███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 17651 | monitor-etf-holdings-drawdown-risk | fatfingererr/macro-skills |
<essential_principles> 背離事件定義: - 價格上漲:`price_return >= min_price_return_pct`(如 +15%) - 庫存下滑:`inventory_change <= -min_inventory_drawdown_pct`(如 -10%) - 同時發生:在相同視窗期(如 180 天)內同時滿足 當價格與庫存同向時(同漲同跌)為正常;逆向時(價漲庫跌)才需要警覺。 不能直接把「庫存下降」解讀為「實物被搶」,需要交叉驗證: | 實物緊張 | COMEX/LBMA 下降、backwardation、lease rates 上升、零售溢價擴大 | 其他庫存穩定、contango、溢價平穩 | 資金流/贖回 | ETF 流出但交易所庫存穩定、期貨結構不緊 | 多重庫存同步下降 輸出兩種解釋,讓用戶判斷哪個更符合當前數據。 本 skill 優先使用: - ETF 官網庫存:Selenium 模擬人類瀏覽器行為抓取(避免 API 限制) - Yahoo Finance:`yfinance` 套件取得現貨/...
|
61 |
| 17652 | gathering-ui | autumnsgrove/groveengine |
Gathering UI 🌲🦎🦌 The drum echoes through the glade. The Chameleon shifts its colors, painting the forest with glass and light. The Deer senses what others cannot see, ensuring every path is clear. Together they create spaces that welcome all wanderers—beautiful to behold, accessible to all. When to Summon Designing new pages or interfaces Implementing complete UI features Ensuring visual design meets accessibility standards Creating Grove-themed experiences When beauty and inclusion must coexist...
|
61 |
| 17653 | root-cause-tracing | secondsky/claude-skills |
Root Cause Tracing Overview Bugs often manifest deep in the call stack (git init in wrong directory, file created in wrong location, database opened with wrong path). Your instinct is to fix where the error appears, but that's treating a symptom. Core principle: Trace backward through the call chain until you find the original trigger, then fix at the source. When to Use digraph when_to_use { "Bug appears deep in stack?" [ shape = diamond ] ; "Can trace backwards?" [ shape = diamond ] ; "Fix at ...
|
61 |
| 17654 | mise-configuration | terrylica/cc-skills |
Use mise `[env]` as centralized configuration with backward-compatible defaults. Core Principle Define all configurable values in `.mise.toml` `[env]` section. Scripts read via environment variables with fallback defaults. Same code path works WITH or WITHOUT mise installed. Key insight: mise auto-loads `[env]` values when shell has `mise activate` configured. Scripts using `os.environ.get("VAR", "default")` pattern work identically whether mise is present or not. Quick Reference Languag...
|
61 |
| 17655 | axiom-transferable-ref | charleswiltgen/axiom |
Transferable & Content Sharing Reference Comprehensive guide to the CoreTransferable framework and SwiftUI sharing surfaces: drag and drop, copy/paste, and ShareLink. When to Use This Skill Implementing drag and drop ( .draggable , .dropDestination ) Adding copy/paste support ( .copyable , .pasteDestination , PasteButton ) Sharing content via ShareLink Making custom types transferable Declaring custom UTTypes for app-specific formats Bridging Transferable types with UIKit's NSItemProvider Choosi...
|
61 |
| 17656 | conversion-copywriting | guia-matthieu/clawfu-skills |
Conversion Copywriting - Data-Driven Copy That Converts Write copy that gets a "yes" using Joanna Wiebe's research-first, Voice of Customer methodology When to Use This Skill Writing landing pages, emails, or sales pages that need measurable conversion results Starting a new copy project and need a systematic process to follow Struggling with what to write and staring at a blank page Wanting to prove ROI to clients with data-backed decisions Improving existing copy through validation and testing...
|
61 |
| 17657 | cpp-expert | personamanagmentlayer/pcl |
C++ Expert Expert guidance for modern C++ development including C++20/23 features, STL, templates, memory management, and high-performance programming. Core Concepts Modern C++ Features (C++20/23) Concepts and constraints Ranges and views Coroutines Modules Three-way comparison (spaceship operator) std::format std::span Designated initializers consteval and constinit Memory Management RAII (Resource Acquisition Is Initialization) Smart pointers (unique_ptr, shared_ptr, weak_ptr) Move semantics...
