documents▌

Have intelligent conversations about PDF documents - ask questions, get summaries, and extract specific information.

Create, read, edit, and analyze Word documents with full formatting control and tracked changes support. \n \n Supports reading, creating, and editing .docx files with comprehensive formatting options including tables, headers/footers, images, hyperlinks, and multi-column layouts \n Provides JavaScript-based document generation via docx-js library with critical guidance on page sizing (defaults to A4; use explicit DXA units), table width configuration, and style overrides \n Enables XML-level ed

Extract text from scanned documents and image-based PDFs using OCR technology.

Four slash commands for creating, maintaining, and auditing project documentation with smart templates. \n \n Provides /docs-init to scaffold CLAUDE.md, README.md, and docs/ structure for new projects, with auto-detection of project type (Cloudflare Workers, Next.js, or generic) \n Includes /docs-update for full documentation audits covering date freshness, version accuracy, broken links, redundancy, and orphaned files \n Offers /docs-claude for focused CLAUDE.md maintenance, checking tech stack

Production-ready PDF processing with forms, tables, OCR, and batch operations. \n \n Includes 10+ pre-built CLI scripts for form analysis, filling, table extraction, text extraction, PDF merging, splitting, and validation \n All scripts feature comprehensive error handling with exit codes, input validation, type hints, and configurable logging for automation integration \n Supports complex workflows: form field detection and filling with validation, multi-page table extraction to CSV/Excel, and

Comprehensive office productivity workflow for document creation, spreadsheet automation, presentation generation, and format conversion using LibreOffice and Microsoft Office tools.

Dual-engine OCR for extracting text from scanned PDFs and images with local or cloud processing. \n \n Supports RapidOCR (local, free, no API key) and SiliconFlow API (cloud-based, high precision) with automatic fallback when local engine fails \n Handles scanned PDFs and multiple image formats (JPG, PNG, BMP, GIF, TIFF, WEBP) with Chinese and English text recognition \n Preserves text order and structure; automatically converts PDF pages to images for processing \n Batch processing capability f

AI-powered illustration generation that analyzes document content and creates styled images for each key topic. \n \n Automatically extracts core themes from any document format (Markdown, plain text, PDF) without requiring specific structure \n Offers three visual styles: gradient glassmorphism, ticket/ticket-stub design, and flat vector illustration \n Supports flexible image ratios (16:9 landscape or 3:4 portrait) and optional cover image generation \n Displays归纳 results for user confirmation

Create, edit, and analyze Word documents with tracked changes, comments, and formatting preservation. \n \n Three distinct workflows: text extraction via pandoc, document creation using docx-js, and editing existing files via the Python Document library with OOXML manipulation \n Redlining workflow for comprehensive tracked changes with batching strategy, minimal precise edits, and systematic change implementation across document sections \n Raw XML access for comments, complex formatting, embed

Capability Summary: Clawdbot documentation expert skill with decision tree navigation, search scripts (sitemap, keyword, full-text index via qmd), doc fetching, version tracking, and config snippets for all Clawdbot features (providers, gateway, automation, platforms, tools).