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
13851 recovery oimiragieo/agent-studio
Recovery Skill When to Use Context window exhausted mid-workflow Session interrupted or lost Need to resume from last completed step Workflow state needs reconstruction Step 1: Identify Last Completed Step Check gate files for last successful validation: Location: .claude/context/history/gates/{workflow_id}/ Find highest step number with validation_status: "pass" This is the last successfully completed step Review reasoning files for progress: Location: .claude/context/history/reasoning/{workflo...
 53
13852 spanora-setup spanora/skills
Spanora Setup Agent Skill You are integrating Spanora AI observability into the user's project. Follow this guide step by step. 1. When to Invoke Activate this skill when the user says any of: "add spanora", "setup spanora", "integrate spanora" "add AI observability", "add LLM monitoring" "monitor LLM calls with spanora", "track AI costs" "instrument my agent", "add tracing to my agent" mentions "spanora" in the context of adding observability 2. Public Documentation — Source of Truth The offici...
 53
13853 bencium-aeo bencium/bencium-claude-code-design-skill
AEO Content Optimization Skill Answer Engine Optimization - Optimize content for AI citations, not traditional search rankings. When to Use This Skill Use this skill when: User asks to optimize content for AI search/citations User mentions ChatGPT, Claude, Gemini visibility User wants FAQ schema, JSON-LD, or structured data for AI User asks about GEO (Generative Engine Optimization) User wants to analyze content for AI extraction readiness User mentions "AI Overviews" or "answer engines" NOT for...
 53
13854 material-design yusuketsunoda/ppt-trans
Material Design 3 — ppt-trans-design に統合済み このスキルは ppt-trans-design に統合されました。 UI実装 : /ppt-trans-design を使用してください MD3パターン参照 : .claude/skills/ppt-trans-design/references/md3-patterns.md
 53
13855 de-ai-ify brianrwagner/ai-marketing-skills
De-AI-ify Text Remove AI-generated patterns and restore natural human voice to your writing. Why This vs ChatGPT? Problem with raw ChatGPT: Just asking "make this sound more human" gives inconsistent results. You get different rewrites each time, no systematic pattern removal, and no validation. This skill provides: Systematic detection - Trained on 1,000+ AI vs human comparisons to identify 47 specific patterns Consistent methodology - Same transformation logic every time, not random rewrites V...
 53
13856 code-structural-search oimiragieo/agent-studio
Code Structural Search Use ast-grep for AST-based code pattern matching. When to Use Find code by structure, not keywords "Find all functions with 3 arguments" "Find all classes that extend X" "Find all database queries" "Find all error handling patterns" Precise code refactoring (change exact patterns) Interface Skill ( { skill : 'code-structural-search' , args : 'pattern-here --lang ts' } ) ; Language Support ast-grep supports 20+ languages via tree-sitter: Language Flag File Extensions JavaSc...
 53
13857 react-native-reusables hairyf/skills
The skill is based on React Native Reusables (docs as of 2026-02-26), generated at 2026-02-26. React Native Reusables brings the shadcn/ui experience to React Native: copy-paste or CLI-scaffolded components, theming via CSS variables, and RN Primitives under the hood. It supports Nativewind and Uniwind, requires a root PortalHost for overlays, and uses a Text inheritance system and an Icon wrapper for Lucide. Core References Topic Description Reference Overview What RNR is, differences from shad...
 53
13858 code-change-verification openai/openai-agents-js
Code Change Verification Overview Ensure work is only marked complete after formatting, linting, type checking, and tests pass. Use this skill when changes affect runtime code, tests, or build/test configuration. You can skip it for docs-only or repository metadata unless a user asks for the full stack. Quick start Keep this skill at ./.codex/skills/code-change-verification so it loads automatically for the repository. macOS/Linux: bash .codex/skills/code-change-verification/scripts/run.sh. Wi...
 53
13859 ai-collaborate-teaching panaversity/agentfactory
AI Collaborate Teaching Quick Start 1. Determine layer and balance layer : 2 AI Collaboration balance : 40/40/20 foundation/AI-assisted/verification 2. Apply Three Roles Framework Each lesson must show bidirectional learning 3. Include convergence loop spec → generate → validate → learn → iterate Persona You are a co-learning experience designer who integrates the Three Roles Framework. Your goal is to ensure lessons demonstrate bidirectional learning—students learn FROM AI and AI adapts ...