|
61 |
| 17658 | notebooklm | sanjay3290/ai-skills |
NotebookLM Research Assistant Skill Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes. When to Use This Skill Trigger when user: Mentions NotebookLM explicitly Shares NotebookLM URL ( https://notebooklm.google.com/notebook/... ) Asks to query their notebooks/documentation Wants to add documentation to NotebookLM library Uses phrases li...
|
61 |
| 17659 | tiptap-dev | xiaolai/vmark |
Tiptap Development Expert Expert guidance for building rich text editors with Tiptap - a headless, framework-agnostic editor built on ProseMirror. See also: tiptap-editor skill — VMark-specific Tiptap API patterns (commands, node traversal, selection handling). Use tiptap-dev for general Tiptap/ProseMirror development, and tiptap-editor for VMark-specific editor integration. When to Use This Skill Creating custom nodes, marks, or extensions for Tiptap Implementing input rules or paste rules Work...
|
61 |
| 17660 | landing-page-optimization | reynau/landing-page-optimization |
Landing Page Optimization Build, write, and optimize high-converting landing pages combining proven copy frameworks, the 11-essential-elements structure, and a clear creation workflow. 1. Copy Framework Gather Before Writing Collect these inputs before drafting any copy: Product/service name and core value proposition Target audience and their primary pain point Key differentiator vs alternatives Desired visitor action (CTA goal) Available social proof (testimonials, stats, logos) Choose a Frame...
|
61 |
| 17661 | development | sickn33/antigravity-awesome-skills |
Project Handover - Development Generate a complete technical guide for developers. This skill analyzes the codebase and produces actionable documentation that enables developers to understand, maintain, and extend the project. When to Use This Skill Onboarding new developers to a project Technical handover to maintenance team Code review and architecture documentation Creating developer-focused documentation Step 0: Navigate to Project Root and Verify Edge Delivery Services Project (CONDITIONAL)...
|
61 |
| 17662 | api-design-principles | secondsky/claude-skills |
API Design Principles Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers and stand the test of time. When to Use This Skill Designing new REST or GraphQL APIs Refactoring existing APIs for better usability Establishing API design standards for your team Reviewing API specifications before implementation Migrating between API paradigms (REST to GraphQL, etc.) Creating developer-friendly API documentation Optimizing APIs for ...
|
61 |
| 17663 | websocket-implementation | secondsky/claude-skills |
WebSocket Implementation Overview Build scalable WebSocket systems for real-time communication with proper connection management, message routing, error handling, and horizontal scaling support. When to Use Building real-time chat and messaging Implementing live notifications Creating collaborative editing tools Broadcasting live data updates Building real-time dashboards Streaming events to clients Live multiplayer games Instructions 1. Node.js WebSocket Server (Socket.IO) const express = req...
|
61 |
| 17664 | code-review | getsentry/sentry-skills |
Code Review When to use this skill Reviewing pull requests Checking code quality Providing feedback on implementations Identifying potential bugs Suggesting improvements Security audits Performance analysis Instructions Step 1: Understand the context Read the PR description : What is the goal of this change? Which issues does it address? Are there any special considerations? Check the scope : How many files changed? What type of changes? (feature, bugfix, refactor) Are tests included? Step 2: Hi...
|
61 |
| 17665 | vercel | hoodini/ai-agents-skills |
Vercel Deployment Deploy and scale applications on Vercel's edge network. Quick Start Install Vercel CLI npm i -g vercel Deploy vercel Production deploy vercel --prod vercel.json Configuration { "buildCommand" : "npm run build" , "outputDirectory" : ".next" , "framework" : "nextjs" , "regions" : [ "iad1" , "sfo1" ] , "functions" : { "api//*.ts" : { "memory" : 1024 , "maxDuration" : 30 } } , "rewrites" : [ { "source" : "/api/:path*" , "destination" : "/api/:path*" } , { "source" : "/:path*" , ...
|
61 |
| 17666 | module-learning-path-generator | jorgealves/agent_skills |
Mentoring & Education: Module Generators This directory contains skills for the "Creation" phase of the teaching lifecycle. Learning Path Generator : Creates the 30,000-foot view of a student's journey. Class Session Planner : Breaks modules into minute-by-minute lesson plans. Project Generator : Creates professional-grade projects to test student skills. Use Cases New Course Development : Rapidly scaffold a curriculum for a new technology. Bootcamp Customization : Tailor a standard learning pat...
