███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 19751 | gitops-principles-skill | julianobarbosa/claude-code-skills |
Complete guide for implementing GitOps methodology in Kubernetes environments - the operational framework where Git is the single source of truth for declarative infrastructure and applications. What is GitOps? GitOps is a set of practices that uses Git repositories as the source of truth for defining the desired state of infrastructure and applications. An automated process ensures the production environment matches the state described in the repository. The OpenGitOps Definition (CNCF) G...
|
45 |
| 19752 | storage-function-structure | zenobi-us/dotfiles |
Each planning artifact type has its own directory: - `Prd/` for Product Requirements Documents - `Epic/` for Epics - `Spec/` for Specifications - `Story/` for User Stories - `Task/` for Tasks - `Decision/` for Decisions - `Research/` for Research Documents - `Retro/` for Retrospectives - Files within these directories are named using the format: `<short-hash>-<descriptive-title>.md` ``` Prd/ feca343-the-prd-title.md Epic/ 123e4567-an-epic-title.md Spec/ 89ab0123-a-spec-title.md...
|
45 |
| 19753 | team-chemistry-evaluator | onewave-ai/claude-skills |
Team Chemistry Evaluator Analyze roster fit and personality dynamics. Leadership assessment, role clarity, locker room culture, trade/signing impact. Instructions You are an expert in sports psychology and team dynamics. Evaluate: roster fit and compatibility, leadership structures, role clarity, playing time balance, locker room culture indicators, and predict trade/signing impact on team chemistry. Output Format Team Chemistry Evaluator Output Generated: {timestamp} --- Results [Your...
|
45 |
| 19754 | godot-platform-web | thedivergentai/gd-agentic-skills |
Platform: Web Browser API integration, LocalStorage persistence, and size optimization define web deployment. Available Scripts web_bridge_sync.gd Expert JavaScriptBridge helpers for browser API integration (persistence, analytics). NEVER Do in Web Development NEVER use FileAccess for saves — FileAccess.open("user://save.dat") on web? Browser sandbox blocks filesystem. Use JavaScriptBridge + localStorage. NEVER forget loading screen — 20MB wasm download with default load screen = user closes tab...
|
45 |
| 19755 | busirocket-core-conventions | busirocket/agents-skills |
Reusable, project-agnostic conventions designed to keep codebases scalable and easy for AI agents to navigate. When to Use Use this skill when: - Starting a new feature and deciding where code should live - Refactoring to improve maintainability - Enforcing “one-thing-per-file” discipline - Establishing naming/layout conventions and boundary rules Non-Negotiables (MUST) - Keep many small, focused files with explicit boundaries. - One exported symbol per file for your own modules (comp...
|
45 |
| 19756 | white paper author | eddiebe147/claude-settings |
White Paper Author Create authoritative, research-backed white papers that establish expertise, educate audiences, and drive high-quality leads. This skill helps you develop comprehensive documents that explore complex topics, present original research, or advocate for specific solutions. Whether you're building thought leadership, supporting enterprise sales cycles, or establishing industry credibility, this skill ensures your white papers are well-researched, professionally structured, and gen...
|
45 |
| 19757 | typescript-type-system | thebushidocollective/han |
Master TypeScript's type system features to write type-safe code. This skill focuses exclusively on TypeScript language capabilities. TypeScript Compiler ``` Type check without emitting files tsc --noEmit Type check with specific config tsc --noEmit -p tsconfig.json Show compiler version tsc --version Watch mode for development tsc --noEmit --watch ``` Strict Mode Configuration tsconfig.json strict mode options: ``` { "compilerOptions": { "strict": true, ...
|
45 |
| 19758 | gin-gonic | 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]
|
45 |
| 19759 | full-stack-bootstrap | terrylica/cc-skills |
Full Stack Bootstrap One-time bootstrap of the entire TTS + Telegram bot stack: Kokoro TTS engine (MLX-Audio on Apple Silicon), Telegram bot via BotFather, secrets management, environment configuration, and shell symlinks. Platform : macOS (Apple Silicon) When to Use This Skill First-time setup of the tts-telegram-sync plugin Reinstalling after a clean OS install or hardware migration Setting up a new machine with the full TTS + Telegram stack Recovering from a broken installation (run kokoro-in...
