Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
16251 review-seo-audit heyvhuang/ship-faster
SEO Audit You are an expert in search engine optimization. Your goal is to identify SEO issues and provide actionable recommendations to improve organic search performance. Initial Assessment Before auditing, understand: Site Context What type of site? (SaaS, e-commerce, blog, etc.) What's the primary business goal for SEO? What keywords/topics are priorities? Current State Any known issues or concerns? Current organic traffic level? Recent changes or migrations? Scope Full site audit or specifi...
 46
16252 helius raintree-technology/claude-starter
Helius — Build on Solana You are an expert Solana developer building with Helius's infrastructure. Helius is Solana's leading RPC and API provider, with demonstrably superior speed, reliability, and global support. You have access to the Helius MCP server which gives you live tools to query the blockchain, manage webhooks, stream data, send transactions, and more. Prerequisites 1. Helius MCP Server CRITICAL : Check if Helius MCP tools are available (e.g., getBalance , getAssetsByOwner ). If NOT ...
 46
16253 motion-framer freshtechbro/claudedesignskills
Motion & Framer Motion Overview Motion (formerly Framer Motion) is a production-ready animation library for React and JavaScript that enables declarative, performant animations with minimal code. It provides motion components that wrap HTML elements with animation superpowers, supports gesture recognition (hover, tap, drag, focus), and includes advanced features like layout animations, exit animations, and spring physics. When to use this skill: Building interactive UI components (buttons, cards...
 46
16254 cost optimizer eddiebe147/claude-settings
Cost Optimizer Analyze spending patterns and identify opportunities to reduce costs without sacrificing quality or performance. Turn expense data into actionable savings strategies. Core Workflows Workflow 1: Spend Analysis Gather Data - Collect all expense data Categorize - Group spending by type and vendor Trend Analysis - Identify patterns over time Benchmark - Compare to industry standards Identify Opportunities - Flag areas for reduction Workflow 2: Vendor Optimization Vendor Review - Audit...
 46
16255 cloudflare heyvhuang/ship-faster
Cloudflare Platform Skill Consolidated skill for building on the Cloudflare platform. Use decision trees below to find the right product, then load detailed references. Authentication (Required Before Deploy) Verify auth before wrangler deploy , wrangler pages deploy , or npm run deploy : npx wrangler whoami Shows account if authenticated Not authenticated? → references/wrangler/auth.md Interactive/local: wrangler login (one-time OAuth) CI/CD: Set CLOUDFLARE_API_TOKEN env var Quick Decision Tre...
 46
16256 zhy-wechat-publish zhylq/yuan-skills
微信公众号草稿箱发布技能 本技能用于将文章发布到微信公众号草稿箱。脚本仅依赖 Node.js 内置模块；自动封面生成步骤会复用现有 bun 生图脚本。 前置条件 Node.js >= 16 若要自动生成封面，还需本机可用 bun 技能目录下 .env 至少包含： WECHAT_APP_ID=你的公众号AppID WECHAT_APP_SECRET=你的公众号AppSecret WECHAT_DEFAULT_THUMB_MEDIA_ID=默认封面图media_id（可选） WECHAT_DEFAULT_AUTHOR=AI源来如此（可选） 运行机器公网 IP 已加入公众号后台 IP 白名单 自动生成封面时，需保证 zhy-article-illustrator 的生图环境可用 安装说明 本 skill 适合与 npx skills add ... --skill zhy-wechat-publish 一起安装到 OpenCode、Claude Code 等支持 SKILL.md 的 agent 工具中。 安装后请在本地 skill 目录手动创建 .env ，不要将真实凭据提交回仓库。 脚本...
 46
16257 materialize-docs materializeinc/agent-skills
Materialize Documentation This skill provides comprehensive documentation for Materialize, a streaming database for real-time analytics. How to Use This Skill When a user asks about Materialize: For SQL syntax/commands : Read files in the sql/ directory For core concepts : Read files in the concepts/ directory For data ingestion : Read files in the ingest-data/ directory For transformations : Read files in the transform-data/ directory Documentation Sections Administrations Usage (Self-Managed) ...
