25 boosters for "agent-skill" — open source, verified from GitHub, ready to install
"name": "anthropic-agent-skills", "name": "Keith Lazuka", "email": "klazuka@anthropic.com"
17 Google Maps tools for AI agents — geocode, search, directions, weather, air quality, map images via MCP server or standalone CLI
检测和改写中文 AI 生成文本的完整工具链。可独立运行（统一 CLI 或独立脚本），也可作为 LLM prompt 指南使用。 所有脚本在 目录下，纯 Python，无依赖。 v3.0 所有阈值都基于 HC3-Chinese 300+300 人类/AI 样本的 Cohen's d 校准：
Use this skill for Step 4 and Step 5 work. If GTM config does not exist yet: For Shopify runs, also expect:
Use this skill for verification and optional publish handoff. If comparing against an older preview run, pass the previous health baseline: Run outside sandboxed environments by default. Do not first attempt the Playwright browser step inside the sandbox and then retry after it is intercepted.
Use this skill for Step 3 work only. If schema context is not prepared yet: If the site has a live GTM container installed, make sure has already produced before running .
Use this skill to audit the site's real live GTM setup before event generation. Run the live baseline step before schema preparation whenever the site has a real GTM container installed: If multiple live containers matter and the user already knows the primary comparison target:
Use this skill when the work starts from and the goal is to produce approved . 1. Read the current and page inventory. 2. Group pages by business purpose, not just URL shape.
Use this skill as the Shopify-specific branch contract after platform detection. Use this skill when: Shopify still uses the same early workflow as generic sites:
Use this skill as the end-to-end coordinator for GA4 + GTM tracking delivery. Do not assume the user wants the full workflow. <!-- event-tracking auto-update bootstrap:start -->
Use this skill for analysis-only work and fresh workflow bootstrap. In this repository, use the repo-root wrapper: Run outside sandboxed environments by default. Do not first attempt the Playwright crawl inside the sandbox and then retry after it is intercepted.
"name": "sciagent-skills", "description": "Life sciences computational skills for scientific AI agents — 60+ skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing", "name": "jaechang-hits"
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "01coder-agent-skills", "description": "Security scanning, content creation, and productivity skills for development workflows",
This skill encodes the complete design specification for professional business presentations — a consultant-grade PowerPoint framework based on McKinsey design principles. It includes: All specifications have been refined through iterative production feedback to ensure visual consistency, profession
"name": "matlab-skills", "description": "A collection of agent skills for MATLAB development, including Live Script generation, unit test creation and execution, performance optimization, HTML/JavaScript app building, and digital filter design.", "name": "The MathWorks, Inc.",
A progressive-disclosure skill for ROS 2 development — from first workspace to production fleet deployment. Each section below gives you the essential decision framework; detailed patterns, code templates, and anti-patterns live in the
Reference documentation for Prismatic platform operations and the standardized API access hierarchy. Prismatic API access follows a two-tier priority system for interactive agents (e.g., Orby). Builder agents (cni-builder, component-builder) use their own script-based pipelines and should not use MC
Reference documentation for building Prismatic Code Native Integrations (CNI). Do NOT use these MCP tools — they return incomplete data that causes broken scaffolds and missing connections downstream. A hook will deny them, but avoid the wasted round trip. All components are accessed via manifests:
Reference documentation for embedding Prismatic's integration marketplace and workflow builder inside a customer-facing web application. Embedding Prismatic means your customers never leave your app to manage integrations. The flow is: 1. Your backend generates a short-lived signed JWT (10 min) auth
Reference documentation for building Prismatic custom components. Do NOT use these MCP tools — they return incomplete data that causes broken scaffolds and missing connections downstream. A hook will deny them, but avoid the wasted round trip. Components define their own inputs — not wrappers. Each
Search and retrieve Prismatic product documentation and code examples to answer conceptual questions, explain features, and provide best-practice guidance. Prismatic docs pages serve clean markdown by appending to the URL path: The version strips HTML/CSS/JS, returning clean content ideal for LLM
你是 Relic 引擎，一个能把万物锻造成可交互数字灵魂的系统。 如果用户说"让我跟奶奶聊天""让我跟咪咪互动""模拟星火工作室群聊"或类似的体验请求： 2. 根据蒸馏对象类型，从 选择合适的模板
"name": "agent-skills", "description": "Portable skills library with output styles: documentation lookup, GitHub operations, dependency intelligence, UI/UX patterns, and skill crafting", "name": "Arvind Menon",
"name": "risingwave-agent-skills", "owner": { "name": "RisingWave Labs" }, "description": "Official RisingWave agent skills for AI coding assistants",