|
45 |
| 19760 | ui-validator | caomeiyouren/momei |
UI Validator Skill (UI 验证专家技能) 概述 (Overview) 本技能专注于所有涉及 UI(用户界面)改动的闭环验证。它通过驱动真实的浏览器环境,确保代码层面的修改在不同主题模式、屏幕尺寸及交互状态下均能正确呈现。 核心职责 (Core Responsibilities) 1. 开发环境自检 (Dev Server Pre-check) 在进行任何页面访问前,必须确保开发服务器 ( localhost:3000 ) 已处于活跃状态。 端口检查 :执行 Test-NetConnection -ComputerName localhost -Port 3000 (Windows) 或 lsof -i:3000 (POSIX) 检查端口。 自动启动 :若端口未启动,则异步执行 pnpm dev (设置 isBackground: true )并等待约 5-10 秒直至就绪。 避免重复 :若端口已占用,严禁再次启动服务器。 2. 浏览器自动化验证 (Browser Automation) 使用浏览器工具(如 Chrome MCP)进行多维检查。 页面访问 :导航至受影...
|
45 |
| 19761 | customer support reply | eddiebe147/claude-settings |
Customer Support Reply The Customer Support Reply skill helps you craft empathetic, effective responses to customer inquiries, issues, and complaints. Whether you're resolving a technical problem, handling a frustrated customer, providing product guidance, or managing a difficult situation, this skill ensures your responses are professional, helpful, and customer-focused. This skill understands that support responses can make or break customer relationships. They need to balance empathy with eff...
|
45 |
| 19762 | linear-relations | finesssee/linear-cli |
Issue Relations List relations linear-cli rel list LIN-123 Add relation linear-cli rel add LIN-1 -r blocks LIN-2 LIN-1 blocks LIN-2 linear-cli rel add LIN-1 -r related LIN-2 Related issues linear-cli rel add LIN-1 -r duplicate LIN-2 Duplicate Remove relation linear-cli rel remove LIN-1 -r blocks LIN-2 Parent/child linear-cli rel parent LIN-2 LIN-1 Set LIN-1 as parent linear-cli rel unparent LIN-2 Remove parent Relation Types blocks , blocked-by , related , duplicate Flags Flag Purpose -...
|
45 |
| 19763 | upload-chapter-slides | panaversity/agentfactory |
Upload Chapter Slides Upload PDF teaching slides to CDN and update chapter README with proper metadata. Usage /upload-chapter-slides <pdf-path> <chapter-number> [--title "Custom Title"] [--name custom-filename] Examples Basic usage - chapter number only /upload-chapter-slides /path/to/slides.pdf 4 With custom title /upload-chapter-slides /path/to/slides.pdf 3 --title "Agentic AI - The Digital FTE" With custom filename (for CDN URL) /upload-chapter-slides /path/to/slides.pdf 4 --name context-e...
|
45 |
| 19764 | backend-dev | srbhr/resume-matcher |
Backend Development Use when creating or modifying FastAPI endpoints, Pydantic schemas, database operations, LLM integrations, or Python service logic. Before Writing Code Read docs/agent/architecture/backend-guide.md for architecture Read docs/agent/apis/front-end-apis.md for API contracts Read docs/agent/llm-integration.md for LLM patterns Check existing code in the relevant directory first Non-Negotiable Rules All functions MUST have type hints - no exceptions Use copy.deepcopy() for mutable ...
|
45 |
| 19765 | learning-medusa | medusajs/medusa-claude-plugins |
Interactive Medusa Learning Tutorial Overview This is NOT a passive reference skill. This is an INTERACTIVE TUTORING SESSION where you (Claude) guide the user through building a brands feature in Medusa, teaching architecture concepts along the way. Your Role: Act as a coding bootcamp instructor - patient, encouraging, thorough, and focused on teaching understanding (not just completion). What You'll Build Together: A brands feature that allows: Creating brands via API Linking brands to prod...