 46
16258 sentry vm0-ai/vm0-skills
Sentry (Read-only Observability) Quick start If not already authenticated, ask the user to provide a valid SENTRY_AUTH_TOKEN (read-only scopes such as project:read , event:read ) or to log in and create one before running commands. Set SENTRY_AUTH_TOKEN as an env var. Optional defaults: SENTRY_ORG , SENTRY_PROJECT , SENTRY_BASE_URL . Defaults: org/project {your-org} / {your-project} , time range 24h , environment prod , limit 20 (max 50). Always call the Sentry API (no heuristics, no caching). I...
 46
16259 excalidraw ooiyeefei/ccc
Excalidraw Subagent Delegation Overview Core principle: Main agents NEVER read Excalidraw files directly. Always delegate to subagents to isolate context consumption. Excalidraw files are JSON with high token cost but low information density. Single files range from 4k-22k tokens (largest can exceed read tool limits). Reading multiple diagrams quickly exhausts context budget (7 files = 67k tokens = 33% of budget). The Problem Excalidraw JSON structure: Each shape has 20+ properties (x, y, w...
 46
16260 angular-directives kobolden/angular-skills
Angular Directives Create custom directives for reusable DOM manipulation and behavior in Angular v20+. Attribute Directives Modify the appearance or behavior of an element: import { Directive, input, effect, inject, ElementRef } from '@angular/core'; @Directive({ selector: '[appHighlight]', }) export class HighlightDirective { private el = inject(ElementRef<HTMLElement>); // Input with alias matching selector color = input('yellow', { alias: 'appHighlight' }); constructor()...
 46
16261 state-management asyrafhussin/agent-skills
State Management When to use this skill 전역 상태 필요: 여러 컴포넌트가 같은 데이터 공유 Props Drilling 문제: 5단계 이상 props 전달 복잡한 상태 로직: 인증, 장바구니, 테마 등 상태 동기화: 서버 데이터와 클라이언트 상태 동기화 Instructions Step 1: 상태 범위 결정 로컬 vs 전역 상태를 구분합니다. 판단 기준: 로컬 상태: 단일 컴포넌트에서만 사용 폼 입력값, 토글 상태, 드롭다운 열림/닫힘 useState, useReducer 사용 전역 상태: 여러 컴포넌트에서 공유 사용자 인증, 장바구니, 테마, 언어 설정 Context API, Redux, Zustand 사용 예시: // ✅ 로컬 상태 (단일 컴포넌트) function SearchBox() { const [query, setQuery] = useState(''); const [isOpen, setIsOpen] = useState(fa...
 46
16262 ios-swift teachingai/full-stack-skills
Use this skill whenever the user wants to: - [待完善：根据具体工具添加使用场景] How to use this skill [待完善：根据具体工具添加使用指南] Best Practices [待完善：根据具体工具添加最佳实践] Keywords [待完善：根据具体工具添加关键词]
 46
16263 coderabbit paulrberg/agent-skills
CodeRabbit AI-powered code review for pull requests and local changes. Quick Navigation Task Reference Install & run CLI cli-usage.md Configure .coderabbit.yaml configuration.md Supported tools (40+ linters) tools.md Git platform setup platforms.md PR commands (@coderabbitai) pr-commands.md Claude/Cursor/Codex workflow agent-integration.md Triage findings triage.md Fix single issue fix.md Reporting & metrics end-to-end-workflow.mdreporting--metrics End-to-end workflow end-to-end-workflow.md Wi...
 46
16264 react-skills llama-farm/llamafarm
React Skills for LlamaFarm Designer Best practices and patterns for React 18 development in the Designer subsystem. Tech Stack React 18.2 with StrictMode TypeScript 5.2+ for type safety TanStack Query v5 for server state management React Router v7 for client-side routing TailwindCSS with tailwind-merge and clsx for styling Radix UI primitives for accessible components Vite for build tooling Vitest + React Testing Library for testing Directory Structure designer/src/ api/ API servic...
 46
16265 test-first s-hiraoku/synapse-a2a
Test-First Development Skill Test-First Development (TDD) ensures that code is written to satisfy specific, predefined requirements, leading to higher quality and better design. TDD Workflow Red : Write a failing test for a small piece of functionality. Green : Write the minimum amount of code required to make the test pass. Refactor : Clean up the code while ensuring the tests remain green. Test Design Principles 1. Comprehensive Coverage Normal Cases : Test the expected "happy path" behavior. ...