|
61 |
| 17667 | speckit-tasks | dceoy/speckit-agent-skills |
Spec Kit Tasks Skill When to Use The implementation plan is ready and you need a dependency-ordered task list. Inputs specs/<feature>/plan.md and specs/<feature>/spec.md Optional artifacts: data-model.md , contracts/ , research.md , quickstart.md Any user constraints or priorities from the request If the plan is missing, ask the user to run speckit-plan first. Workflow Setup : Run .specify/scripts/bash/check-prerequisites.sh --json from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. Al...
|
61 |
| 17668 | specification-writing | epicenterhq/epicenter |
Specification Writing Follow writing-voice for prose sections. A specification gives an agent (or human) the context they need to implement a feature autonomously. The goal is NOT to describe everything exhaustively; it's to provide enough initial context that the implementer can do their own research and make informed decisions. Note : This guide uses [PLACEHOLDER] markers for content you must fill in. Code blocks show templates; replace all bracketed content with your feature's details. The Co...
|
61 |
| 17669 | scheduled-jobs | groeimetai/snow-flow |
Scheduled Jobs automate recurring tasks, batch processing, and maintenance operations. Job Types | Scheduled Script Execution | sysauto_script | Run custom scripts | Report Scheduler | sysauto_report | Generate and email reports | Table Cleaner | sys_auto_flush | Delete old records | LDAP Refresh | ldap_server_config | Sync LDAP data | Discovery | discovery_schedule | Network discovery Scheduled Script Execution (ES5) Basic Scheduled Job ``` // Table: sysauto_script //...
|
61 |
| 17670 | umbraco-sections | umbraco/umbraco-cms-backoffice-skills |
Umbraco Sections What is it? Sections are top-level navigation items in the Umbraco backoffice that appear alongside default options like Content, Media, and Settings. They serve as a home for custom content and functionality, providing a blank canvas that can be extended with dashboards, sidebars, and section views. Sections require permission configuration for user groups to access them. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbrac...
|
60 |
| 17671 | app-router | davepoon/buildwithclaude |
Next.js App Router Patterns Overview The App Router is Next.js's file-system based router built on React Server Components. It uses a app/ directory structure where folders define routes and special files control UI behavior. Core File Conventions Route Files Each route segment is defined by a folder. Special files within folders control behavior: File Purpose page.tsx Unique UI for a route, makes route publicly accessible layout.tsx Shared UI wrapper, preserves state across navigations load...
|
60 |
| 17672 | r-econometrics | meleantonio/awesome-econ-ai-stuff |
R Econometrics Purpose This skill helps economists run rigorous econometric analyses in R, including Instrumental Variables (IV), Difference-in-Differences (DiD), and Regression Discontinuity Design (RDD). It generates publication-ready code with proper diagnostics and robust standard errors. When to Use Running causal inference analyses Estimating treatment effects with panel data Creating publication-ready regression tables Implementing modern econometric methods (two-way fixed effects, event ...
|
60 |
| 17673 | okx-trading | jasonviipers/okx-trading-skill |
OKX Provider Broker Skill Use this workflow when editing src/providers/okx/* . 1. Load only needed references For SDK usage patterns and method names, read references/okx-sdk-usage.md . For error-to-action mapping, read references/okx-error-map.md . For full source context, consult .trae/okx-api-llm.txt only for missing details. 2. Keep architecture compatibility Preserve compatibility with src/providers/types.ts ( BrokerProvider , MarketDataProvider , OptionsProvider ). Put OKX-specific expande...
|
60 |
| 17674 | strategy-expert | shipshitdev/library |
Content Strategy Expert Overview This skill enables Claude to assist users with comprehensive content strategy tasks including building customer personas from analytics data, conducting competitive content analysis, planning content calendars, managing research-to-content workflows, and ensuring brand voice consistency across all content. When to Use This Skill This skill activates automatically when users: Ask about content strategy or strategic planning Request help building personas or de...
|
60 |
| 17675 | b2c-sandbox | salesforcecommercecloud/b2c-developer-tooling |
B2C Sandbox Skill Only create or delete sandboxes when explicitly requested. Always confirm destructive actions. Use the b2c CLI plugin to manage Salesforce B2C Commerce On-demand sandboxes (ODS). Only create or delete a sandbox if explicitly asked as this may be a billable or destructible action. Tip: If b2c is not installed globally, use npx @salesforce/b2c-cli instead (e.g., npx @salesforce/b2c-cli sandbox list ). Alias: The ods prefix is still supported as a backward-compatible alias (e.g., ...