|
45 |
| 19766 | creative-analyzer | dengineproblem/agents-monorepo |
Creative Analyzer Ты - эксперт по анализу и оптимизации рекламных креативов в Facebook/Instagram. Твои задачи Risk Score - оценка риска креатива (0-100) Группировка по тегам - агрегация метрик по creative_tag Multi-period анализ - сравнение 7d vs 30d Топ/худшие креативы - найти лучших и худших A/B тестирование - настройка и анализ тестов Creative fatigue - выявление выгорания Рекомендации - что улучшить в креативах Risk Score (0-100) Оценка риска креатива. Чем выше — тем хуже. Формула def calcul...
|
45 |
| 19767 | godot-genre-educational | thedivergentai/gd-agentic-skills |
Genre: Educational / Gamification Expert blueprint for educational games that make learning engaging through game mechanics. NEVER Do NEVER punish failure with "Game Over" — Learning requires safe experimentation. Use "Try Again" or "Here's a Hint" instead of fail states. NEVER separate learning from gameplay — "Chocolate-covered broccoli" feels like homework. Make mechanics BE the learning (e.g., Typing of the Dead). NEVER use walls of text — Players skip tutorials. Show, don't tell. Interactio...
|
45 |
| 19768 | angular-primeng | seikaikyo/dash-skills |
Angular 21 + PrimeNG 開發規範 適用場景 MES 製造執行系統 ERP 企業資源規劃 後台管理系統 資料密集型應用 核心原則 1. 專案結構 src/app/ ├── core/ 核心模組(單例服務) │ ├── auth/ 認證相關 │ ├── guards/ 路由守衛 │ ├── interceptors/ HTTP 攔截器 │ ├── models/ 資料模型 │ └── services/ 共用服務 ├── shared/ 共用模組 │ ├── components/ 可復用元件 │ ├── directives/ 自定義指令 │ ├── pipes/ 資料管線 │ └── utils/ 工具函數 ├── features/ ...
|
45 |
| 19769 | panews | panewslab/skills |
Public read-only PANews content via https://universal-api.panewslab.com . Set the PA-Accept-Language request header to localize responses. Current first-class support in this skill is limited to the bundled scripts below. Other public endpoints may appear in references as HTTP notes, but they are not part of the default supported workflow unless scripts are added later. When to Use The user wants structured JSON data from the PANews API The task is article discovery, article detail lookup, ranki...
|
45 |
| 19770 | building-ai-agent-on-cloudflare | cloudflare/cloudflare-docs |
Building Cloudflare Agents Creates AI-powered agents using Cloudflare's Agents SDK with persistent state, real-time communication, and tool integration. When to Use User wants to build an AI agent or chatbot User needs stateful, real-time AI interactions User asks about the Cloudflare Agents SDK User wants scheduled tasks or background AI work User needs WebSocket-based AI communication Prerequisites Cloudflare account with Workers enabled Node.js 18+ and npm/pnpm/yarn Wrangler CLI (npm instal...
|
45 |
| 19771 | vitest | teachingai/full-stack-skills |
Vitest is a next-generation testing framework powered by Vite. It provides a Jest-compatible API with native ESM, TypeScript, and JSX support out of the box. Vitest shares the same config, transformers, resolvers, and plugins with your Vite app. Key Features: Vite-native: Uses Vite's transformation pipeline for fast HMR-like test updates Jest-compatible: Drop-in replacement for most Jest test suites Smart watch mode: Only reruns affected tests based on module graph Native ESM, TypeScript, JSX su...
|
45 |
| 19772 | erpnext-impl-whitelisted | openaec-foundation/erpnext_anthropic_claude_development_skill_package |
ERPNext Whitelisted Methods - Implementation This skill helps you determine HOW to implement REST API endpoints. For exact syntax, see erpnext-syntax-whitelisted . Version : v14/v15/v16 compatible Main Decision: What Type of API? ┌───────────────────────────────────────────────────────────────────┐ │ WHAT ARE YOU BUILDING? │ ├───────────────────────────────────────────────────────────────────┤ │ ...
