documents▌

Extract text, tables, and metadata from PDF documents with character-level precision. \n \n Supports text extraction with layout preservation, word-level positioning, and character-level access including font and size metadata \n Includes advanced table detection with customizable strategies (lines, text, explicit) and tolerance tuning for complex layouts \n Provides visual debugging via image rendering with overlays for characters, words, lines, and detected table boundaries \n Handles cropping

Technical writing and editing for Gemini CLI documentation with strict style adherence. \n \n Enforces comprehensive documentation standards covering voice, tone, grammar, formatting, and structure to ensure consistency across all .md files and /docs directory content \n Requires investigation of relevant code and existing documentation before making changes, with checks for impacted pages and sidebar navigation updates \n Applies specific rules for headings, lists, procedures, links, and access

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

将 Markdown 文档转换为专业的苹果设计风格 PDF 白皮书。

Create well-structured MDX documentation files for 8-bit components following the established patterns.

Consolidate redundant documentation while preserving 100% of valuable content.

Unified cross-application orchestrator for Excel, Word, and PowerPoint document workflows. \n \n Manages application state detection, switching, and document lifecycle (open, save, close) across all three WPS Office applications \n Handles cross-application data migration, content copying, and format synchronization between Excel tables, Word documents, and PowerPoint presentations \n Supports batch operations including format conversion, multi-file processing, and template application across do

Convert documents between formats using pandoc, the universal document converter.

Three tasks. One skill.

This skill enables advanced document parsing using docling - IBM's state-of-the-art document understanding library. Parse complex PDFs, Word documents, and images while preserving structure, extracting tables, figures, and handling multi-column layouts.