 46
16266 deep-research cklxx/elephant.ai
Deep Research Core System Instructions Purpose: Deliver citation-backed, verified research reports through 8-phase pipeline (Scope → Plan → Retrieve → Triangulate → Synthesize → Critique → Refine → Package) with source credibility scoring and progressive context management. Context Strategy: This skill uses 2025 context engineering best practices: Static instructions cached (this section) Progressive disclosure (load references only when needed) Avoid "loss in the middle" (critical info at start...
 46
16267 archive-conversation nweii/agent-stuff
AI Conversation Archival Summary Create an archival summary of an AI conversation that captures its intellectual journey, key insights, or technical work session logs. Document either how thinking evolved throughout the discussion or the specific actions and technical decisions made during a work session. Deep Analysis Requirements Conduct a thorough analysis of the entire conversation: Read through completely first, identifying all conceptual threads, task sequences, and transitions Note pa...
 46
16268 github-repo-hunter breverdbidder/life-os
GitHub Repository Hunter Autonomous agent for discovering, evaluating, and integrating relevant GitHub repositories into BidDeed.AI and Life OS ecosystems. Mission Hunt GitHub for open-source projects that could enhance: BidDeed.AI - Foreclosure auction intelligence (scrapers, ML models, document processing, workflow automation) Life OS - Productivity, ADHD management, swimming analytics, dual-timezone coordination Core Workflow 1. Discovery Phase Search GitHub API using domain-specific keywords...
 46
16269 alicloud-ai-multimodal-qvq-test cinience/alicloud-skills
Category: test Minimal Viable Test Goals Validate that the QVQ skill includes the visual reasoning models and sample payload. Prerequisites Target skill: skills/ai/multimodal/alicloud-ai-multimodal-qvq Recommended check python skills/ai/multimodal/alicloud-ai-multimodal-qvq/scripts/prepare_qvq_request.py \ --output output/alicloud-ai-multimodal-qvq/request.json
 46
16270 canonical-format-checker panaversity/agentfactory
Canonical Format Checker Overview Prevent format drift by verifying content follows authoritative canonical sources. When teaching a pattern that exists elsewhere in the platform (skills, subagents, ADRs, etc.), this skill ensures the taught format matches the canonical source. Why this matters : The Chapter 14 format drift failure occurred because the lesson taught skill format differently from Chapter 5 (canonical source). Students learned incorrect patterns that contradicted earlier chapters....
 46
16271 research synthesizer eddiebe147/claude-settings
Research Synthesizer Synthesize insights from multiple research sources into cohesive analysis When to Use This Skill Use this skill when you need to: Analyze data and extract insights Conduct thorough investigation Synthesize complex information Not recommended for: Tasks requiring creative content generation business operations Quick Reference Action Command/Trigger Create research synthesizer research synthesis Review and optimize review research synthesizer Get best practices research synthe...
 46
16272 hitpay hit-pay/agent-skills
Payment gateway integration for APAC businesses using Next.js and JavaScript/TypeScript. Supports card payments via redirect and QR-based payments (PayNow, GrabPay, etc.) via embedded QR codes. When to Apply Reference this skill when: - Integrating HitPay payment gateway - Creating payment checkout flows - Implementing QR code payments (PayNow, GrabPay, ShopeePay) - Handling payment webhooks - Processing refunds Step 1: Determine Payment Methods Ask which payment methods the customer ...
 46
16273 git-expert cin12211/orca-q
Git Expert You are an expert in Git version control with deep knowledge of advanced workflows, branching strategies, collaboration patterns, and best practices. You help teams manage code efficiently and resolve complex version control issues. Core Expertise Essential Git Commands Basic Operations: Initialize repository git init git clone https://github.com/user/repo.git Check status and differences git status git diff Unstaged changes git diff --staged Staged changes git diff main .. .featu...
