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...
21,860
总 Skills
40.8M
总安装量
2,461
贡献者
# Skill 仓库 描述 安装量
15201 crypto-hft alsk1992/cloddsbot
Crypto HFT - Binary Market Trading Trade Polymarket's crypto binary markets with 4 automated strategies. Just say what you want! Available market durations (pick one): 5-minute : BTC only - ultra-high frequency HFT 15-minute : All assets (BTC, ETH, SOL, XRP) - balanced, most popular 1-hour : All assets - faster swing trading 4-hour : All assets - multi-hour trends Daily : All assets - position trading, overnight holds Each round has UP/DOWN token pairs that settle at 0 or 1 using Chainlink price...
 57
15202 document-to-narration jwynia/agent-skills
Document to Narration Convert written documents into narrated video scripts with precise word-level timing. Core Principle The agent interprets; the document guides. Rather than rigid template-based splits, this skill uses agent judgment to find where the content naturally breathes, argues, and transitions. The document's argument flow determines scene breaks, not a predetermined structure. When to Use This Skill Use this skill when: Converting a blog post or essay to video narration Preparing c...
 57
15203 searching-context volcengine/openviking
OpenViking (OV) context searching The ov search command performs context-aware retrieval across all memories and resources in OpenViking — combining semantic understanding with directory recursive retrieval to find the most relevant context for any query. Table of Content When to Use Search Modes Context-Aware Search ( ov search ) Content Pattern Search ( ov grep ) File Glob Search ( ov glob ) Search Options Result Control Scope Control Session-Aware Search Output Other Utilities List Contents (...
 57
15204 workers-frameworks secondsky/claude-skills
Build full-stack applications on Cloudflare Workers using modern frameworks. Quick Start: Choose Your Framework | Hono | APIs, lightweight apps | ✅ | ✅ | ✅ Native | Remix | Full-stack apps | ✅ | ✅ | ✅ Adapter | Next.js | React apps | ✅ | ✅ | ⚠️ OpenNext | Astro | Content sites | ✅ | ✅ | ✅ Adapter | SvelteKit | Svelte apps | ✅ | ✅ | ✅ Adapter | Qwik | Resumable apps | ✅ | ✅ | ✅ Adapter | Nuxt | Vue apps | ✅ | ✅ | ✅ Nitro Framework Decision Tree ``` N...
 57
15205 tauri-app-dev xiaolai/vmark
Tauri 2.0 App Development Tauri is a framework for building small, fast, secure desktop apps using web frontends and Rust backends. Architecture Overview ┌─────────────────────────────────────────┐ │ Frontend (Webview) │ │ HTML/CSS/JS • React/Vue/Svelte │ └────────────────┬────────────────────────┘ │ IPC (invoke/events) ┌────────────────▼────────────────────────┐ │ Tauri Core (Rust) │ │ Commands • State • Plugins • Events │ └───────────────...
 57
15206 adcp-creative adcontextprotocol/adcp
AdCP Creative Protocol This skill enables you to execute the AdCP Creative Protocol with creative agents. Use the standard MCP tools ( list_creative_formats , build_creative , preview_creative ) exposed by the connected agent. Overview The Creative Protocol provides 3 standardized tasks for building and previewing advertising creatives: Task Purpose Response Time list_creative_formats View format specifications ~1s build_creative Generate or transform creatives ~30s-5m preview_creative Get visua...
 57
15207 llamaindex orchestra-research/ai-research-skills
LlamaIndex - Data Framework for LLM Applications The leading framework for connecting LLMs with your data. When to use LlamaIndex Use LlamaIndex when: Building RAG (retrieval-augmented generation) applications Need document question-answering over private data Ingesting data from multiple sources (300+ connectors) Creating knowledge bases for LLMs Building chatbots with enterprise data Need structured data extraction from documents Metrics: 45,100+ GitHub stars 23,000+ repositories use Lla...
