown"

What it does

The skill analyzes a comic page image and produces a markdown transcript that captures:

• Dialogue — speech bubbles, thought bubbles, narration boxes
• Action — character movements, staging, physical interactions
• Scene descriptions — settings, environments, visual context
• Sound effects — onomatopoeia as rendered in the art

Output follows a consistent play-script format with panel-by-panel breakdown, making comic content accessible and searchable.

Example output

## PAGE 4, PANEL 1

_A rain-soaked rooftop at night. The city skyline glows in the background._

_Nova crouches at the edge of the rooftop, peering down at the street below._

> _[DISPATCH - NARRATION]: All units — we have a Code Theta in the warehouse district._

**NOVA:** Copy that. I see movement on the third floor.

## PAGE 4, PANEL 2

_Close-up on Nova's face. Her eyes narrow._

**NOVA** _(whispering)_**:** Grim, are you in position?

**GRIM** _(off-panel)_**:** Always.

Installation

npx skills add rachelnabors/comic-transcriber

Or manually copy SKILL.md to your Claude Code skills directory.

Limitations

• Single-page transcription only (one image in, one markdown out)
• Does not handle PSD files or multi-page batch processing
• Designed for comics, not manga (uses Western left-to-right reading order)
• Non-comic images are not supported

License

MIT