|
44 |
| 19773 | code-simplifier | duc01226/easyplatform |
Code Simplifier You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. Refinement Principles 1. Preserve Functionality Never change what the code does - only how it does it. All original features, outputs, ...
|
44 |
| 19774 | linear-bulk | finesssee/linear-cli |
Bulk Operations Update status for multiple issues linear-cli b update-state -s Done LIN-1 LIN-2 LIN-3 Assign multiple issues linear-cli b assign --user me LIN-1 LIN-2 linear-cli b assign --user "John Doe" LIN-1 LIN-2 Unassign multiple issues linear-cli b unassign LIN-1 LIN-2 Add label to multiple issues linear-cli b label --add bug LIN-1 LIN-2 LIN-3 Pipe issue IDs from stdin linear-cli i list -t ENG --id-only | linear-cli b assign --user me - Flags Flag Purpose --dry-run Preview changes --o...
|
44 |
| 19775 | blueprint-upgrade | laurigates/claude-plugins |
Upgrade the blueprint structure to the latest format version. Current Format Version : 3.2.0 This command delegates version-specific migration logic to the blueprint-migration skill. Steps : Check current state : Read docs/blueprint/.manifest.json (v3.0 location) or .claude/blueprints/.manifest.json (v1.x/v2.x location) If not found in either location, suggest running /blueprint:init instead Extract current format_version (default to "1.0.0" if field missing) Determine upgrade path : Read curre...
|
44 |
| 19776 | migration planner | eddiebe147/claude-settings |
Migration Planner Plan and execute migrations with minimal disruption. From database migrations to full platform transitions, follow proven methodologies for successful migrations. Core Workflows Workflow 1: Migration Planning Assessment - Document current state and requirements Strategy - Choose migration approach (big bang vs. phased) Risk Analysis - Identify potential issues Timeline - Create realistic schedule Rollback Plan - Define abort criteria and procedures Workflow 2: Data Migration Sc...
|
44 |
| 19777 | pachca-messages | pachca/openapi |
pachca-messages Quick start Ask user for Pachca token (bot: Automations → Integrations → API, or user: Automations → API). Run commands with npx @pachca/cli and --token flag: npx @pachca/cli <command> --token $PACHCA_TOKEN Or set PACHCA_TOKEN for multiple commands: export PACHCA_TOKEN=<token> npx @pachca/cli <command> Help: npx @pachca/cli --help | Scenarios: npx @pachca/cli guide After successful use, suggest installing CLI globally: npm install -g @pachca/cli && pachca auth login --token $PACH...
|
44 |
| 19778 | postgresql database administration | manutej/luxor-claude-marketplace |
PostgreSQL Database Administration for Customer Support Overview This comprehensive skill covers PostgreSQL database administration specifically tailored for customer support tech enablement. PostgreSQL is a powerful, open-source object-relational database system with over 35 years of active development, known for its reliability, feature robustness, and performance. In customer support environments, PostgreSQL excels at handling complex ticket management, user analytics, audit logging, and real...
|
44 |
| 19779 | agent-browser | clawdbrunner/skill-agent-browser |
Browser Automation with agent-browser The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser , brew install agent-browser , or cargo install agent-browser . Run agent-browser install to download Chrome. Core Workflow Every browser automation follows this pattern: Navigate : agent-browser open <url> Snapshot : agent-browser snapshot -i (get element refs like @e1 , @e2 ) Interact : Use refs to click, fill, select Re-snapshot : After navigation or DOM changes, get fresh r...
|
44 |
| 19780 | accessibility-issues | dylantarre/animation-principles |
Accessibility Issues Make animations inclusive using Disney's principles thoughtfully. Problem Indicators Motion sickness complaints Vestibular disorder triggers Screen reader confusion Cognitive overload Seizure risk (flashing) Keyboard focus lost during animation Diagnosis by Principle Squash and Stretch Issue: Excessive distortion causes disorientation Fix: Reduce or eliminate squash/stretch for users with prefers-reduced-motion. Use opacity changes instead. Secondary Action Issue: Too m...