 57
15208 asciinema-converter terrylica/cc-skills
asciinema-converter Convert asciinema .cast recordings to clean .txt files for Claude Code analysis. Achieves 950:1 compression (3.8GB -> 4MB) by stripping ANSI codes and JSON structure. Platform: macOS, Linux (requires asciinema CLI v2.4+) Why Convert? Format Size (22h session) Claude Code Compatible Searchable .cast 3.8GB No (NDJSON + ANSI) Via jq .txt ~4MB Yes (clean text) Grep/Read Key benefit: Claude Code's Read and Grep tools work directly on .txt output. Requirements Component Requir...
 57
15209 anygen-image anygenio/anygen-skills
AnyGen Image Generator You MUST strictly follow every instruction in this document. Do not skip, reorder, or improvise any step. If this skill has been updated since it was last loaded, reload this SKILL.md before proceeding and always follow the latest version. Generate images, illustrations and visual content using AnyGen OpenAPI ( www.anygen.io ). Images are generated server-side; this skill sends the user's prompt and optional reference files to the AnyGen API and retrieves the results. An A...
 57
15210 en-to-zh-translator seefreed/skills
English to Chinese Translator Overview Translates English text files to natural Chinese while preserving sentence structure for effective bidirectional translation practice. Combines broken sentences into complete lines. Output files use the _zh suffix (e.g., document.txt → document_zh.txt). Translation Workflow Read the source file - Read the full English text file to understand context and tone Translate to Chinese - Apply translation guidelines (see below) Write translated file - Create {or...
 57
15211 dojo-indexer dojoengine/book
Dojo Indexer (Torii) Set up and use Torii, the Dojo indexer, for efficient querying and real-time subscriptions to your world state. When to Use This Skill "Set up Torii indexer" "Configure GraphQL for my world" "Create subscriptions for entity updates" "Query world state efficiently" What This Skill Does Manages Torii indexer: Start and configure Torii Create GraphQL queries Set up real-time subscriptions Access SQL database directly Quick Start Start Torii: torii --world < WORLD_ADDRESS > This...
 57
15212 nextjs-development manutej/luxor-claude-marketplace
Next.js Development Skill This skill provides comprehensive guidance for building modern Next.js applications using the App Router, Server Components, data fetching patterns, routing, API routes, middleware, and full-stack development techniques based on official Next.js documentation. When to Use This Skill Use this skill when: Building full-stack React applications with server-side rendering (SSR) Creating static sites with incremental static regeneration (ISR) Developing modern web applic...
 57
15213 reviewing-changes bitwarden/android
Reviewing Changes - Android Additions This skill provides Android-specific workflow additions that complement the base bitwarden-code-reviewer agent standards. Instructions IMPORTANT : Use structured thinking throughout your review process. Plan your analysis in <thinking> tags before providing final feedback. Step 1: Retrieve Additional Details Retrieve any additional information linked to the pull request using available tools (JIRA MCP, GitHub API). If pull request title and message do not pr...
 57
15214 dry-consolidation laurigates/claude-plugins
DRY Consolidation Systematic extraction of duplicated code into shared, tested abstractions. When to Use This Skill Use this skill when... Use these instead when... Multiple files have identical/near-identical code blocks Single file needs cleanup → /code:refactor Copy-pasted utility functions across components Looking for anti-patterns without fixing → /code:antipatterns Repeated UI patterns (dialogs, pagination, error states) Functional refactoring of a file or directory → /code:refactor Dupli...
 57
15215 wiki-changelog sickn33/antigravity-awesome-skills
Wiki Changelog Generate structured changelogs from git history. When to Activate User asks "what changed recently", "generate a changelog", "summarize commits" User wants to understand recent development activity Procedure Examine git log (commits, dates, authors, messages) Group by time period: daily (last 7 days), weekly (older) Classify each commit: Features (🆕), Fixes (🐛), Refactoring (🔄), Docs (📝), Config (🔧), Dependencies (📦), Breaking (⚠️) Generate concise user-facing descriptions using p...
 57
15216 dojo-world dojoengine/book
Dojo World Management Manage your Dojo world's permissions, namespaces, resource registration, and access control policies. When to Use This Skill "Configure world permissions" "Set up namespace access" "Grant writer permissions" "Manage resource ownership" What This Skill Does Handles world management: Namespace configuration Writer permissions (can write data) Owner permissions (can write data + manage permissions) Permission hierarchy management Quick Start Configure permissions: "Grant write...
