textfocus

Align and center a target word across images using OCR.

28|4|Updated Jul 15, 2025
One-click install
npx skills add https://github.com/CodingWithLewis/TextFocus --skill textfocus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: textfocus
Source: https://github.com/CodingWithLewis/TextFocus/tree/main
Command: npx skills add https://github.com/CodingWithLewis/TextFocus --skill textfocus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Align and center a target word across multiple images using OCR to produce consistent, documentary-style word-focused frames.

Core Features & Use Cases

  • Center a word across frames: keep a keyword perfectly centered and uniformly scaled across many images.
  • Batch-processing for video frames: process large sets of screenshots or footage efficiently.
  • Flexible backgrounds and outputs: supports dominant color, white, black, or transparent backgrounds with consistent dimensions, suitable for After Effects / Premiere.

Quick Start

Run quick-cuts on your image set with -w "<target_word>" to center and normalize the target word across all frames.

Frequently Asked Questions about textfocus

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I center a specific word across multiple video frames using OCR?

To center a word across video frames using OCR, you run a batch-processing command that detects the target keyword in each image and re-aligns the crop so the word remains perfectly centered and uniformly scaled throughout the sequence.

Can I batch-crop and normalize images for a documentary-style sequence without manual editing?

Yes, you can batch-crop and normalize images for a documentary-style sequence without manual editing by using automated OCR detection, which locks the target word into the center and applies consistent dimensions across all frames.

What's the best way to keep a keyword locked in the center across screenshots for After Effects?

The best way to keep a keyword centered across screenshots for After Effects is to process the image set with OCR-based alignment, generating frames with configurable size, uniform word height, and transparent or solid backgrounds.

Do I need Tesseract OCR and Python 3.8+ to process images for word-centered outputs?

Yes, you need Tesseract OCR and Python 3.8+ installed in your environment, as the system validates these prerequisites to perform automated text detection and batch image alignment.

What background options are supported when aligning words across frames for Premiere?

When aligning words across frames for Premiere, the supported background options include dominant color, white, black, and transparent, ensuring consistent dimensions suitable for video editing workflows.

How does parallel processing work for batch-cropping large sets of video frames?

Parallel processing for batch-cropping video frames works by running the OCR alignment task concurrently across multiple images, allowing large sets of screenshots to be processed efficiently without manual intervention.