 46
16274 cto lotosbin/claude-skills
No SKILL.md available for this skill. View on GitHub
 46
16275 elasticsearch-index-manager jeremylongshore/claude-code-plugins-plus-skills
Elasticsearch Index Manager Purpose This skill provides automated assistance for elasticsearch index manager tasks within the DevOps Advanced domain. When to Use This skill activates automatically when you: Mention "elasticsearch index manager" in your request Ask about elasticsearch index manager patterns or best practices Need help with advanced devops skills covering kubernetes, terraform, advanced ci/cd, monitoring, and infrastructure as code. Capabilities Provides step-by-step guidance ...
 46
16276 ld-permissions lightdash/lightdash
Permissions & Authorization Guide This skill helps you work with Lightdash's CASL-based permissions system, including scopes, custom roles, and authorization enforcement. What do you need help with? Add a new scope/permission - Step-by-step guide to add a new permission Debug a permission issue - Troubleshoot why a user can't access something Understand the permission flow - Learn how permissions work end-to-end Work with custom roles - Create or modify custom roles with specific scopes Quick Re...
 46
16277 workflow-test-fix catlog22/claude-code-workflow
Workflow Test Fix Unified test-fix orchestrator that combines test planning generation (Phase 1-4) with iterative test-cycle execution (Phase 5) into a single end-to-end pipeline. Creates test sessions with progressive L0-L3 test layers, generates test tasks, then executes them with adaptive fix cycles until pass rate >= 95% or max iterations reached. Architecture Overview ┌───────────────────────────────────────────────────────────────────────────┐ │ Workflow Test Fix Orchestrator (SKILL.md) ...
 46
16278 question-refiner liangdabiao/claude-code-stock-deep-research-agent
Question Refiner Role You are a Deep Research Question Refiner specializing in crafting, refining, and optimizing prompts for deep research. Your primary objectives are: Ask clarifying questions first to ensure full understanding of the user's needs, scope, and context Generate structured research prompts that follow best practices for deep research Eliminate the need for external tools (like ChatGPT) - everything is done within Claude Code Core Directives Do Not Answer the Research Query Dire...
 46
16279 sports-trivia-builder onewave-ai/claude-skills
Sports Trivia Builder Generate sports trivia questions by sport/era/difficulty. Multiple formats with obscure stats, fun facts, pub quiz ready content. Instructions You are an expert sports historian and trivia creator. Generate engaging trivia questions across sports, eras, and difficulty levels. Include: multiple choice, true/false, fill-in-blank formats, obscure stats, fun facts, answer explanations with context, and difficulty ratings. Output Format Sports Trivia Builder Output Generat...
 46
16280 nushell-usage ypares/agent-skills
Nushell Usage Patterns Critical Distinctions Pipeline Input vs Parameters CRITICAL: Pipeline input ($in) is NOT interchangeable with function parameters! ❌ WRONG - treats $in as first parameter def my-func [list: list, value: any] { $list | append $value } ✅ CORRECT - declares pipeline signature def my-func [value: any]: list -> list { $in | append $value } Usage [1 2 3] | my-func 4 Works correctly my-func [1 2 3] 4 ERROR! my-func doesn't take positional params This applie...
 46
16281 commit-message junoh-moon/skills
Commit Message Convention Based on the following git diff of staged changes, generate a conventional commit message with a clear subject line (max 72 chars) and body (wrapped at 72 chars). The message should clearly explain what changed and why. To create a commit message, focus on staged files ONLY. Run git diff --cached to see the changes. Sometimes, you have to git add files by yourself -- pre-commit fail, unstaged files, or manual edit by a user. In this case, NEVER USE git add -u or git ad...
 45
16282 outlier-detective dkyazzentwatwa/chatgpt-skills
Detect anomalies and outliers in numeric data using multiple methods. Features - Statistical Methods: Z-score, IQR, Modified Z-score - ML Methods: Isolation Forest, LOF, DBSCAN - Visualization: Box plots, scatter plots - Multi-Column: Analyze multiple variables - Reports: Detailed outlier reports - Flexible Thresholds: Configurable sensitivity Quick Start ``` from outlier_detective import OutlierDetective detective = OutlierDetective() detective.load_csv("sales_data.csv") Detect ou...
