Introduction¶
Daily PDF work often involves switching between many scattered tools: one library for text extraction, another script for table export, and separate commands for watermarks, merging, splitting, Word conversion, and compression. Data must be shuttled between local tools and online conversion sites, which is unfriendly to intranets or sensitive files. Below is a Skill that consolidates 23 PDF operations into a single script. It covers the entire workflow of reading, extraction, generation, and editing, runs purely locally with no data leaving the machine, and is released under the MIT license.
What Is This¶
PDF Toolbox 23-in-1 is an Agent Skill for batch PDF reading and writing tasks, located at @user_2fb0af44/pdf-toolkit-pro, published by user_2fb0af44, version 1.5.2, sourced from the community, and categorized under office-efficiency. It uses a single set of commands to handle both PDF reading/extraction and writing/editing, positioned as “install once to cover the entire workflow,” eliminating the need to switch between multiple independent tools.
Core Features¶
For reading and extraction: supports text export to txt / Markdown / json (with layout preservation and coordinate bbox), table export to csv / xlsx / json, embedded image export and full-page rendering to PNG / JPG, bookmark/table of contents export to md / txt / json, AcroForm form fields (including checkbox states, hierarchical names, XFA detection), annotations and hyperlinks, embedded attachments, structure inspection (page count, metadata, scanned document detection, blank page detection, duplicate header/footer detection), keyword and regex search (returning matched page numbers and context), encrypted PDF decryption and reading, and scanned document OCR fallback recognition.
For writing and editing: supports Markdown-to-PDF generation, merging, splitting (per page / every N pages / by range / by bookmark), rotation, text and image watermarks, encryption and permission settings, password removal, conversion to Word docx, size compression, image-to-PDF composition, metadata modification (including XMP), page rearrangement and blank page deletion, and form filling (JSON / CSV batch processing with individual output files, Chinese glyph embedding in appearance streams, with flattening capability).
Six writing commands support multi-file batch processing; inputs support files, directories, and globs, with automatic success/failure summarization.
Installation and Activation¶
Official address:
https://api.skillhub.cn/user_2fb0af44/pdf-toolkit-pro
SkillHub page:
https://www.skillhub.cn/skills/user_2fb0af44/pdf-toolkit-pro
Install according to the standard SKILL.md format. This Skill is tagged with requires_api_key=false, requiring no API key, and relies on purely local execution. Since the official page does not provide command-level installation examples or CLI parameters in the captured materials, specific installation commands and parameter calls for each tool should be based on the official address page; no speculation is made here.
Typical Usage¶
The following usage comes from the official introduction, describing the input methods and batch behaviors supported by commands, not specific command-line parameters.
For reading tasks, inputs can be single files, directories, or globs; the six writing commands support multi-file batch processing and automatically summarize success/failure after batch operations, making it suitable for unified text extraction, table-to-csv/xlsx conversion, image export, bookmark/TOC export, annotation/attachment reading, scanned document detection, encrypted PDF decryption and reading, or OCR fallback recognition on batches of PDFs.
For writing tasks, form filling supports JSON / CSV batch processing with individual output files, Chinese glyph embedding in appearance streams, and flattening; splitting supports four granularities: per page, every N pages, by range, and by bookmark; page adjustment supports rearrangement and blank page deletion; metadata modification includes XMP.
This Skill can be used when users need to extract PDF content, convert tables to Excel/CSV, export images, convert to Markdown, export bookmark/TOC, read annotations/attachments, detect scanned documents, process encrypted PDFs, perform OCR recognition, handle batch processing, locate keywords by page number, fill forms, remove passwords, delete blank pages, generate PDFs, merge/split/rotate/watermark, convert PDF to Word, compress, convert images to PDF, modify titles/authors, adjust pages, etc.
Use Cases and Notes¶
Suitable for developers and office automation scenarios requiring batch, multi-step PDF processing, especially those with requirements for data to remain on-device and who want to replace multiple tool switches with a single script.
Points to note: First, command-level parameters, environment dependencies, and installation steps are not provided in the captured materials, so confirmation is needed at the official address before implementation; second, OCR is a fallback recognition for scanned documents, and effectiveness depends on the original image quality; third, form filling involves Chinese glyph embedding and flattening, so it is recommended to verify appearance stream rendering on a single sample before batch output.
Conclusion¶
The value of PDF Toolbox 23-in-1 lies in consolidating 23 PDF reading and writing operations into a single local script, running purely locally, keeping data on-device, and being MIT licensed. Official address:
https://api.skillhub.cn/user_2fb0af44/pdf-toolkit-pro