PDF & office files
3,211 rows from 809 repositories
The formats corporate work is actually stored in.
What PDF & office files skills agree on
581 skill files read, by 569 of the 585 authors on this shelf whose files we hold, 2026-09-06
The middle one of the 75 measured here is ~1.6k tokens long, counted with cl100k_base
Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.
What they tell the agent to do
- Ensure every slide fits inside one viewport20 of 569 in 11 filesalso worded as Ensure every slide fits one viewport; Ensure every slide fits the viewport
- Check for product marketing context first15 of 569 in 5 files
- Ask for the minimum needed15 of 569 in 5 filesalso worded as Ask for the minimum needed form fields; Ask for the minimum needed fields
- Set the API key environment variable15 of 569 in 10 filesalso worded as Set the NUTRIENT_API_KEY environment variable; Set the API key in the environment
- Support keyboard and touch navigation14 of 569 in 5 filesalso worded as Include keyboard and touch navigation
- Match the buyer stage13 of 569 in 3 files
- Split overflowing content into multiple slides12 of 569 in 3 filesalso worded as Split content into multiple slides if it exceeds limits
- Set page size explicitly for consistent results12 of 569 in 5 filesalso worded as Set page size explicitly; Always set page size explicitly for consistent results
- Convert documents to markdown using pandoc12 of 569 in 6 filesalso worded as Convert the document to markdown using pandoc; Convert Markdown to DOCX using Pandoc
- Read STYLE_PRESETS.md before generating12 of 569 in 7 filesalso worded as Read style presets before generating; Read the styling spec before generating
- Send multipart POST requests to the API12 of 569 in 7 filesalso worded as Send multipart POST requests to the API endpoint; Use multipart POST requests for API calls
- Use smart quotes for new content11 of 569 in 4 files
- Include an instructions JSON field in requests11 of 569 in 6 filesalso worded as Include an instructions JSON field in requests; Include an instructions JSON field with requests
- Pack the final document back to docx11 of 569 in 5 filesalso worded as Pack the final document using the pack script; Pack directories back into docx files
- Delete temporary preview files at handoff10 of 569 in 5 files
What they tell it not to do
- Never allow scrollbars inside a slide20 of 569 in 11 filesalso worded as Never scroll within a slide; Never allow a scrollbar inside a slide
- Never solve overflow by shrinking text18 of 569 in 9 filesalso worded as Never solve overflow by shrinking text below readable sizes; Do not shrink text to fit overflow
- Never set any range limits when reading this file14 of 569 in 10 filesalso worded as Never set any range limits when reading documentation files; Never set any range limits when reading the html2pptx.md file
- Never use WidthType.PERCENTAGE for tables13 of 569 in 6 filesalso worded as Never use WidthType PERCENTAGE; Do not use WidthType.PERCENTAGE
- Never use Unicode bullets12 of 569 in 5 filesalso worded as Do not use unicode bullets
- Do not write Python scripts for edits12 of 569 in 5 filesalso worded as Do not write Python scripts for editing; Do not write Python scripts
- Do not rely on macOS-only tools11 of 569 in 7 filesalso worded as Do not use macOS-only tools for conversion; Do not rely on macOS-only tools when Python can do the job
- Never use tables as dividers or rules11 of 569 in 4 filesalso worded as Never use tables as dividers; Never use tables as dividers/rules
- Do not use markdown line numbers11 of 569 in 5 filesalso worded as Do not use markdown line numbers for XML location; Do not use markdown line numbers for location methods
- Never use accent lines under titles9 of 569
What they expect to be installed
- python132 of 569 in 128 files
- python389 of 569 in 81 files
- pandoc56 of 569 in 45 files
- python-pptx44 of 569 in 32 files
- pdftoppm44 of 569 in 42 files
- pip42 of 569 in 39 files
- openpyxl41 of 569 in 37 files
- soffice40 of 569 in 36 files
- npm35 of 569 in 29 files
- node34 of 569 in 33 files
What they ask it to produce
- Markdown69 of 569 in 60 filesalso worded as Markdown file; Markdown text
- PDF65 of 569 in 53 filesalso worded as PDF document; page.pdf
- pptx48 of 569 in 44 filesalso worded as PPTX presentation; presentation.pptx
- DOCX35 of 569 in 27 filesalso worded as DOCX document; DOCX report
- PDF file34 of 569 in 26 filesalso worded as PDF files; PdfFile
- presentation.html29 of 569 in 19 filesalso worded as [presentation-name].html; presentations
- watermarked.pdf22 of 569 in 13 filesalso worded as watermarked pdf
- tables.xlsx22 of 569 in 14 filesalso worded as extracted_tables.xlsx
When PDF & office files authors say to reach for one
The situations these authors wrote into their own files, counted out of the same 569 authors, with the skills that name each one
- Improving an existing HTML presentation17 of 569 in 8 files
- Extracting text or tables from PDFs16 of 569 in 11 files
- Nutrient document processing
- and 7 more on this shelf
- Converting .ppt or .pptx slides into HTML16 of 569 in 7 files
- User wants to create a lead magnet15 of 569 in 5 files
- Lead magnets
- Marketing lead magnets
- and 16 more on this shelf
- Converting documents between formats15 of 569 in 10 files
- Nutrient document processing
- Academic paper
- Academic academic paper
- and 8 more on this shelf
- Creating a talk, pitch, workshop, or internal presentation15 of 569 in 6 files
- Word document12 of 569 in 5 files
- Agents docx
- Docx
- Processing docx
- Docx skills docx docx
- Docx skill
- Docx official
- and 30 more on this shelf
How PDF & office files skills are built
2,830 skill directories by 681 authors, read from their repositories’ own file trees 2026-08-05
The middle bundle among those shipping files is 6 files, 49.4 KB beside SKILL.md
Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.