 45
16283 cursor-agent-supervisor ypares/agent-skills
Agent Supervisor You can start subagents (e.g. to work on a specific JJ revision) with: Create a conversation with a sub-agent: cursor-agent --print --model <model-name> create-chat Prints a conversation uuid Give a task to the sub-agent: (command will finish when sub-agent is done) cursor-agent --print --resume <conversation-uuid> "...description of the subagent's task..." Model Selection cursor-agent --print --model unknown-model will print an error that will list available models. Un...
 45
16284 android_ui_verification sickn33/antigravity-awesome-skills
Android UI Verification Skill This skill provides a systematic approach to testing React Native applications on an Android emulator using ADB commands. It allows for autonomous interaction, state verification, and visual regression checking. When to Use Verifying UI changes in React Native or Native Android apps. Autonomous debugging of layout issues or interaction bugs. Ensuring feature functionality when manual testing is too slow. Capturing automated screenshots for PR documentation. 🛠 Prereq...
 45
16285 risk assessor eddiebe147/claude-settings
Risk Assessor The Risk Assessor skill helps teams proactively identify, analyze, prioritize, and mitigate project risks before they become problems. It uses systematic risk management frameworks to surface threats, evaluate their likelihood and impact, and create actionable mitigation strategies. This skill excels at conducting pre-mortem exercises, creating risk registers, assessing probability and impact, developing contingency plans, and establishing early warning indicators to catch risks be...
 45
16286 figma-prototyping dylantarre/animation-principles
Implement all 12 Disney animation principles using Figma's prototyping and Smart Animate features. 1. Squash and Stretch - Create two frames: normal and squashed states - Scale element: `width: 120%`, `height: 80%` - Connect with Smart Animate - Use "Ease In and Out" timing ``` Frame 1: Circle 100x100 Frame 2: Circle 120x80 (squashed) Interaction: Smart Animate, 150ms ``` 2. Anticipation Create 3 frames: - Idle - Starting position - Anticipate - Wind-up (move opposite to action) - ...
 45
16287 background-job-orchestrator erichowens/some_claude_skills
Background Job Orchestrator Expert in designing and implementing production-grade background job systems that handle long-running tasks without blocking API responses. When to Use ✅ Use for: Long-running tasks (email sends, report generation, image processing) Batch operations (bulk imports, exports, data migrations) Scheduled tasks (daily digests, cleanup jobs, recurring reports) Tasks requiring retry logic (external API calls, flaky operations) Priority-based processing (premium users firs...
 45
16288 code-documentation-generator dengineproblem/agents-monorepo
Эксперт по созданию качественной документации кода. Основные принципы - Clarity > Sophistication — ясность важнее сложности - Progressive disclosure — от общего к деталям - Consistency — единообразие форматирования - Accuracy — синхронизация с кодом - Accessibility — для разных уровней разработчиков JSDoc (JavaScript/TypeScript) ``` / * Calculates the total price including tax and discounts. * * @param {number} basePrice - The original price before modifications * @param {number} t...
 45
16289 systematic-debugging zenobi-us/dotfiles
Systematic Debugging Overview Random fixes waste time and create new bugs. Quick patches mask underlying issues. Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure. Violating the letter of this process is violating the spirit of debugging. The Iron Law NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST If you haven't completed Phase 1, you cannot propose fixes. When to Use Use for ANY technical issue: Test failures Bugs in production Unexpected behavior Perfor...
 45
16290 release-please-configuration laurigates/claude-plugins
Expert knowledge for configuring Google's release-please for automated releases. Core Files | `release-please-config.json` | Package configuration, changelog sections, extra-files | `.release-please-manifest.json` | Current versions for each package | `.github/workflows/release-please.yml` | GitHub Actions workflow Monorepo Configuration Critical Settings for Monorepos ``` { "$schema": "https://raw.githubusercontent.com/googleapis/release-please/main/schemas/config.json", "in...
 45
16291 deep-research heyvhuang/ship-faster
Deep Research Core System Instructions Purpose: Deliver citation-backed, verified research reports through 8-phase pipeline (Scope → Plan → Retrieve → Triangulate → Synthesize → Critique → Refine → Package) with source credibility scoring and progressive context management. Context Strategy: This skill uses 2025 context engineering best practices: Static instructions cached (this section) Progressive disclosure (load references only when needed) Avoid "loss in the middle" (critical info at start...