|
60 |
| 17676 | design-tokens | laurigates/claude-plugins |
This skill generates the foundational design tokens for a project. Run this after the design brief and before building any components. Every component built after this references these tokens instead of hardcoding values. Example prompts "Set up design tokens for this project" "Generate a token system based on Dieter Rams" "I need a spacing scale and color palette before I start building" "Create tokens that match our brief" Process Check what already exists. Before generating anything, scan the...
|
60 |
| 17677 | convex-performance-patterns | fluid-tools/claude-skills |
Convex Performance Patterns Overview Convex is designed for performance, but requires specific patterns to achieve optimal results. This skill covers denormalization strategies, index design, avoiding common performance pitfalls, and handling concurrency with OCC (Optimistic Concurrency Control). TypeScript: NEVER Use any Type CRITICAL RULE: This codebase has @typescript-eslint/no-explicit-any enabled. Using any will cause build failures. When to Use This Skill Use this skill when: Queries...
|
60 |
| 17678 | more-vaults | tradingstrategy-ai/web3-ethereum-defi |
Add more vaults to protocol This skill guides you through adding more smart contract types to the existing vaults. Required inputs Before starting, gather the following information from the user: Vault protocol name: The exiting vault protocol in the codebase Vault class name: What is the Python class name we use for this vault smart contract type Vault smart contract address - The address of an example vault contract on a blockchain Chain - Which blockchain (Ethereum, Arbitrum, Base, etc.) ...
|
60 |
| 17679 | wechat-article-maker | alpha-hecoding/awesome-skills |
微信公众号文章创作与发布 语言 匹配用户语言 :使用用户所用的语言进行回应。用户用中文则用中文回应,用英文则用英文回应。 目录结构 wechat-article-maker/ ├── scripts/ TypeScript 源文件 │ ├── wechat-api.ts API 发布逻辑 │ ├── wechat-article.ts 浏览器发布逻辑 │ ├── wechat-browser.ts 图文发布逻辑 │ ├── image-utils.ts 图片处理工具(sharp 集成) │ ├── generate-cover.ts 封面生成逻辑 │ ├── md-to-wechat.ts Markdown 转换逻辑 │ ├── ensure-deps.ts 依赖自动安装 │ └── md/ Markdown 渲染引擎 │ ├── render.ts │ ├── themes/ ...
|
60 |
| 17680 | figma-use | dannote/figma-use |
use_figma — Figma Plugin API Skill Use the use_figma tool to execute JavaScript in Figma files via the Plugin API. All detailed reference docs live in references/ . Always pass skillNames: "figma-use" when calling use_figma . This is a logging parameter used to track skill usage — it does not affect execution. If the task involves building or updating a full page, screen, or multi-section layout in Figma from code , also load figma-generate-design . It provides the workflow for discovering desig...
|
60 |
| 17681 | ai-llm | vasilyu1983/ai-agents-public |
LLM Development & Engineering — Complete Reference Build, evaluate, and deploy LLM systems with modern production standards. This skill covers the full LLM lifecycle: Development: Strategy selection, dataset design, instruction tuning, PEFT/LoRA fine-tuning Evaluation: Automated testing, LLM-as-judge, metrics, rollout gates Deployment: Serving handoff, latency/cost budgeting, reliability patterns (see ai-llm-inference) Operations: Quality monitoring, change management, incident response (see ...
|
60 |
| 17682 | api-development-expert | oimiragieo/agent-studio |
Api Development Expert When designing REST APIs, follow these core architectural principles: Resource-Oriented Design Use nouns for resources (plural form): /users, /products, /orders Avoid verbs in URIs: ❌ /getUsers, /createProduct Structure hierarchically: /users/{userId}/orders (orders belonging to a user) Use lowercase with hyphens: /product-details not /productdetails No trailing slashes: /users not /users/ HTTP Methods (Verbs with Purpose) GET - Retrieve resources (idempotent & safe, ...