 57
15217 drizzle-best-practices honra-io/drizzle-best-practices
Drizzle ORM Best Practices (PostgreSQL) Comprehensive best practices guide for Drizzle ORM with PostgreSQL. Contains guidance across 8 categories, prioritized by impact to help you write correct, performant, and maintainable database code. When to Apply Reference these guidelines when: Defining table schemas with pgTable Writing select, insert, update, or delete queries Setting up relations between tables using defineRelations or the legacy relations API Configuring drizzle-kit for migrations ( ...
 57
15218 openapi-generator patricio0312rev/skills
OpenAPI Generator Generate OpenAPI 3.0/3.1 specifications from your API codebase automatically. Core Workflow Scan routes: Find all API route definitions Extract schemas: Types, request/response bodies, params Build paths: Convert routes to OpenAPI path objects Generate schemas: Create component schemas from types Add documentation: Descriptions, examples, tags Export spec: YAML or JSON format OpenAPI 3.1 Base Template openapi: 3.1.0 info: title: API Title version: 1.0.0 description: API...
 57
15219 docker-watch-mode-2025 josiahsiegel/claude-plugin-marketplace
Docker Compose Watch Mode (2025 GA) Docker Compose Watch enables automatic hot reload during local development by synchronizing file changes instantly without manual container restarts. Three Watch Actions 1. sync - Hot Reload For frameworks with hot reload (React, Next.js, Node.js, Flask). Copies changed files directly into running container. 2. rebuild - Compilation For compiled languages (Go, Rust, Java) or dependency changes. Rebuilds image and recreates container when files change. 3....
 57
15220 ios-swift-expert sjungling/claude-plugins
Elite-level guidance for iOS and macOS development with deep expertise in Swift, SwiftUI, UIKit, and the entire Apple development ecosystem. Core principle: Follow Apple's Human Interface Guidelines, Swift API Design Guidelines, and modern iOS development best practices while writing clean, performant, memory-safe code. When to Use Automatically activates when: - Working with `.swift` source files - Opening or modifying Xcode projects (`.xcodeproj`, `.xcworkspace`) - Editing SwiftUI views...
 57
15221 graphite-stacks outfitter-dev/agents
Graphite Stacks Trunk-based development with stacked PRs using Graphite CLI. <when_to_use> Creating or managing branch stacks Submitting stacked PRs Reorganizing branch relationships Addressing PR feedback across a stack Recovering from stack corruption Any gt command usage </when_to_use> Core Principle Use gt commands exclusively. Mixing git and gt causes sync issues and divergent stacks. The only exception: git add for staging (or use -a flags). This, Not That Task This Not That Create branch ...
 57
15222 headless-terminal letta-ai/skills
This skill guides the implementation of headless terminal interfaces—programmatic wrappers that control shell sessions without a visible terminal UI. These implementations typically involve spawning shell processes, sending input (keystrokes, commands), and capturing output. Approach Step 1: Understand the Interface Contract Before implementing, thoroughly read and understand the interface to be implemented: - Identify all required methods and their signatures - Note return types and expe...
 57
15223 langchain orchestra-research/ai-research-skills
LangChain - Build LLM Applications with Agents & RAG The most popular framework for building LLM-powered applications. When to use LangChain Use LangChain when: Building agents with tool calling and reasoning (ReAct pattern) Implementing RAG (retrieval-augmented generation) pipelines Need to swap LLM providers easily (OpenAI, Anthropic, Google) Creating chatbots with conversation memory Rapid prototyping of LLM applications Production deployments with LangSmith observability Metrics: 119,0...
 57
15224 monetization-strategy travisjneuman/.claude
Monetization Strategy You are an expert in mobile app monetization with deep knowledge of subscription economics, paywall psychology, and pricing strategy. Your goal is to help the user maximize revenue while maintaining user satisfaction. Initial Assessment Check for app-marketing-context.md — read it for context Ask for current monetization model (free, freemium, paid, subscription, ads) Ask for current pricing (if applicable) Ask for conversion rate (free to paid, trial to subscription) Ask f...
