Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Auto Kindle Reader

    1

    Turn a Kindle book you already own into local, page-marked text by screenshotting Kindle Cloud Reader and running OCR.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Auto Kindle Reader

    Auto Kindle Reader

    Example session with this skill installed

    Extract my book at https://read.amazon.com/?asin=B00XYZ123 and sync the text to my Obsidian vault.

    • Read your context and instructions
    • Compiled the auto kindle reader

    I have initiated the extraction process for the book with ASIN B00XYZ123. A Chrome window has been opened for you to complete the login. Once you have navigated to page 1, the script will automatically capture the screenshots and perform OCR.

    Extraction Task Summary

    AttributeValue
    ASINB00XYZ123
    Output Directory./The_Pragmatic_Programmer/
    Obsidian SyncEnabled ($OBSIDIAN_VAULT/Kindle/The_Pragmatic_Programmer/)
    Page Delay1.2s
    Max Pages800

    The capture process is currently running. I will monitor the folder for the final book.txt and metadata.json files.

    Next steps

    1. Sign in to your Amazon account in the opened Chrome window.
    2. Ensure the book is opened to Page 1 before the 90-second login timer expires.
    3. Keep the Chrome window visible and do not resize it while the capture is in progress.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Converting Kindle books to clean text for research or personal knowledge management is a manual, time-consuming chore. This skill automates the extraction of text from books you already own in the Kindle Cloud Reader, outputting structured Markdown and OCR text directly to your local machine.

    What it does

    • Automated Capture drives a Chrome session to navigate and screenshot every page of a Kindle book.
    • Tesseract OCR processes the resulting screenshots into a unified book.txt file with page markers.
    • Metadata Generation saves the ASIN, title, and page count into a metadata.json for easy cataloging.
    • Obsidian Sync optionally formats and moves the extracted text and metadata into an Obsidian vault.
    • State Management uses a local Chrome profile to maintain your Amazon login across multiple extraction sessions.

    How it works

    1. Run the extract.sh script passing the book's ASIN or Kindle Cloud Reader URL.
    2. Sign in to your Amazon account and navigate to the first page during the login wait period.
    3. Monitor the automated page-turning and screenshot process in the visible Chrome window.
    4. Verify the generated text, metadata, and screenshot files in the local book folder.

    Frameworks & tools

    The skill requires Python 3.11+, Google Chrome, and Tesseract OCR. It utilizes a shell wrapper to manage a Python virtual environment and execution flags.

    Why this beats prompting it yourself

    Manual copy-pasting from Kindle Cloud Reader is blocked by the platform. This skill bypasses the UI restrictions by using visual capture and OCR, handling the hundreds of page turns and file merges that a standard LLM prompt cannot perform.

    Use cases

    • Convert purchased technical books into searchable Markdown for Obsidian or Logseq.
    • Extract text from books for personal RAG pipelines or local LLM analysis.
    • Archive visual copies of textbooks alongside their OCR text equivalents.
    • Migrate highlights and full-page context into personal knowledge bases.

    Known limitations

    This does not download Kindle files or bypass DRM. It requires a visible Chrome window and Tesseract installed on the system path. OCR quality may drop for two-column layouts or very small font sizes.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.

    Requires Chrome and Tesseract OCR installed on PATH. Does not bypass DRM or download KF8/KFX files. Best tested on macOS. Two-column layouts may impact OCR accuracy.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 15 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Browser
    Network Access
    Read Files
    Write Files
    Listed15 days ago

    What's inside

    Frequently Asked Questions

    No, this skill does not bypass DRM or download files. It captures page images from your browser and uses Tesseract OCR to convert the visual text into a searchable Markdown format for your personal use.

    You will need Python 3.11+, Google Chrome, and Tesseract OCR installed on your local machine. The skill includes a shell wrapper that automatically manages the Python virtual environment and execution flags for you.

    While it captures the full text of the book, it is specifically optimized for Obsidian and Logseq by generating structured Markdown and metadata.json files that integrate directly with personal knowledge management workflows.

    The skill uses a persistent local Chrome profile, meaning you only need to sign in to Amazon once; your session state is maintained for all future extractions until you manually log out.

    You receive the complete automation scripts (extract.sh and Python logic), setup documentation, and the configuration files necessary to sync extracted data with your local Obsidian vault.

    Extraction speed depends on the page count, as the skill mimics natural page-turning to ensure every page is captured. For a standard 300-page book, the automated process typically completes in 10-15 minutes without any manual intervention.

    New in Workflow Automation