|
60 |
| 17683 | umbraco-dynamic-root | umbraco/umbraco-cms-backoffice-skills |
Umbraco Dynamic Root What is it? Dynamic Roots allow content pickers to have a starting point (origin) that is determined dynamically rather than being a fixed node. This includes two extension types: Dynamic Root Origin : Defines where the picker starts (e.g., current page, site root, nearest ancestor of type) Dynamic Root Query Step : Defines navigation steps from the origin (e.g., find nearest ancestor, get children of type) These enable flexible content picker configurations that adapt based...
|
60 |
| 17684 | orchestrator | i9wa4/dotfiles |
Orchestrator Skill You are the Orchestrator (coordinator). You do NOT execute tasks yourself. Delegate execution to Worker/Subagent. NOTE: postman daemon handles all message delivery automatically. Role constraints and communication paths are defined in postman config. 1. Immediate Actions When orchestrator skill is invoked: Detect task type from user message Start appropriate workflow Keyword Workflow plan, design Plan review Review code, implement Code pr, pull request PR 2. Subagent Execution...
|
60 |
| 17685 | gmail | vm0-ai/vm0-skills |
Gmail Gmail is a free email service provided by Google. It's widely used by individuals and businesses for sending, receiving, and organizing emails. Official docs: https://developers.google.com/gmail/api Gmail Overview Email Attachment Draft Label Thread Working with Gmail This skill uses the Membrane CLI to interact with Gmail. Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing. Install the CLI Install the...
|
60 |
| 17686 | shared | rshankras/claude-code-apple-skills |
Shared References This directory contains shared reference documents used by multiple skills: validation-contract.md - Verification requirements for accepting spawned work references/claude-code-latest-features.md - Claude Code feature contract (slash commands, agent isolation, hooks, settings) references/backend-claude-teams.md - Concrete examples for Claude native teams ( TeamCreate + SendMessage ) references/backend-codex-subagents.md - Concrete examples for Codex CLI and Codex sub-agents ref...
|
60 |
| 17687 | slack | i9wa4/dotfiles |
Slack Automation Interact with Slack workspaces to check messages, extract data, and automate common tasks. Quick Start Connect to an existing Slack browser session or open Slack: Connect to existing session on port 9222 (typical for already-open Slack) agent-browser connect 9222 Or open Slack if not already running agent-browser open https://app.slack.com Then take a snapshot to see what's available: agent-browser snapshot -i Core Workflow Connect/Navigate : Open or connect to Slack Snapshot ...
|
60 |
| 17688 | market-research | majesticlabs-dev/majestic-marketplace |
Market Research Produce research that supports decisions, not research theater. When to Activate researching a market, category, company, investor, or technology trend building TAM/SAM/SOM estimates comparing competitors or adjacent products preparing investor dossiers before outreach pressure-testing a thesis before building, funding, or entering a market Research Standards Every important claim needs a source. Prefer recent data and call out stale data. Include contrarian evidence and downside...
|
60 |
| 17689 | initializing-memory | letta-ai/letta-code |
Memory Initialization Request The user has requested that you initialize or reorganize your memory. Your memory is a filesystem — files under system/ are rendered in-context every turn, while all file metadata is always visible in the filesystem tree. Files outside system/ (e.g. reference/ , history/ ) are accessible via tools when needed. Autonomous Mode If you are running as a background subagent (you cannot use AskUserQuestion): Default to standard research depth (~5-20 tool calls) Detect use...
|
60 |
| 17690 | fake-driven-testing | dagster-io/erk |
Fake-Driven Testing Architecture for Python Use this skill when : Writing tests, fixing bugs, adding features, or modifying gateway layers in Python projects. Prerequisites : For Python code standards, load the dignified-python-313 skill first. This skill focuses on testing architecture, not Python syntax. Overview This skill provides a defense-in-depth testing strategy with five layers for Python applications: ┌─────────────────────────────────────────┐ │ Layer 5: Business Logic Integration Te...
|
60 |
| 17691 | commit | paulrberg/agent-skills |
Sentry Commit Messages Follow these conventions when creating commits for Sentry projects. Prerequisites Before committing, always check the current branch: git branch --show-current If you're on main or master , you MUST create a feature branch first — unless the user explicitly asked to commit to main. Do not ask the user whether to create a branch; just proceed with branch creation. The create-branch skill will still propose a branch name for the user to confirm. Use the create-branch skill t...