 45
16292 domain-cli actionbook/rust-skills
CLI Domain Layer 3: Domain Constraints Domain Constraints → Design Implications Domain Rule Design Constraint Rust Implication User ergonomics Clear help, errors clap derive macros Config precedence CLI > env > file Layered config loading Exit codes Non-zero on error Proper Result handling Stdout/stderr Data vs errors eprintln! for errors Interruptible Handle Ctrl+C Signal handling Critical Constraints User Communication RULE: Errors to stderr, data to stdout WHY: Pipeable output, scriptabilit...
 45
16293 styling-system mgd34msu/goodvibes-plugin
Resources scripts/ validate-styling.sh references/ styling-comparison.md Styling System This skill guides you through CSS architecture decisions and implementation using GoodVibes precision tools. Use this workflow when setting up styling infrastructure, creating design systems, or implementing theming and responsive patterns. When to Use This Skill Load this skill when: Setting up a new project's styling infrastructure Choosing between Tailwind, CSS Modules, CSS-in-JS, or vanilla CSS Implementi...
 45
16294 executing-plans guanyang/antigravity-skills
Executing Plans Overview Load plan, review critically, execute all tasks, report when complete. Announce at start: "I'm using the executing-plans skill to implement this plan." Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill. The Proce...
 45
16295 changelog railwayapp/railway-skills
Changelog Format specification for CHANGELOG.md based on Keep a Changelog 1.1.0. Language Requirement (Mandatory) All changelog content MUST be written in English. If source information is provided in another language, translate it to English. Do not mix languages within the same changelog. Quick Reference File Header Changelog All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this projec...
 45
16296 athlete-social-media-manager onewave-ai/claude-skills
Athlete Social Media Manager Create brand-safe content for athletes. Personal branding strategy, engagement optimization, crisis communication, sponsor integration. Instructions You are an expert athlete brand manager and social media strategist. Create: brand-safe content strategies, personal branding plans, engagement optimization tactics, crisis communication templates, sponsor integration ideas, and platform-specific content calendars. Output Format Athlete Social Media Manager Output ...
 45
16297 staging-mastery dylantarre/animation-principles
Staging Mastery The Clarity Principle Staging is the presentation of an idea so that it is unmistakably clear. Borrowed from theater, this principle addresses animation's core challenge: the audience has limited time to comprehend each moment. Poor staging creates confusion; masterful staging creates effortless understanding. Core Theory One Idea Per Moment: The eye cannot process competing focal points simultaneously. Every frame should have exactly one primary point of interest. Secondary e...
 45
16298 us-stock-analysis nicepkg/ai-workflow
US Stock Analysis Overview Perform comprehensive analysis of US stocks covering fundamental analysis (financials, business quality, valuation), technical analysis (indicators, trends, patterns), peer comparisons, and generate detailed investment reports. Fetch real-time market data via web search tools and apply structured analytical frameworks. Data Sources Always use web search tools to gather current market data: Primary Data to Fetch: Current stock price and trading data (price, volume, 52-w...
 45
16299 telegram himself65/finance-skills
📬 Telegram CLI Fast Telegram CLI for reading, searching, and sending messages. 🎯 When to Use Use this skill when the user: Asks to check Telegram messages or inbox Wants to search Telegram for a topic/keyword Wants to send a Telegram message or reply to one Asks about a Telegram group, contact, or chat Wants to see unread messages Needs to look up group members or admins Wants to mute/unmute a noisy chat or group Needs to kick/remove a user from a group Wants to export or sync chat history to fi...
 45
16300 vendor manager eddiebe147/claude-settings
Vendor Manager Expert vendor and supplier management system that helps you evaluate vendors, manage contracts, track performance, negotiate terms, and optimize procurement. This skill provides structured workflows for vendor selection, performance monitoring, and relationship management based on supply chain and procurement best practices. Effective vendor management reduces costs, mitigates risk, and ensures reliable supply. This skill helps you build strategic vendor relationships, hold suppli...
 45