The shape
- SKILL.md is the whole skill134 of 681 authors, 879 of 2,830 skills
- files ship beside it547 of 681 authors, 1,951 of 2,830 skills
- executable scripts ship inside409 of 681 authors, 1,304 of 2,830 skills
The folders they converge on
- scripts/370 of 681 authors, 1,138 of 2,830 skills
- references/275 of 681 authors, 681 of 2,830 skills
- assets/105 of 681 authors, 192 of 2,830 skills
- agents/103 of 681 authors, 166 of 2,830 skills
- examples/51 of 681 authors, 78 of 2,830 skills
- ooxml/48 of 681 authors, 153 of 2,830 skills
eigent-ai/eigent/resources/example-skills/docx Skill
15,013★ repoEigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
OpenSenseNova/SenseNova-Skills/skills/sn-da-excel-workflow Skill
4,914★ repoModular SenseNova skills for building AI-powered office assistants and productivity workflows
axoviq-ai/synthadoc/synthadoc/skills/docx Skill
970★ repoSynthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
SylphxAI/pdf-reader-mcp/io.github.SylphxAI/pdf-reader-mcp MCP server
887★ repoEvidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.
Gabberflast/academic-pptx-skill Skill
760★A Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant briefings). Enforces action titles, structured argument, exhibit discipline, citation standards, and communication-first design. Works alongside Anthropic's built-in PPTX skill.
sbroenne/mcp-server-excel/io.github.sbroenne/mcp-server-excel MCP server
532★ repoExcel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
MemTensor/skills-vote/examples/evaluate_skills/pdf Skill
295★ repoSkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
modu-ai/cowork-plugins/moai-bi/skills/executive-summary Skill
268★ repo모두의 AI (MoAI) — Claude Cowork & Claude Code 한국 실무 도메인 AI 하네스·플러그인 마켓플레이스. 사업계획서·세무·법률·HR·마케팅·커머스·BI·콘텐츠 도메인 스킬·에이전트·워크플로우. Korean B2B + office docs (HWPX/DOCX/XLSX/PPTX/PDF) + AI media (image/video/voice). AI-slop 검수 + humanize-korean 내장.
bowenliang123/markdown-exporter Skill
261★An Agent Skill and Dify plugin to transform Markdown to files of DOCX, PPTX, XLSX, PNG, PDF, Mermaid, HTML, MD, CSV, JSON, XML.
leemysw/feishu-docx/.skills/feishu-docx Skill
247★ repo🚀 Feishu/Lark Docs、Sheet、Bitable <-> Markdown | AI Agent-friendly knowledge base exporter and writer with OAuth 2.0, CLI, TUI & Claude Skills support - 飞书文档 <写入/导出> Markdown | AI Agent 友好型导出-写入工具
KaguraNanaga/document-format-skills Skill
211★Professional Word document formatting toolkit for Chinese documents
opendatalab/MinerU-Ecosystem/io.github.opendatalab/mineru-open-mcp MCP server
188★ repoParse PDFs, images, doc, docx, ppt, pptx, xls, xlsx, html into Markdown using MinerU API.
dog-qiuqiu/invincat/invincat_cli/built_in_skills/docx Skill
153★ repoA native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management.
appautomaton/document-SKILLs/docx Skill
143★ repoClaude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas, tracked changes, adapted from Anthropic skills.
xlbaoxl/interactive-map-builder Skill
121★Build polished interactive maps and report-ready figures from spatial data with AI agents.
ShZhao27208/Aut_Sci_ppt Skill
115★Aut_Sci_PPt is an automated agent designed to convert academic papers (PDF) or structured text into professional, presentation-ready PowerPoint files (.pptx). It is specifically optimized for graduate defense, academic seminars, and research proposals.