|
44 |
| 19781 | context-analyzer | vladm3105/aidoc-flow-framework |
Context Analyzer Skill (上下文分析技能) 能力 (Capabilities) 项目结构分析 : 理解 Nuxt 目录约定 ( server/api , components , pages ) 以及 Nuxt 4 特性。 符号解析 : 定位组件、自动导入的可组合函数 (composables) 和 TypeORM 实体的定义。 认证流程分析 : 深入理解 Better-Auth 的集成,包括 lib/auth.ts (服务端), lib/auth-client.ts (客户端), middleware/auth.global.ts (全局中间件)。 依赖检查 : 读取 package.json 以验证已安装的包和版本。 指令 (Instructions) 读取结构 : 使用目录列表工具了解布局,忽略 node_modules 和 .output 。 识别 Nuxt 类型 : 将 server/api 识别为后端定义,将 pages / components 识别为前端。 追踪逻辑 : 广泛搜索符号定义,以理解数据如何在后端实体 (Entities) 和前端组件 ...
|
44 |
| 19782 | erpnext-errors-clientscripts | openaec-foundation/erpnext_anthropic_claude_development_skill_package |
ERPNext Client Scripts - Error Handling This skill covers error handling patterns for Client Scripts. For syntax, see erpnext-syntax-clientscripts . For implementation workflows, see erpnext-impl-clientscripts . Version : v14/v15/v16 compatible Main Decision: How to Handle the Error? ┌─────────────────────────────────────────────────────────────────────────┐ │ WHAT TYPE OF ERROR ARE YOU HANDLING? │ ├──────────────────────────────────────────────────────────────...
|
44 |
| 19783 | microservices-patterns | manutej/luxor-claude-marketplace |
Microservices Patterns Master microservices architecture patterns including service boundaries, inter-service communication, data management, and resilience patterns for building distributed systems. When to Use This Skill Decomposing monoliths into microservices Designing service boundaries and contracts Implementing inter-service communication Managing distributed data and transactions Building resilient distributed systems Implementing service discovery and load balancing Designing event-driv...
|
44 |
| 19784 | vtable development assistant | visactor/vtable |
VTable Development Assistant Skill 角色定义 你是 VTable 开发助手,专门帮助用户使用 @visactor/vtable 进行高性能表格组件的开发。你熟悉 VTable 的三种核心表格类型(ListTable、PivotTable、PivotChart)、全部 13 种单元格类型、样式/主题系统、自定义渲染、事件系统和完整 API。 知识库结构 references/ knowledge/ 结构化知识文档 type/ 用户可见的类型定义(markdown 格式) examples/ 精选示例代码模式 查询路由规则 根据用户问题,查询对应知识模块: 使用规则: 先用关键词命中路由表,按顺序加载对应文件(优先 knowledge,再补 type) 只加载解决当前问题必需的 1-3 个文件,不要一次性加载全部 references 若用户要“可运行 demo/完整配置”,再补充加载 references/examples/ 中最接近的示例 用户意图关键词 查询文件 创建表格、初始化、入门 referenc...
|
44 |
| 19785 | backup-restore-runbook-generator | patricio0312rev/skills |
Backup/Restore Runbook Generator Create reliable disaster recovery procedures for your databases. Backup Strategy Database Backup Strategy Backup Types 1. Full Backup (Daily) - When: 2:00 AM UTC - Retention: 30 days - Storage: S3 `s3://backups/full/` - Size: ~50 GB - Duration: ~45 minutes 2. Incremental Backup (Hourly) - When: Every hour - Retention: 7 days - Storage: S3 `s3://backups/incremental/` - Size: ~500 MB - Duration: ~5 minutes 3. Transaction Log Backup (Every 15 min) - Wh...
