documents▌

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.

Extract formatting information from existing Word documents (.docx) and use it to generate new documents with identical formatting but different content. This skill enables creating document templates, maintaining consistent formatting across multiple documents, and replicating complex Word document structures.

Convert Office documents to clean, searchable Markdown using Microsoft's markitdown tool. \n \n Supports Word, Excel, PowerPoint, PDF, HTML, images, and audio files with format-specific handling (tables, slides, OCR) \n Preserves document structure including headings, lists, tables, formatting, and hyperlinks during conversion \n Includes Python API and command-line interface for single files or batch processing across multiple documents \n Optional LLM integration with Claude for enhanced image

负责钉钉知识库和文档的所有操作。本文件为策略指南，仅包含决策逻辑和工作流程。完整 API 请求格式见文末「references/api.md 查阅索引」。

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Programmatic creation, editing, and manipulation of Word documents with formatting, tables, and images. \n \n Supports document creation from scratch, opening existing files, and template-based workflows with placeholder replacement \n Includes comprehensive formatting capabilities: paragraphs, headings, character styling, page setup, headers, footers, and built-in Word styles \n Enables table creation with dynamic row/column management, cell merging, and data population from structured sources

Add watermarks, page numbers, headers, footers, and other overlay elements to PDF documents.

This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.

Complete technical documentation for Hindsight - a biomimetic memory system for AI agents.

Professional document creation, editing, and analysis across Word, PDF, PowerPoint, and Excel formats. \n \n Four specialized sub-skills handle distinct document types: docx for Word documents with tracked changes and comments, pdf for text/table extraction and document merging, pptx for presentation creation and layout management, and xlsx for spreadsheet manipulation and formulas \n Supports both creation from scratch and editing of existing files, with language-specific libraries (docx-js for