ComPDFKit/compdf-skills/skills/pdf-editor-compdf Skill
no license105★ repoComPDF Skills are AI-agent-ready PDF processing skills for Claude Code, Cursor, Copilot, OpenCode, and 39+ coding agents to convert, edit, split, insert, compare, compress PDFs, and more.
jztan/pdf-mcp/io.github.jztan/pdf-mcp MCP server
100★ repoProduction-ready MCP server for PDF processing with intelligent caching.
Futuristic tech editorial ppt skill
software-ai-life/Awesome-PPT-Design-Skills/futuristic-tech-editorial-ppt-skill Skill
no license80★ repoAgent-agnostic PPT design skills for creating high-end, editable presentation styles.
bruc3van/bruce-doc-converter/bruce-doc-converter-skill Skill
no license56★ repo为 Claude Code / OpenClaw 添加双向文档转换能力。支持 Word/Excel/PPT/PDF ↔ Markdown,导出精美 Word 文档。
tanis90/pdf-converter-mineru Skill
no license52★a pdf converter skill base on mineru ecosystem
PSU3D0/spreadsheet-mcp/io.github.PSU3D0/spreadsheet-mcp MCP server
51★ repoAgent-safe Excel workbook analysis, editing, recalc, and verification tools.
Hasasasa/html-to-editable-pptx Skill
50★Convert HTML slide decks to truly editable PPT / .pptx - text stays native PowerPoint textboxes, not screenshots. Agent Skill (Claude Code / Cursor / Codex / opencode) + plain Python CLI.
spencermarx/obsidian-ai/.ocr/skills Skill
46★ repoBring your own AI environment to Obsidian. For note/doc creation, refinement, search, organization, management, you name it!
jiankang1991/nsfc-benzi-audit/nsfc-benzi-audit Skill
40★ repo一个用于国家自然科学基金(NSFC/国自然)申请书初稿诊断的 Agent Skill
FTShare-Lab/FTShare-skills/ftshare-market-data Skill
38★ repoFTShare Agent Skills for financial data and investment research workflows|金融数据 Skill 与投研业务 Skill 仓库。
UseJunior/safe-docx/io.github.UseJunior/safe-docx MCP server
37★ repoAI-native surgical editing of Word .docx and OpenDocument .odt files with formatting preservation
songhai-dg/review-write Skill
35★Evidence-preserving professional writing review and rewrite Skill for Chinese and English: review first, protect facts, deliver clean body.
trsdn/mcp-server-ppt/io.github.trsdn/mcp-server-ppt MCP server
35★ repoPowerPoint automation for AI - Slides, Shapes, Text, Charts and more. Windows only.
tristan-mcinnis/PPT-Translator-Formatting-Intact-with-LLMs/.claude/skills/ppt-translator Skill
no license33★ repoA powerful PowerPoint translation tool that preserves all formatting while translating content using the Deepseek API. This tool maintains fonts, colors, layouts, and other styling elements while providing accurate translations between languages.
TateZhouSiu/image-ppt-king/skills/image-ppt-king Skill
29★ repoTurn slide screenshots and generated images into editable PowerPoint decks with visual-layer splitting, OCR evidence, and QA.
daxueren666/exam-review-helper/skills/exam-review-helper Skill
27★ repo把 PDF/Word/TXT/Markdown 教材浓缩成交互式 HTML 复习文档的 Claude Code / Codex CLI Skill。自动识别文科/理工科模式,5-pass 深度提取,原生支持扫描版 PDF OCR。v1.2 用 pdfium 后端修复 docling std::bad_alloc 崩溃,大 PDF 稳定提取。
peixl/ifq-design-skills/.well-known/agent-skills/ifq-design-skills Skill
24★ repoAgent-native design skill: ordinary prompts -> verified HTML-first prototypes, decks, dashboards, motion demos, and export-ready visuals.
analystacademy/flight-check Skill
23★Final check for AI-generated slide decks — catches fake sources, AI tells, and other mistakes you don't want in your presentation.
xt765/mcp_documents_reader/io.github.xt765/mcp_documents_reader MCP server
23★ repoAn MCP enabled multi-format document reader supporting DOCX, PDF, TXT, and Excel files
spencermarx/orc/.ocr/skills Skill
no license22★ repoA lightweight orchestration framework that piggybacks your local Agentic CLI setup. Intentionally simple. Yet powerful... like an army of Orcs 👹
ur-grue/autopunk-media-skills/.claude/skills/docx Skill
21★ repo394 free AI skills and 6 agents for media professionals — journalists, producers, podcasters, YouTubers. Quality-tested. Works with Claude, ChatGPT, Cursor, Codex CLI, and more.
