Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    PDF Add Bookmarks

    1

    Add reviewed, hierarchical bookmarks to Chinese and English text, scanned and mixed PDFs.

    Free

    1 useSecurity scanned

    About this skill

    Add clickable, hierarchical bookmarks to Chinese and English PDF textbooks, exam papers, slides and articles. Supports text-based, scanned and mixed PDFs. Review suggested headings before writing, or import a manually corrected table of contents. Original input files are preserved; output replaces existing bookmarks without adding an OCR text layer.

    Requirements: a local agent with terminal/file access, Python 3.10–3.13, and the pinned packages in requirements.txt. Scanned pages additionally require separately installed Tesseract OCR and language data (chi_sim+eng by default). Windows, macOS and Ubuntu installation instructions are included.

    Automatic recognition always requires review. Complex layouts and poor scans can produce omissions or incorrect text, hierarchy or page targets. Manual TOC import is supported. Signed PDFs are rejected; provide an unsigned original. OCR failure stops processing by default. This skill does not promise fully automatic or error-free recognition.

    Project source is MIT-licensed; retain LICENSE. Dependencies have their own licenses, including PyMuPDF under AGPL or a commercial license. No third-party binaries, OCR language models or source PDF samples are bundled.

    Source and documentation: https://github.com/StarryCode-Lang/pdf-add-bookmarks Version: 0.4.3

    All automatically detected titles, hierarchy and page targets require human review. Complex layouts and low-quality scans can cause omissions or recognition errors. Signed PDFs are rejected. Scans require separately installed Tesseract and language packs; no searchable OCR text layer is added. Input/output use absolute paths. Local execution of the three supporting scripts is required; execution through Agensi delivery has not been verified.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Requires

    Python 3.10–3.13
    PyMuPDF 1.26.6
    pytesseract 0.3.13
    Pillow 12.3.0
    packaging 26.3
    Node.js
    Python
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Network Access

    Reads the selected PDF and optional TOC file; writes a bookmarked output PDF and suggested TOC, with overwrite protection. Executes local Python and Tesseract. OCR workers set OMP_THREAD_LIMIT=1; no credentials are collected. Network is needed for dependency/source installation, not PDF processing. Reviewer: this MIT-licensed package contains three local Python scripts. Please confirm supporting-file execution through agent delivery or the permitted public GitHub installation route before approval; platform execution has not been tested.

    Listed25 days ago

    What's inside

    Frequently Asked Questions

    This skill builds hierarchical PDF outlines using text/layout heuristics and optional Tesseract OCR. Automatic recognition requires review; complex layouts and poor scans can produce errors. A manually reviewed TOC can be imported. It does not guarantee better results than every PDF editor.

    The skill is built for Python 3.10–3.13 environments and requires Tesseract OCR to be installed on your system if you plan to process scanned images or non-selectable text.

    Yes, the tool generates a draft 'suggested_toc.txt' file, allowing you to manually adjust headings or indentation levels before the final bookmarks are permanently written to the PDF.

    The documented recognition workflow targets Chinese and English. Other Tesseract language data can be selected, but heading recognition quality for other languages has not been validated.

    Digitally signed PDFs are rejected. Unreadable, malformed or protected files may fail. OCR errors stop processing by default. Use an unsigned, readable original; the skill does not bypass document protection.

    The free v0.4.3 ZIP contains SKILL.md, requirements.txt, LICENSE and three Python scripts. Dependencies, Tesseract, language models and source PDF samples are installed or supplied separately. No batch-processing command is promised.

    New in Productivity

    Free