CMS, document processing, and media generation.
SwiftUI Text rendering, AttributedString, native Markdown support, and rich text editing. Use when user asks about Text, Markdown, AttributedString, rich text, TextEditor, text formatting, or localization.
Merge a cover image into a PDF book while preserving aspect ratio and matching width. Use when the user wants to "merge cover", "combine pdf", "fix cover size", or "add cover image".
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Run and interpret visual QA pipeline for EPUB XHTML files. Use when user asks about layout, screenshots, visual issues, or rendering problems in REBRANDED_OUTPUT.
Structure documents with TLDR-first format. Use when creating any document, PRD, vision doc, or decision record.
Universal media processor that auto-detects and processes images or videos with appropriate tools. Use when users ask to process media files, batch convert media, compress mixed folders, auto-detect file types, or handle both images and videos together.
專案文檔結構管理工具，用於建立、維護和驗證專案的層級聚攏文檔結構。 使用時機： - 當需要建立新的 README.md 文件 - 當需要為程式檔案添加標準化開頭註解 - 當重構或更新專案文檔結構 - 當需要驗證 README 連結有效性 - 當需要檢查文檔結構完整性 關鍵字：README、文檔結構、層級聚攏、檔案註解、連結驗證、結構檢查
Automate the internationalization process: extracting strings, generating keys, and updating locale files.
Parse bank statement PDF text into structured transaction data with account information and transactions in consistent JSON format. Works with any bank format. Use when you need to extract or parse transactions from PDF bank statements.
Manipulate PDF files in Python: extract text/tables, create, merge, split, and fill forms. WHEN: Extracting text from PDFs, creating PDF documents, merging/splitting PDFs, filling PDF forms, working with pdfplumber/PyPDF2/reportlab. WHEN NOT: Word documents (use python-docx), Excel files (use python-xlsx), image processing.
Convert flat/scanned PDF documents into interactive fillable PDF forms using OCR-based field detection with AWS Textract and AI vision validation. Use when users need to: (1) Transform static PDFs into editable forms, (2) Detect and convert form fields (text inputs, checkboxes, signatures) automatically, (3) Digitize paper-based forms for electronic completion, (4) Validate form field detection accuracy, or (5) Batch convert multiple similar forms while preserving original styling and layout.
Extract and process content from PDFs and DOCX files. Handles large files, OCR for scanned documents, page splitting, and markdown conversion. Use when: (1) Processing PDF references in notes, (2) Extracting text from large documents for analysis, (3) Converting DOCX to markdown, (4) Handling scanned/image PDFs with OCR, (5) Integrating with Obsidian or note-taking workflows, (6) Splitting large documents into manageable chunks. Invoke with: /process-document, /extract-pdf, /extract-docx, or say "use document-processor skill to..."
Document OCR integration using Google Gemini Flash API for extracting data from passports and licenses.
Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.
Enforce consistent chapter formatting, numbering conventions, and structural alignment across the entire textbook. Use when creating new chapters, reviewing existing content for consistency, or establishing formatting standards.
Re-index all PDF and HTML documents, update index.html, and commit/push changes to the repository
Merge multiple PDF files into single document with customizable options. Supports page selection, bookmarks, and metadata. Use when combining PDFs, creating documents from multiple sources, or organizing PDF collections.
Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, remote URLs (including YouTube), or EPubs to Markdown format for LLM processing or text analysis.