|
44 |
| 19786 | better-auth-best-practices | panaversity/agentfactory |
Better Auth Integration Guide Always consult better-auth.com/docs for code examples and latest API. Setup Workflow Install: npm install better-auth Set env vars: BETTER_AUTH_SECRET and BETTER_AUTH_URL Create auth.ts with database + config Create route handler for your framework Run npx @better-auth/cli@latest migrate Verify: call GET /api/auth/ok — should return { status: "ok" } Quick Reference Environment Variables BETTER_AUTH_SECRET - Encryption secret (min 32 chars). Generate: openssl rand -b...
|
44 |
| 19787 | nano-banana-pro | nkchivas/openclaw-skill-nano-banana-pro |
Nano Banana Pro Image Generation & Editing Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image). Usage Run the script using absolute path (do NOT cd to skill directory first): Generate new image: uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 1K|2K|4K] [--api-key KEY] Edit existing image: uv run ~/.claude/skills/nano-banana-pro/scripts/generate_imag...
|
44 |
| 19788 | frontend-architect | tomlord1122/tomtom-skill |
Frontend Architecture Expert Expert assistant for frontend architecture design, component patterns, state management, performance optimization, and technology selection. Thinking Process When activated, follow this structured thinking approach to design frontend architectures: Step 1: Context Discovery Goal: Understand the current state and constraints before proposing changes. Key Questions to Ask: What is the existing tech stack? (framework, bundler, styling approach) What is the current archi...
|
44 |
| 19789 | recognition-program-builder | dengineproblem/agents-monorepo |
Recognition Program Builder Expert in creating and optimizing employee recognition programs that drive engagement, retention, and performance. Core Principles recognition_principles : timely : "Recognize immediately after achievement" specific : "Detail exactly what was recognized" personal : "Tailored to individual preferences" visible : "Public recognition amplifies impact" valuable : "Meaningful to the recipient" recognition_types : formal : - "Awards and ceremonies" - "Performance bonuses" -...
|
44 |
| 19790 | term sheet analyzer | eddiebe147/claude-settings |
Term Sheet Analyzer Analyze VC term sheets, understand key terms, and negotiate favorable conditions When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create term sheet analyzer term sheet Review and optimize review term sheet analyzer Get best practices term sheet analy...
|
44 |
| 19791 | convex-auth | igorwarzocha/opencode-workflows |
Auth Operations In functions: ctx.auth.getUserIdentity() returns tokenIdentifier, subject, issuer plus provider claims. Custom JWT auth MAY expose claims at identity["properties.email"] style paths. User storage patterns: Client mutation to store user from JWT, or webhook from provider to upsert users. Index lookups SHOULD use by_token / byExternalId. Webhooks: You MUST implement via HTTP actions and verify signatures with provider SDK; signing secrets MUST be stored in env vars. Convex Auth (Be...
|
44 |
| 19792 | lead-enrichment | chadboyda/agent-gtm-skills |
Lead Enrichment Skill You are a B2B data enrichment architect. You build waterfall enrichment systems, ICP scoring frameworks, and contact verification pipelines that maximize coverage while minimizing cost per verified lead. You know the provider landscape cold and design workflows that sequence providers for maximum incremental yield. Before Starting Confirm with the user: (1) target ICP - industry, company size, geography, persona; (2) current stack - CRM, enrichment tools, outreach platforms...
|
44 |
| 19793 | undervalued-stock-screener | geeksfino/finskills |
低估值股票筛选器 扮演专业的权益研究分析师。扫描A股市场,筛选出基本面强劲但被市场低估的上市公司。 工作流程 第一步:确定参数 与用户确认: 筛选范围 — 全市场、特定申万一级行业、主板/创业板/科创板/北交所、或自定义股票池 市值范围 — 无限制(默认)、大盘(>500亿)、中盘(100–500亿)、小盘(<100亿) 结果数量 — 默认:10家 侧重点 — 综合评估(默认)、深度价值(低PB导向)、成长价值(PEG导向)、红利价值 默认参数:全市场、无市值限制、10家、综合评估。 第二步:应用筛选条件 对全部候选股票应用以下筛选条件。详细标准参见 references/screening-methodology.md 。 筛选条件 标准 PE估值 滚动PE低于所属申万行业中位数 PB估值 PB低于所属行业中位数(配合ROE筛选) 营收与利润增长 近3–5年营收和归母净利润复合增长率为正 资产负债率 低于行业中位数(金融行业除外) 自由现金流 正值且近3年累计为正 ROIC/ROE ROE高于行业平均水平 自动排除 :ST/*ST公司、上市不满2年的公司、近12个月净利润为负的公司。...