|
60 |
| 17692 | slides-generator | bmad-labs/skills |
slides-generator Create Hummingbot-branded presentation slides in PDF format from markdown content. Features two-column layouts and Mermaid diagram rendering for technical architecture and flowcharts. Workflow Step 1: Get Markdown Content Ask the user to provide a markdown file or paste markdown content. The content should follow this format: Presentation Title 1. First Slide Title Content for the first slide. Can include: - Bullet points - Bold text and * italic text * - Code blocks 2. Sec...
|
60 |
| 17693 | seo-keyword-cluster-builder | secondsky/claude-skills |
Seo Keyword Cluster Builder Group related keywords into topic clusters. Create content hub architecture recommendations and internal linking strategies. Instructions You are an expert at SEO and content architecture. Build topic clusters, plan pillar content, and design internal linking strategies for maximum search visibility. Output Format Seo Keyword Cluster Builder Output Generated: {timestamp} --- Results [Your formatted output here] --- Recommendations [Actionable next steps]...
|
60 |
| 17694 | sqlmodel-expert | bilalmk/todo_correct |
Advanced SQLModel patterns and comprehensive Alembic migrations for production databases. Quick Start Define a Basic Model ``` from sqlmodel import Field, SQLModel from typing import Optional from datetime import datetime class Task(SQLModel, table=True): id: Optional[int] = Field(default=None, primary_key=True) title: str = Field(index=True) description: Optional[str] = None completed: bool = Field(default=False) created_at: datetime = Field(default_factory=datetime.ut...
|
60 |
| 17695 | chrome-devtools | secondsky/claude-skills |
Chrome DevTools Agent Overview A specialized skill for controlling and inspecting a live Chrome browser. This skill leverages the chrome-devtools MCP server to perform a wide range of browser-related tasks, from simple navigation to complex performance profiling. When to Use Use this skill when: Browser Automation : Navigating pages, clicking elements, filling forms, and handling dialogs. Visual Inspection : Taking screenshots or text snapshots of web pages. Debugging : Inspecting console messag...
|
60 |
| 17696 | b2c-metadata | salesforcecommercecloud/b2c-developer-tooling |
Metadata Skill This skill guides you through working with site metadata XML for Salesforce B2C Commerce, including custom attributes, custom objects, and site preferences. Overview Metadata defines the structure of your B2C Commerce data: Metadata Type Purpose System Object Extensions Add custom attributes to Products, Orders, Customers, etc. Custom Objects Define entirely new data types Site Preferences Site-specific configuration values Site Archive Structure Metadata is organized in site arch...
|
60 |
| 17697 | fastmcp-server | davila7/claude-code-templates |
FastMCP 3.0 Server Development Complete reference for building production-ready MCP (Model Context Protocol) servers with FastMCP 3.0 - the fast, Pythonic framework for connecting LLMs to tools and data. When to use this skill Use FastMCP Server when: Creating a new MCP server in Python Adding tools, resources, or prompts to an MCP server Implementing authentication (OAuth, OIDC, token verification) Setting up middleware for logging, rate limiting, or authorization Configuring providers (local, ...
|
60 |
| 17698 | revealjs | kziemski/revealjs-skill |
Reveal.js Presentations Create HTML presentations using reveal.js. No build step required - just open the HTML in a browser. What You Create A reveal.js presentation consists of: HTML file - Contains slides and loads reveal.js from CDN CSS file - Custom styles for layouts, colors, typography, and components Design Principles CRITICAL: Before creating any presentation, analyze the content and choose appropriate design elements: Consider the subject matter: What is this presentation about? W...
|
60 |
| 17699 | walkthrough | alexanderop/walkthrough |
No SKILL.md available for this skill. View on GitHub
|
60 |
| 17700 | sqlserver-expert | fabriciofs/mcp-postgres |
SQL Server Expert You are a DBA and developer expert in Microsoft SQL Server. T-SQL Advanced CTEs (Common Table Expressions) WITH RankedUsers AS ( SELECT Id , Name , Email , ROW_NUMBER ( ) OVER ( PARTITION BY Department ORDER BY HireDate ) AS RowNum FROM Users ) SELECT * FROM RankedUsers WHERE RowNum = 1 ; Window Functions SELECT OrderId , OrderDate , Amount , SUM ( Amount ) OVER ( ORDER BY OrderDate ) AS RunningTotal , LAG ( Amount ) OVER ( ORDER BY OrderDate ) AS PreviousAmount , AVG ( Amount ...
|
60 |