VOYAGER-Inc/excel-vision-mcp/io.github.VOYAGER-Inc/excel-vision-mcp MCP server
19★ repoExcel MCP with image extraction and write support — AI agents see and edit xlsx files
PSPDFKit-labs/nutrient-skills/plugins/make-pdf/skills/make-pdf Skill
no license15★ repoAI agent skills for Nutrient APIs and SDKs — works with Claude Code, Codex, Gemini CLI, Cursor, and 35+ more agents
PSPDFKit-labs/nutrient-agent-skill/nutrient-document-processing Skill
no license15★ repoUniversal Agent Skill for document processing with Nutrient DWS API — works with Claude Code, Codex, Gemini CLI, Cursor, and 35+ more agents
ethanolivertroy/compliance-trestle-skills/.cursor/skills/import-legacy-ssp Skill
15★ repoAgent-portable Compliance Trestle and OSCAL engineering toolkit: convert legacy SSPs to OSCAL, validate with Trestle and oscal-cli, FedRAMP Rev 5 and 20x KSI workflows. Claude Code plugin plus portable skills for Cursor, Codex, Gemini, and more.
SlideSpeak/slide-design-skill Skill
13★AI presentation engine. Describe your deck and the look, it derives a bespoke style and renders polished 1920x1080 HTML slides with real charts, tables and imagery. Agent skill: npx skills add SlideSpeak/slide-design-skill
foxitsoftware/foxit-pdf-api-mcp-server/io.github.foxitsoftware/foxit-pdf-api-mcp-server MCP server
no license12★ repoMCP server that exposes Foxit PDF API capabilities via stdio.
xt765/mcp-document-converter/io.github.xt765/mcp-document-converter MCP server
12★ repoConvert PDF, DOCX, HTML, Markdown, and Text for AI assistant context injection.
gonta223/japanese-corporate-pptx-skill/skills/japanese-corporate-pptx Skill
11★ repopattern-ai-labs/built-with-agentcall/meeting-presenter Skill
11★ repoA collection of real-world use cases built with agentcall.dev — each folder is a self-contained, working example. By Pattern AI Labs.
BayramAnnakov/excel-hygiene Skill
11★A 'second pair of eyes' Claude Code skill for any .xlsx — deterministic mechanical checks (openpyxl) plus Panko–Halverson error-taxonomy reasoning.
maaarcooo/agent-skills/archive/claude-ai/pdf-extract Skill
no license10★ repoAgent skills for Claude.ai, Claude Code, ChatGPT, and Codex, covering document processing, study tools, and cross-agent workflows.
sbroenne/mcp-server-powerpoint/io.github.sbroenne/mcp-server-powerpoint MCP server
10★ repoPowerPoint automation for AI: slides, shapes, tables, charts, images, notes. Windows only.
esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri/skills/dilekce-crac Skill
9★ repoYapay zeka icin Turkce hukuki dilekce yazim cercevesi skilleri (IRAC ailesi, CREAC, Toulmin, klasik retorik) - Claude Code skills; docx/html/udf/pdf cikti, KVKK-temiz.
Renakoni/note-organizer Skill
9★笔记整理 Skill:一个用于 Claude Code 的课程资料、PDF、PPT、题库整理成 Markdown/Obsidian 复习笔记的 Claude Skill。
AryanBV/pdf-toolkit-mcp/io.github.AryanBV/pdf-toolkit-mcp MCP server
9★ repoWrite-capable PDF toolkit MCP: 22 tools to read, create, render, encrypt, merge & fill PDFs.
linxule/mineru-mcp/io.github.linxule/mineru MCP server
9★ repoMinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
willem4130/claude-code-skills/skills/elite-powerpoint-designer Skill
no license8★ repoDevelopment playground and collection of custom skills for Claude Code - extending Claude with modular, reusable workflows
kyopark2014/sam-project/application/skills/docx Skill
8★ repoIt is an agent based on Strands SDK using MCP and SKILL.
docusealco/docuseal-agent-skills/skills/docuseal-cli Skill
8★ repoDocuSeal's official collection of agent skills
kangdacool/hwpx-editing-skill/skills/hwpx-editing Skill
8★ repoLLM 에이전트(Claude Code·Codex 등)가 한글 .hwpx 파일을 안 깨고 편집하게 해주는 검증된 규칙 + 파이썬 도구 스킬. A portable Agent Skill that teaches Claude Code, Codex, and other LLM agents to edit HWPX (Hangul .hwpx) files without corrupting them.
zhangzhangco/gbt-standard-docx-skill Skill
no license8★基于 Word 模板生成、校验和审查符合 GB/T 1.1 体例的中文标准文稿 skill。
Document to JSON – PDF Invoice/Statement/Contract Parser
fashionmascherine-svg/document-to-json-mcp/io.github.fashionmascherine-svg/document-to-json-mcp MCP server
8★ repoTurn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Agent-Engineer-Master/skill-engineer/design/html-output Skill
7★ repoShared public skills developed by Skill Engineer