Office & Document Skills

Skills for working with office documents and productivity suites. From extracting data from PDFs to generating PowerPoint slides and managing Google Workspace, these skills extend Claude Code into document workflows.

347 skills

find-skills

vercel-labs/skills

1.1M

14.2k

When users ask "how do I do X" or "can you help with Y," this skill searches the open agent skills ecosystem instead of making you reinvent the wheel. It checks skills.sh for existing solutions, runs CLI searches with specific keywords, and verifies quality by checking install counts and source reputation before recommending anything. The skill prioritizes battle-tested options from sources like vercel-labs and anthropics over unknown packages with low install counts. It's essentially a package manager interface that prevents you from manually coding solutions that already exist as installable skills.

azure-compute

microsoft/azure-skills+1 more

182.2k

633

Routes Azure VM questions to either recommendation or troubleshooting workflows based on user intent. If you're asking about VM sizing, pricing, or VMSS configuration, it hits the retail pricing API and VM families documentation to give workload-specific recommendations. For connectivity issues, it walks through RDP/SSH failures, NSG blocking, and password resets with structured diagnostics. The routing logic is clean and the workflows feel comprehensive, though you'll still need Azure CLI access for live troubleshooting. Solid choice if you're regularly fielding VM questions and want consistent, reference-backed responses instead of generic advice.

azure-ai

microsoft/github-copilot-for-azure

103.7k

160

Azure AI provides developers and cloud architects with tools to integrate Azure's AI services—including AI Search, Speech, OpenAI, and Document Intelligence—into their applications through MCP tools and CLI commands. The skill solves the problem of implementing complex AI capabilities like vector search, speech-to-text conversion, OCR, and semantic search by offering simplified access to these services. It serves users building AI-enhanced applications who need quick reference guides, SDK documentation, and command-line access to Azure's cognitive services.

AppSignal

Monitor with ease. Code with confidence.

monitoringapmdevtools

Start Free Trial

Sponsored

qwen-image-2-pro

inferen-sh/skills+11 more

96.5k

173

This is Alibaba's professional image generation model wrapped for Claude via the inference.sh CLI. The Pro version excels at text rendering in images, making it solid for posters, banners, and marketing materials where you need crisp, readable text overlays. It handles complex prompts better than the standard model and produces more photorealistic textures. You can control dimensions, generate multiple variations, and use reference images for style transfer. The skill shows practical examples for marketing banners and text-heavy designs. Good choice when DALL-E or Midjourney aren't cutting it for text-heavy commercial work.

seo-audit

coreyhaines31/marketingskills+3 more

78.7k

21.4k

Claude runs a systematic SEO audit covering crawlability, technical foundations, on-page optimization, and content quality. It checks robots.txt, sitemaps, Core Web Vitals, title tags, heading structure, and internal linking while flagging common issues like duplicate content, canonicalization problems, and keyword cannibalization. The skill includes a helpful warning about schema markup detection limitations since web_fetch can't see JavaScript-injected structured data. It adapts the audit scope based on your site type and provides actionable recommendations in priority order. Good for diagnosing traffic drops, pre-launch reviews, or comprehensive health checks when you suspect SEO issues but aren't sure where to start looking.

pdf

anthropics/skills+6 more

74.9k

118.1k

This is your Swiss Army knife for PDF operations. It covers the essential Python libraries (pypdf, pdfplumber, reportlab) plus command-line tools like qpdf for merging, splitting, text extraction, and table parsing. The OCR integration with pytesseract handles scanned documents, and it includes form filling guidance. What I appreciate is the practical focus on real workflows rather than just API documentation. The quick reference table saves time when you need to pick the right tool for each task. It won't replace specialized PDF tools for complex layouts, but it handles 90% of typical automation needs.

lark-im

larksuite/cli+22 more

59.8k

7.9k

A comprehensive Lark (Feishu) instant messaging integration that handles the full spectrum of chat operations: sending messages, searching chat history, managing group members, and downloading files with automatic chunking for large attachments. The skill wraps Lark's IM APIs with smart shortcuts that handle identity switching between user and bot tokens, resolve P2P chat IDs automatically, and batch operations for efficiency. What makes this particularly solid is the upfront handling of Lark's complex permission model and the practical shortcuts for common workflows like threaded replies and message search across multiple chats.

