🎯
Skills
Loading...
Showing 30 of 146049 results
Teaches AI agents how to connect to and operate Google Drive via the Membrane platform, enabling file management actions through natural language without manual API key handling. Part of Membrane's library of 3,000+ app integration skills.
OpenClaw is a self-hosted personal AI assistant that works across 14+ messaging channels (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Teams, and more) with voice support on macOS/iOS/Android and a live Canvas feature.
Agent skills for Vue 3 development, derived from real-world issues and providing specialized patterns for AI agents to enhance Vue development workflows.
Guides AI agents on iOS app localization using String Catalogs, pluralization rules, FormatStyle, and right-to-left layout support for Swift 6.3 and iOS 26+. Part of the swift-ios-skills collection.
Part of the 365 Skills collection, production-grade Claude Code skills including plugins for Draw.io, Mermaid, Excalidraw, PlantUML, and Tldraw diagram creation with PNG/SVG/PDF export capabilities.
AI skills for PixiJS v8 that teach agents correct usage of the fast 2D rendering library for WebGL, WebGPU, and Canvas, covering application setup, scene graph, sprites, graphics, filters, custom rendering, and migration from v7.
Parse unstructured documents (PDF, DOCX, PPTX, XLSX, images) locally with LlamaIndex's `@llamaindex/liteparse` CLI — no cloud, no LLM required. Supports text/JSON output, page ranges, OCR on/off via optional external OCR server, configurable DPI, and batch-parse on directories.
Full-stack development guide covering backend architecture, frontend-backend integration, API design (REST/GraphQL/tRPC), authentication, real-time features (SSE/WebSocket), error handling, and production hardening across multiple frameworks including Express, Next.js, Django, and Go.
Run agent-browser browser automation on AWS Bedrock AgentCore cloud browser sessions, resolving credentials automatically from environment variables or the AWS CLI. All standard agent-browser commands (open, snapshot, click, screenshot, close) work identically — only the browser runtime changes to a managed AWS-hosted session.
An AI skill for PixiJS v8 that teaches agents advanced custom rendering techniques including custom shaders, uniforms, filters, and batchers using Shader.from, GlProgram/GpuProgram, UBO, and Filter.from.
Agent skill for benchmarking and optimizing Xcode build performance across clean builds, incremental builds, compile hotspots, project settings, and Swift Package Manager overhead.
Helps developers customize and extend the Medusa admin dashboard by generating modular, best-practice UI components and configuration code.
An AI skill for PixiJS v8 that teaches agents how to overlay HTML elements on the canvas using DOMContainer, including anchor positioning, CSS transforms, and pointer-events integration.
Official ClickHouse agent skills providing 28 best-practice rules for schema design, query optimization, and data ingestion, covering both open-source ClickHouse and ClickHouse Cloud. Also includes skills for chdb, the in-process ClickHouse engine for Python.
A collection of 65 Claude Code skills and 9 workflows with progressive disclosure, covering full-stack development including context engineering and Atlassian integration.
AI skills for PixiJS v8 that teach agents correct usage of the fast 2D rendering library for WebGL, WebGPU, and Canvas, covering scene graph, sprites, graphics, filters, performance optimization, and migration from v7.
Xiaohongshu (小红书) note analysis tool built as an AI Studio app, analyzing content performance and providing recommendations for social media posts.
A Claude Code skill for TanStack Router that provides guidance on type-safe file-based routing with search params and data loading.
A lightweight web content extraction tool that converts any webpage into clean Markdown format, using Scrapling with dual fast/stealth modes and Jina Reader as fallback, with excellent support for Chinese platforms like WeChat, Zhihu, CSDN, and Juejin.
A research API skill for discovering crypto and Solana startup opportunities, using builder project history, crypto archives, investor theses, and market signals to vet ideas and perform deep competitive analysis.
Build throwaway prototypes before committing to a solution to surface design issues — can be a runnable terminal app for state/business-logic problems or multiple UI variants toggled on the same route. Chinese localized version of mattpocock/skills.
A comprehensive performance optimization system for AI agent harnesses, providing 48+ agents, 184+ skills, hooks, rules, and MCP configurations across 12+ language ecosystems for Claude Code, Codex, Cursor, and other AI coding assistants.
Searches Naver blogs, reads full post content, and downloads images using only python3 stdlib — no API key required. Uses mobile (m.blog.naver.com) to bypass iframes, returns structured JSON from naver_search.py/naver_read.py, and pulls images from blogfiles.naver.net and postfiles.pstatic.net CDNs.
A collection of Agent Skills for Xiaohongshu (Little Red Book) based on xiaohongshu-mcp, providing full automation including login management, posting notes, searching content, browsing recommendations, user interaction (likes, bookmarks, comments), and content planning.
An AI skill for PixiJS v8 that teaches agents how to create custom geometry and mesh-based rendering using MeshGeometry, MeshSimple, MeshPlane, MeshRope, and PerspectiveMesh for advanced visual effects.
A collection of 65 Claude Code skills and 9 workflows with progressive disclosure, covering full-stack development including context engineering and Atlassian integration.
A collection of production-ready Claude Code skills covering Tailwind CSS v4, shadcn/ui integration, and modern web development patterns.