|
44 |
| 19794 | swift-data | pproenca/dot-skills |
SwiftData Best Practices — Modular MVVM-C Data Layer Comprehensive data modeling, persistence, sync architecture, and error handling guide for SwiftData aligned with the clinic modular MVVM-C stack. Architecture Alignment This skill enforces the same modular architecture mandated by swift-ui-architect : ┌───────────────────────────────────────────────────────────────┐ │ Feature modules: View + ViewModel, no SwiftData imports │ ├──────────────────────────────────────────────────────────────...
|
44 |
| 19795 | statusline-config | sd0xdev/sd0x-dev-flow |
StatusLine Config Customize ~/.claude/statusline-command.sh — segments, themes, and colors. When NOT to Use Scenario Use Instead Setting statusline for the first time (no customization needed) Built-in statusline-setup agent (Claude Code agent type) — applies defaults automatically Editing settings.json directly Manual edit — this skill manages statusline-command.sh , not settings.json Debugging Claude Code startup issues /claude-health — config health check Segments Segment JSON Field Default N...
|
44 |
| 19796 | onboarding-specialist | ncklrs/startup-os-skills |
Onboarding Specialist Expert guidance for transforming new customers into successful, activated users. The onboarding phase is the most critical window for customer retention — get it right, and you create advocates; get it wrong, and you create churn. Philosophy Customer onboarding is not a checklist — it's a transformation: Time-to-value is everything — Every day before value is a day closer to churn Onboarding is not training — It's guiding customers to their specific outcomes Structured flex...
|
44 |
| 19797 | almanak-strategy-builder | almanak-co/sdk |
Almanak Strategy Builder You are helping a quant build DeFi strategies using the Almanak SDK. Strategies are Python classes that return Intent objects. The framework handles compilation to transactions, execution, and state management. Quick Start Install the CLI globally pipx install almanak Scaffold a new strategy (creates a self-contained Python project) almanak strat new --template mean_reversion --name my_rsi --chain arbitrum Run on local Anvil fork (auto-starts gateway + Anvil) cd my_rs...
|
44 |
| 19798 | teach-oh | open-horizon-labs/skills |
/teach-oh Setup that gathers project context and saves it to AGENTS.md (the cross-agent standard). Run when starting on a project or when strategy/aims have shifted. When to Use Invoke /teach-oh when: Starting on a new project - Before diving into work Context keeps getting lost - AI assistants don't "get" your project Onboarding a new AI tool - Establish shared understanding upfront After major strategic shifts - When aims or constraints have changed Do not use when: You're mid-task. This ...
|
44 |
| 19799 | workshop facilitator | eddiebe147/claude-settings |
Workshop Facilitator Design and facilitate effective workshops with agendas, activities, and outcomes When to Use This Skill Use this skill when you need to: Enhance team collaboration Improve stakeholder engagement Facilitate clear dialogue Not recommended for: Tasks requiring technical development data analysis Quick Reference Action Command/Trigger Create workshop facilitator workshop facilitation Review and optimize review workshop facilitator Get best practices workshop facilitator best pra...
|
44 |
| 19800 | x-publish | kangarooking/x-skills |
X Publish Publish tweets and threads to X draft using Playwright browser automation. Prerequisites Playwright MCP for browser automation User logged into X (Twitter) Python 3.9+ with dependencies: macOS: pip install Pillow pyobjc-framework-Cocoa Windows: pip install Pillow pywin32 Critical Rules NEVER auto-publish - Only save to draft User must be logged in - Prompt to login if not Verify content before saving - Double-check tweet text Content Types Short Tweet Single tweet ≤280 characters T...
|
44 |