Reading Level Simplifier Prompt

WHAT IT DOES

This script analyzes any webpage's text to estimate its reading level and provides a simplified version for easier comprehension. When you visit a page, the script extracts the main content and calculates the reading level using the Flesch-Kincaid grade level formula. A badge appears in the corner showing the estimated grade level (e.g., "Grade 8," "College Level," "Simple"). Click the badge to open a panel with a detailed breakdown: the exact grade level, word count, sentence count, a summary of the page content, and a simplified version where complex sentences are split and difficult words are replaced with simpler synonyms. This is especially helpful for students, people with reading difficulties, non-native speakers, or anyone who wants to quickly understand complex content.

WHERE IT RUNS

The script runs on all websites (*://*/*), making it truly universal. It works on any page with text—articles, blog posts, documentation, news, and more. It supports both desktop and mobile views.

HOW TO USE

After installation, the settings panel appears on the left side of the screen with the gear emoji (⚙️). Open the panel to configure the script:

- The "Show reading level badge" toggle enables or disables the badge.

- Toggle "Show summary in popup" to control whether the summary appears when you click the badge.

- Click "Analyze current page" to manually trigger an analysis.

- Click "Show summary" to open the summary panel without clicking the badge.

The badge appears automatically on pages with sufficient text. Click the badge to open the summary panel showing the reading level, summary, and simplified version.

TECHNICAL SECTION — REAL MECHANISM

The script extracts text from the page by scanning common content containers (article, main, .content, .article, .post, .entry, .text, .body, .prose, and p elements). It cleans the text by removing extra whitespace. The reading level is calculated using the Flesch-Kincaid Grade Level formula: 0.39 * (words / sentences) + 11.8 * (syllables / words) - 15.59. Syllables are counted using a vowel-based algorithm that handles common English patterns (silent 'e', 'le' endings, etc.). The summary is generated using a text summarization algorithm that scores sentences based on word frequency—sentences containing more frequent words are considered more important. The simplified version replaces complex words with simpler synonyms from a built-in dictionary (e.g., "utilize" → "use," "commence" → "start," "facilitate" → "help") and splits long sentences (over 15 words) at punctuation marks. The badge and panel are created using style properties and textContent (never innerHTML). A MutationObserver watches for DOM changes and re-analyzes the page when content changes.

THE PANEL

The settings panel is built with BotGentz's BGPanel component. It is draggable via its header, allowing you to reposition it anywhere on the screen. The panel snaps to the left edge by default but can be moved freely. Click the gear emoji to collapse the panel into a small bubble, and click the bubble to expand it again. The panel remembers its position per page session. Press the Escape key to quickly close or minimize the panel. The panel includes a status flash bar that provides visual feedback when settings are changed or actions are performed. All settings save automatically via GM_setValue.

PLEASE NOTE

This script requires the free BotGentz browser extension to run. It does not function as a standalone Chrome extension and does not use chrome.* APIs. The reading level calculation is an estimate and may not be perfectly accurate for all types of text. The simplification uses basic heuristics and a small synonym dictionary—it is not a full natural language processing system. The script works best on English text. The script stores only your preferences via GM_setValue. No data is sent externally—all analysis is performed locally in your browser. The script never reads or writes password fields, hidden inputs, or file inputs. All DOM operations use safe methods (style properties, textContent, appendChild) and never use innerHTML.