secure-linux-web-hosting

xixu-me/skills

56.2k

This walks you through hardening a fresh cloud server for web hosting without falling into outdated tutorial traps. It enforces safety gates like testing SSH keys before disabling password auth, verifying DNS before attempting Let's Encrypt, and confirming HTTPS works before forcing redirects. The workflow covers the full stack from firewall rules through Nginx config to certificate renewal, with separate branches for static sites versus reverse proxying apps. It verifies current package names and service units against official docs rather than assuming Debian defaults work everywhere. Good for when you need the discipline of a checklist but with commands that actually work on your specific distro.

caveman

juliusbrussee/caveman+2 more

48.3k

31.6k

Cuts Claude's response tokens by about 75% while keeping technical accuracy intact. Drops articles, filler words, and pleasantries but preserves exact technical terms and code blocks. Has six intensity levels from lite (just removes hedging) to ultra (heavy abbreviation) to wenyan modes that use classical Chinese patterns for maximum compression. Auto-triggers on phrases like "be brief" or "less tokens" and stays active until you say "normal mode". Smart enough to drop caveman temporarily for security warnings or destructive operations where clarity matters more than brevity.

better-auth-best-practices

better-auth/skills+1 more

37.8k

177

The better-auth-best-practices skill guides developers through configuring Better Auth, a TypeScript authentication library, including server and client setup, database adapter configuration, session management, and plugin integration. It's designed for developers building authentication systems with email/password or OAuth flows who need step-by-step setup instructions and configuration reference. The skill solves the problem of implementing secure, production-ready authentication by providing installation procedures, environment variable requirements, CLI commands, and core configuration options in one centralized guide.

nodejs-backend-patterns

wshobson/agents+5 more

25k

33.7k

Solid patterns for building Node.js backends that don't fall apart in production. Covers the essentials like proper layered architecture with controllers, services, and repositories, plus error handling middleware that actually catches things. Shows both Express and Fastify setups with TypeScript, authentication flows, and database integration patterns. The code examples are practical, not toy demos. You'll get structured approaches for REST APIs, input validation, password hashing, and SQL query organization. Good reference when you're past the tutorial phase but need proven patterns for real applications that handle traffic and don't leak memory.

firebase-auth-basics

firebase/agent-skills+1 more

23.6k

225

Firebase-auth-basics provides developers with guidance on setting up and implementing Firebase Authentication for applications that require user sign-in, account management, or secure data access. The skill covers core concepts including user properties, multiple identity provider options (email/password, Google, phone, anonymous, and custom auth), and token-based authentication workflows. It solves the problem of securely authenticating users and managing access control through Firebase's backend services and SDKs.

remotion

google-labs-code/stitch-skills+1 more

19.8k

4.5k

Converts Stitch design projects into professional walkthrough videos using Remotion's programmatic video generation. Pulls screenshots from your Stitch screens, sets up a React-based Remotion project with smooth transitions and text overlays, then renders everything to MP4. Handles the entire pipeline from asset retrieval to final render, creating ScreenSlide components with zoom animations and sequencing them with fade/slide transitions. Great when you need to demo app flows or create presentation videos from existing designs without screen recording. The generated Remotion code is clean and modifiable, so you can tweak timing, add voiceovers, or customize animations after the initial setup.

obsidian-markdown

kepano/obsidian-skills+4 more

19.5k

24.3k

Creates proper Obsidian-flavored markdown with all the vault-specific syntax that standard markdown parsers don't handle. Handles wikilinks with custom display text and section references, embeds for notes and media, the full callout system with folding, YAML frontmatter properties, and block references. Most useful when you're building notes that need to link together or when you want callouts and embeds to render correctly in Obsidian. The workflow approach is solid, walking through frontmatter setup to content creation to verification. Covers the syntax differences that trip people up when moving from regular markdown to Obsidian's extended version.