 57
15225 vite itechmeat/llm-code
Vite Based on Vite 8 beta (Rolldown-powered). Vite 8 uses Rolldown bundler and Oxc transformer. Vite is a next-generation frontend build tool with fast dev server (native ESM + HMR) and optimized production builds. Preferences Use TypeScript: prefer vite.config.ts Always use ESM, avoid CommonJS Core Topic Description Reference Configuration vite.config.ts , defineConfig , conditional configs, loadEnv core-config Features import.meta.glob , asset queries ( ?raw , ?url ), import.meta.env , HMR API...
 57
15226 integration-tests andrelandgraf/fullstackrecipes
Integration Tests To set up Integration Tests, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/integration-tests If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/integration-tests
 57
15227 acquiring-skills letta-ai/letta-code
Acquiring New Skills This skill teaches you how to safely discover and install skills from external sources. SAFETY - READ THIS FIRST Skills can contain: Markdown files (.md) - Risk: prompt injection, misleading instructions Scripts (Python, TypeScript, Bash) - Risk: malicious code execution Trusted Sources (no user approval needed for download) https://github.com/letta-ai/skills - Letta's community skills https://github.com/anthropics/skills - Anthropic's official skills Untrusted Sources (ALWA...
 57
15228 control-flow epicenterhq/epicenter
Human-Readable Control Flow When refactoring complex control flow, mirror natural human reasoning patterns: Ask the human question first: "Can I use what I already have?" -> early return for happy path Assess the situation: "What's my current state and what do I need to do?" -> clear, mutually exclusive conditions Take action: "Get what I need" -> consolidated logic at the end Use natural language variables: isUsingNavigator, isUsingLocalTranscription, needsOldFileCleanup: names that read like...
 57
15229 cloud-devops-expert oimiragieo/agent-studio
Cloud Devops Expert Core Services: Compute: EC2, Lambda (serverless), ECS/EKS (containers), Fargate Storage: S3 (object), EBS (block), EFS (file system) Database: RDS (relational), DynamoDB (NoSQL), Aurora (MySQL/PostgreSQL) Networking: VPC, ALB/NLB, CloudFront (CDN), Route 53 (DNS) Monitoring: CloudWatch (metrics, logs, alarms) Best Practices: Use AWS Organizations for multi-account management Implement least privilege with IAM roles and policies Enable CloudTrail for audit logging Use AWS ...
 57
15230 particles-physics bbeierle12/skill-mcp-claude
Particle Physics Apply forces, fields, and constraints to create dynamic particle motion. Quick Start // Simple gravity + velocity useFrame((_, delta) => { for (let i = 0; i < count; i++) { // Apply gravity velocities[i * 3 + 1] -= 9.8 * delta; // Update position positions[i * 3] += velocities[i * 3] * delta; positions[i * 3 + 1] += velocities[i * 3 + 1] * delta; positions[i * 3 + 2] += velocities[i * 3 + 2] * delta; } geometry.attributes.position.needsUpdate...
 57
15231 api-test-suite-generator patricio0312rev/skills
API Test Suite Generator Generate comprehensive API test suites automatically from your route definitions. Core Workflow Scan routes: Find all API route definitions Analyze contracts: Extract request/response schemas Generate tests: Create test files for each resource Add assertions: Status codes, response structure, headers Include edge cases: Invalid inputs, auth, not found Setup fixtures: Test data and database seeding Test Structure tests/ ├── setup.ts Global test setup ├── f...
 57
15232 android-kotlin-coroutines thebushidocollective/han
Android - Kotlin Coroutines Asynchronous programming patterns using Kotlin coroutines and Flow in Android. Key Concepts Coroutine Basics // Launching coroutines class UserViewModel : ViewModel() { fun loadUser(id: String) { // viewModelScope is automatically cancelled when ViewModel is cleared viewModelScope.launch { try { val user = userRepository.getUser(id) _uiState.value = UiState.Success(user) } catch (e: Excepti...
 57
15233 post-process-logo tradingstrategy-ai/web3-ethereum-defi
Post-process logo This skill transforms original logo images into standardised 256x256 PNG format suitable for vault protocol metadata. It automatically selects the most square variant from available logos and applies padding if needed to create a perfect square output. Required inputs Before starting, gather the following from the user: Input folder - Folder containing original logo files (e.g., eth_defi/data/vaults/original_logos/protocol-name/) Output folder - Folder where processed logos...
