文档与 Office技能

Extract page text and tables from PDF files with Python, including tables that continue across pages. The skill shows how to turn table rows into pandas DataFrames and combine matching tables for analysis.

中文简介正在准备中。当前显示英语简介。

• Extracting tables from a PDF report
• Combining table data across PDF pages
• Loading PDF table rows into pandas

Fill Word templates with data by replacing placeholders across paragraphs, tables, headers, and footers. It handles placeholders split across formatting runs, nested tables, and conditional sections, then saves the completed document.

中文简介正在准备中。当前显示英语简介。

• Populate a Word template from a data file
• Replace placeholders split across text runs
• Process nested tables, headers, and footers

Prepare academic PDFs for blind review by removing matching identifying details before the References section. The skill focuses redaction on specific text matches, preserves references and self-citations, and checks that the saved document retains its pages and most of its text.

中文简介正在准备中。当前显示英语简介。

• Anonymizing an academic paper for blind review
• Removing author names and affiliations from a PDF
• Checking a redacted paper for text loss

Create, edit, and analyze Word documents while preserving formatting. Workflows cover text extraction, comments, tracked changes for review, and document creation, with guidance for handling complex document structure and embedded content.

中文简介正在准备中。当前显示英语简介。

• Creating a new Word document
• Editing a document with tracked changes
• Extracting text or reviewing comments in a DOCX

Create, edit, and analyze Excel workbooks. Use pandas to inspect and summarize spreadsheet data, and openpyxl for formulas, formatting, cell-level changes, multiple sheets, and programmatically defined pivot tables that group and aggregate data.

中文简介正在准备中。当前显示英语简介。

• Creating a formatted Excel workbook
• Analyzing data across Excel sheets
• Building a pivot table to summarize data

Extracts printed text from images with Tesseract OCR through Python. It can process single images or batches, report confidence and quality warnings, and return text in JSON, making scans, screenshots, receipts, and forms easier to search or reuse.

中文简介正在准备中。当前显示英语简介。

• Reading text from scanned documents or photos
• Extracting text from screenshots
• Processing receipts or forms in batches

Convert PDFs into Markdown with `marker_single`, preserving document structure and LaTeX formulas where available. Use it to extract text from academic papers or technical documents with equations, then read the Markdown through a Python helper or command line.

中文简介正在准备中。当前显示英语简介。

• Extract text and structure from an academic PDF
• Convert a technical PDF with equations into Markdown
• Keep intermediate conversion files for troubleshooting

Read and edit PDF documents with PyMuPDF while keeping their text layer intact. Find text positions, fill blank form fields, replace existing values in place, and remove sensitive text through true redaction. The guide also explains workflows to avoid when preserving searchable content matters.

中文简介正在准备中。当前显示英语简介。

• Extracting text from a PDF before editing
• Filling blank fields in a PDF form
• Replacing an existing value in place

Parse structured text files containing field names and values, including lines with or without leading bullets. The skill shows how to turn the text into key-value data that can be matched to labels when filling PDFs.

中文简介正在准备中。当前显示英语简介。

• Extracting names and contact details from a text file
• Preparing key-value data for filling a PDF
• Handling input lines with or without bullets

Extract text, tables, and images from PDFs, create documents, combine or split files, and fill forms. It also covers OCR, which reads text from scanned pages, plus watermarks, page rotation, and password protection.

中文简介正在准备中。当前显示英语简介。

• Extract PDF text and tables for reuse
• Merge documents or split selected pages
• Create PDFs and fill PDF forms

Create, edit, and analyze PowerPoint presentations. Work with slide content and layouts, and handle comments or speaker notes when needed. The supplied guidance covers both new decks and edits to existing presentations, including template based work.

中文简介正在准备中。当前显示英语简介。

• Creating a new PowerPoint presentation
• Editing slides in an existing deck
• Adapting a presentation to an existing template

Create, edit, and analyze Excel or delimited text spreadsheets. Work with formulas and formatting, preserve existing workbook conventions, summarize data, and recalculate formulas to check for spreadsheet errors.

中文简介正在准备中。当前显示英语简介。

• Creating a spreadsheet with formulas and formatting
• Analyzing or visualizing spreadsheet data
• Updating a workbook while preserving formulas

Process PDF files with Python libraries and command-line tools. Extract text, tables, metadata, or images; create, merge, split, rotate, and protect PDFs; and fill forms. Scanned documents can also be converted to images and read with OCR software.

中文简介正在准备中。当前显示英语简介。

• Extracting text or tables from PDFs
• Combining or splitting PDF files
• Creating reports or adding watermarks

Process filler word annotations to generate video edit lists. Use when working with timestamp annotations for removing speech disfluencies (um, uh, like, you know) from audio/video content.

中文简介正在准备中。当前显示原文说明。

Convert problem descriptions into graph representations

中文简介正在准备中。当前显示原文说明。

Generate visual representations of algorithm execution

中文简介正在准备中。当前显示原文说明。

Create Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.

中文简介正在准备中。当前显示原文说明。

Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet presentation'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate). DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base.

中文简介正在准备中。当前显示原文说明。

Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents. Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename.

中文简介正在准备中。当前显示原文说明。

Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style transition', 'animated slide sequence', 'shape continuity across slides'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate 1–5a). DO NOT invoke for a generic deck, pitch deck, or board review without cross-slide motion — route those to officecli-pptx base or officecli-pitch-deck.

中文简介正在准备中。当前显示原文说明。

Use this skill any time a .xlsx file is involved -- as input, output, or both. This includes: creating spreadsheets, financial models, dashboards, or trackers; reading, parsing, or extracting data from any .xlsx file; editing, modifying, or updating existing workbooks; working with formulas, charts, pivot tables, or templates; importing CSV/TSV data into Excel format. Trigger whenever the user mentions 'spreadsheet', 'workbook', 'Excel', 'financial model', 'tracker', 'dashboard', or references a .xlsx/.csv filename.

中文简介正在准备中。当前显示原文说明。

Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename.

中文简介正在准备中。当前显示原文说明。

Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation that requires planning before coding. Also triggers on Chinese keywords: "改造", "重写", "迁移", "重构", "大规模", "规范驱动". Performs full project analysis, task decomposition, documentation generation, project-level instruction and native memory surface resolution, progress tracking setup, and then executes the plan within the same session.

中文简介正在准备中。当前显示原文说明。

Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value', 'LBO', 'debt schedule', 'cash sweep', 'MOIC', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'ARR model', 'unit economics', 'CAC / LTV', 'cap table forecast'. Output is a single formula-driven .xlsx. This skill is a scene layer on top of officecli-xlsx — it inherits every xlsx v2 rule (4-color code, visual floor, number formats, cache-drift, Known Issues, Delivery Gate minimum cycle). DO NOT invoke for a simple budget tracker, CSV dump, or operational KPI sheet — route those to officecli-xlsx base.

中文简介正在准备中。当前显示原文说明。