gws-gmail

googleworkspace/cli+85 more

19k

24.8k

A comprehensive Gmail wrapper that handles the common email operations you actually need. Built on Google Workspace CLI, it covers sending, reading, replying, forwarding, and inbox triage without forcing you to wrestle with raw Gmail API calls. The helper commands like `+triage` for unread summaries and `+reply` with automatic threading save you from implementing message parsing yourself. Authentication and security are handled through the shared GWS framework. If you're building anything that needs to interact with Gmail programmatically, this beats writing your own API integration from scratch.

electron

vercel-labs/agent-browser

16.8k

29.3k

The electron skill enables agents to automate Electron desktop applications (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) by connecting to their Chrome DevTools Protocol port and using the agent-browser snapshot-interact workflow. It solves the problem of automating native desktop apps by leveraging the fact that Electron apps are built on Chromium and expose a CDP port, allowing the same browser automation techniques to work on desktop applications. This skill is for users who need to interact with, test, or control Electron applications across macOS, Linux, and Windows platforms.

baoyu-slide-deck

jimliu/baoyu-skills

16.3k

14.6k

Baoyu-slide-deck generates professional slide deck images from markdown content by creating structured outlines with customizable style instructions and then rendering individual slides as images. It serves users who need to quickly transform written content into visual presentations, supporting multiple styles (blueprint, corporate, minimal, etc.), target audiences, and languages. The skill solves the problem of manually designing slides by automating the outline-to-image pipeline while allowing control over visual presentation, slide count, and content complexity.

excalidraw-diagram-generator

github/awesome-copilot+5 more

14.1k

29.9k

The excalidraw-diagram-generator skill converts natural language descriptions into Excalidraw-format diagrams, enabling users to create visual representations of flowcharts, mind maps, system architectures, and other diagram types without manual drawing. It serves developers, architects, and analysts who need to quickly visualize processes, systems, relationships, and ideas by generating .excalidraw JSON files that open directly in Excalidraw. This skill solves the problem of translating conceptual descriptions into structured visual diagrams, supporting nine diagram types including flowcharts, relationship diagrams, data flow diagrams, and sequence diagrams.

summarize

steipete/clawdis+4 more

11.4k

358.2k

A solid CLI that pulls text from URLs, PDFs, and YouTube videos, then feeds them to your choice of LLM for summarization. Handles the annoying extraction work so you don't need to copy-paste articles or hunt for YouTube transcripts. Supports all the major AI providers and has sensible defaults like Gemini Flash for speed. The YouTube transcript extraction is hit-or-miss depending on the video, but when it works it saves you from manually transcribing or installing yt-dlp. Good fallback options with Firecrawl for stubborn websites.

notion-api

intellectronica/agent-skills+1 more

11.3k

242

The notion-api skill provides comprehensive instructions for developers and automation users to interact with Notion workspaces through REST API calls, covering authentication, all available endpoints, pagination, error handling, and best practices. It solves the problem of programmatically reading, creating, updating, and deleting Notion content by offering detailed guidance on proper API key handling, request formatting, rate limiting, and confirmation protocols for destructive operations. The skill is designed for developers building integrations, agents, or scripts that need reliable, secure access to Notion data.

ckm%3Adesign-system

nextlevelbuilder/ui-ux-pro-max-skill+2 more

8.5k

65.7k

The ckm:design-system skill provides a three-layer token architecture (primitive, semantic, and component tokens) for creating systematic design systems, CSS variable management, and generating brand-compliant presentations. It serves design-to-code teams and frontend developers who need to establish design tokens, component specifications, spacing and typography scales, and Tailwind theme configurations. The skill solves the problem of maintaining consistency between design and implementation by automating token generation, validating token usage across codebases, and ensuring brand compliance through standardized token-driven slide creation.

ideabrowser.com

Find trending startup ideas with real demand. Launch with a team of AI agents.

startupsai agentsideas

Get trending startup ideas →

FAQ

Can Claude Code work with office documents?

Yes — office skills help Claude extract data from PDFs, manipulate Excel files, generate presentations, and integrate with Google Workspace and other productivity suites.

Related categories

Automation & Workflows891 Data Science & ML337 Productivity & Planning278