 57
15234 intent-build-now arcblock/idd
Intent Build Now Start building from Intent. Validates completeness, then chooses execution path. Workflow /intent-build-now [path] ↓ Locate Intent + plan.md ↓ Validate completeness ──→ Incomplete? ──→ Show gaps, suggest /intent-plan ↓ Check for TaskSwarm │ ├── Has TaskSwarm + TASK.yaml ──→ Delegate to /swarm run │ └── No TaskSwarm ──→ Execute TDD phases directly Step 1: Locate Files Search for Intent files in order: User-specified path intent/{name}/ directories Current directory Required files...
 57
15235 multi-agent-performance-profiling terrylica/cc-skills
Multi-Agent Performance Profiling Overview Prescriptive workflow for spawning parallel profiling agents to comprehensively identify performance bottlenecks across multiple system layers. Successfully discovered that QuestDB ingests at 1.1M rows/sec (11x faster than target), proving database was NOT the bottleneck - CloudFront download was 90% of pipeline time. When to Use This Skill Use this skill when: Performance below SLO (e.g., 47K vs 100K rows/sec target) Multi-stage pipeline optimization (...
 57
15236 git-2025-features josiahsiegel/claude-plugin-marketplace
📌 NOTE: For detailed Git 2.49+ features (git-backfill, path-walk API, zlib-ng), see git-2-49-features.md skill. 🚨 CRITICAL GUIDELINES Windows File Path Requirements MANDATORY: Always Use Backslashes on Windows for File Paths When using Edit or Write tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/). Examples: ❌ WRONG: D:/repos/project/file.tsx ✅ CORRECT: D:\repos\project\file.tsx This applies to: Edit tool file_path parameter Write tool file_path parame...
 57
15237 database-migration-integrity-checker jorgealves/agent_skills
Database Migration Integrity Checker Purpose and Intent The database-migration-integrity-checker is a safety net for your most critical asset: your data. It catches dangerous SQL operations that might pass a standard code review but could cause production outages or data loss. When to Use CI/CD Pipelines : Block deployments if a migration contains a high-risk operation without manual override. Local Development : Run before committing a new migration to ensure it follows safe DDL practices. When...
 57
15238 claude-agent-sdk rysweet/amplihack
Claude Agent SDK - Structured Outputs & Error Prevention Guide Package: @anthropic-ai/claude-agent-sdk@0.2.12 Breaking Changes: v0.1.45 - Structured outputs (Nov 2025), v0.1.0 - No default system prompt, settingSources required What's New in v0.1.45+ (Nov 2025) Major Features: 1. Structured Outputs (v0.1.45, Nov 14, 2025) JSON schema validation - Guarantees responses match exact schemas outputFormat parameter - Define output structure with JSON schema or Zod Access validated results - Via me...
 57
15239 deep-research z0gsh1u/oh-my-writing-skill
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...
 57
15240 betterauth-tanstack-convex sstobo/convex-skills
This skill provides guidance for integrating Better Auth authentication with Convex backend and TanStack Start framework. It covers the complete setup process from installation to SSR-compatible authentication flows. When to Use This Skill - Setting up authentication in a new Convex + TanStack Start project - Troubleshooting Better Auth configuration issues - Implementing sign up, sign in, or sign out flows - Configuring SSR authentication with `expectAuth: true` - Adding authenticated se...
 57
15241 frontend-development aaaaqwq/claude-code-skills
Frontend Development Guidelines Purpose Comprehensive guide for modern frontend development across React, Vue 3, Svelte 5, and Angular. Covers framework-specific patterns, common architectural principles, and cross-framework best practices. When to Use This Skill Creating components or pages in React, Vue, Svelte, or Angular Building new features with framework-specific patterns Implementing state management (Pinia, Zustand, stores, signals) Setting up routing (TanStack Router, Vue Router, Svelt...
 57
15242 framework orchestrator daffy0208/ai-dev-standards
Framework Orchestrator Overview The Framework Orchestrator is the meta-skill that coordinates all other skills and frameworks throughout your project lifecycle. It analyzes your project, identifies the appropriate pattern, and sequences frameworks and skills in the optimal order. Think of it as: Your AI project manager that knows when to apply which methodology. When to Use This Skill Use Framework Orchestrator when: Starting a new project and need guidance on methodology Unsure which frameworks...
 57
15243 databricks-apps databricks/databricks-agent-skills
Databricks Apps Development FIRST : Use the parent databricks skill for CLI basics, authentication, and profile selection. Build apps that deploy to Databricks Apps platform. Required Reading by Phase Phase READ BEFORE proceeding Scaffolding Parent databricks skill (auth, warehouse discovery); run databricks apps manifest and use its plugins/resources to build databricks apps init with --features and --set (see AppKit section below) Writing SQL queries SQL Queries Guide Writing UI components Fro...
 57
15244 docs-style existential-birds/beagle
Documentation Style Guide Apply these principles when writing or reviewing documentation to ensure clarity, consistency, and accessibility for both human readers and LLMs. Voice and Tone Use Second Person Address the reader directly as "you" rather than "the user" or "developers." <!-- Good --> You can configure the API by setting environment variables. <!-- Avoid --> The user can configure the API by setting environment variables. Developers should configure the API by setting environment ...
 57
15245 kubernetes-operations laurigates/claude-plugins
Kubernetes Operations Expert knowledge for Kubernetes cluster management, deployment, and troubleshooting with mastery of kubectl and cloud-native patterns. Core Expertise Kubernetes Operations Workload Management : Deployments, StatefulSets, DaemonSets, Jobs, and CronJobs Networking : Services, Ingress, NetworkPolicies, and DNS configuration Configuration & Storage : ConfigMaps, Secrets, PersistentVolumes, and PersistentVolumeClaims Troubleshooting : Debugging pods, analyzing logs, and inspecti...
 57
15246 artifacts-builder shipshitdev/library
Artifacts Builder To build powerful frontend claude.ai artifacts, follow these steps: Initialize the frontend repo using scripts/init-artifact.sh Develop your artifact by editing the generated code Bundle all code into a single HTML file using scripts/bundle-artifact.sh Display artifact to user (Optional) Test the artifact Stack : React 18 + TypeScript + Vite + Parcel (bundling) + Tailwind CSS + shadcn/ui Design & Style Guidelines VERY IMPORTANT: To avoid what is often referred to as "AI slop", ...
 57
15247 code-antipatterns-analysis laurigates/claude-plugins
Expert knowledge for systematic detection and analysis of anti-patterns, code smells, and quality issues across codebases using ast-grep and parallel agent delegation. Analysis Philosophy This skill emphasizes parallel delegation for comprehensive analysis. Rather than sequentially scanning for issues, launch multiple specialized agents to examine different categories simultaneously, then consolidate findings. Analysis Categories 1. JavaScript/TypeScript Anti-patterns Callback Hell & Asy...
 57
15248 code-review sgcarstrends/sgcarstrends
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...
 57
15249 godot-inventory-system thedivergentai/gd-agentic-skills
Inventory System Slot management, stacking logic, and resource-based items define robust inventory systems. Available Scripts grid_inventory_logic.gd Expert grid inventory with tetris-style placement logic. inventory_grid.gd Grid-based inventory controller with drag-and-drop foundations and auto-sorting. NEVER Do in Inventory Systems NEVER use Nodes for items — Item extends Node = memory leak nightmare. Inventory with 100 items = 100 nodes in tree. Use Item extends Resource for save compatibilit...
 57
15250 defi-security 0xlayerghost/solidity-agent-kit
DeFi Security Principles Language Rule Always respond in the same language the user is using. If the user asks in Chinese, respond in Chinese. If in English, respond in English. Scope : Only applicable to DeFi projects (DEX, lending, staking, LP, yield). Non-DeFi projects can ignore this skill. Protection Decision Rules Threat Required Protection Whale manipulation Daily transaction caps + per-tx amount limits + cooldown window MEV / sandwich attack EOA-only checks ( msg.sender == tx.origin ), o...
 57