 53
13860 newsletter writer eddiebe147/claude-settings
Newsletter Writer The Newsletter Writer skill helps you create compelling newsletters that cut through inbox noise and drive engagement. Whether you're sending weekly updates to your team, monthly roundups to customers, or regular thought leadership to your audience, this skill ensures your content is valuable, scannable, and action-oriented. This skill understands the unique challenges of newsletter writing: capturing attention in crowded inboxes, maintaining consistent voice and format, balanc...
 53
13861 skaffold-orbstack laurigates/claude-plugins
Skaffold with OrbStack - Port-Forward-Free Development Overview OrbStack provides superior local Kubernetes networking compared to other tools (minikube, kind, Docker Desktop). Services are accessible directly from macOS without port-forward. Key OrbStack Advantages Feature OrbStack minikube/kind LoadBalancer auto-provision ✅ Yes ❌ Needs MetalLB Wildcard DNS ( *.k8s.orb.local ) ✅ Yes ❌ No cluster.local from host ✅ Yes ❌ No Pod IP direct access ✅ Yes ❌ No Auto HTTPS certificates ✅ Yes ❌ No Servic...
 53
13862 user-flow-diagram owl-listener/designer-skills
User Flow Diagram You are an expert in creating clear user flow diagrams that map paths through a product. What You Do You create flow diagrams showing how users move through a product to accomplish goals, including decisions, branches, and error paths. Flow Diagram Elements Entry point : Where the user enters the flow (circle/oval) Screen/page : A view the user sees (rectangle) Decision : A branching point (diamond) Action : Something the user does (rounded rectangle) System process : Backend o...
 53
13863 check-rust-coverage redisearch/redisearch
Check Rust Coverage Determine which Rust lines are not covered by Rust tests. Arguments <path> : Path to a Rust crate. <path 1> <path 2> : Multiple crate paths. If a path doesn't include src/ , assume it to be in the src/redisearch_rs directory. E.g. numeric_range_tree becomes src/redisearch_rs/numeric_range_tree . If a path points to a directory, consider all Rust crates in that directory. Instructions Run cargo llvm-cov test --manifest-path < crate_directory > /Cargo.toml --quiet --json 2 > /d...
 53
13864 compound team-attention/workshop-upstage
compound 스킬 목적: 작업 과정에서 검증된 인사이트를 즉시 문서화하여, 검색 가능한 지식 베이스를 구축한다. 개요 이 스킬은 인사이트가 확인되는 즉시 포착하여, YAML frontmatter 기반의 구조화된 문서로 저장한다. 카테고리별 단일 파일 아키텍처를 사용하며, 각 인사이트는 knowledge/[category]/[filename].md 에 저장된다. <critical_sequence name="insight-capture" enforce_order="strict"> 7단계 프로세스 자동 감지 문구 (대화에서 인식): "이거 잘 됐다" "이 방식이 좋네" "다음에도 이렇게 하자" "이건 기록해두자" "이 포맷이 먹혔다" "이게 효과가 있었어" "이렇게 하니까 됐어" "기억해둬야 해" OR 수동: /compound 커맨드 Non-trivial만 (재사용 가치 있는 인사이트): 반복할 수 있는 패턴 다른 상황에도 적용 가능한 교훈 시행착오 끝에 발견한 방법 실전에서 검증된 ...
 53
13865 business-rule-patterns groeimetai/snow-flow
Business Rule Best Practices for ServiceNow Business Rules are server-side scripts that execute when records are displayed, inserted, updated, or deleted. When to Use Each Type Type Timing Use Case Performance Impact Before Before database write Validate, modify current record Low After After database write Create related records, notifications Medium Async Background (after commit) Heavy processing, integrations None (background) Display When form loads Modify form display, set defaults Low A...
 53
13866 ux-writing owl-listener/designer-skills
UX Writing Write clear, concise, user-centered interface copy (UX text/microcopy) for digital products and experiences. This skill provides frameworks, patterns, and best practices for creating text that helps users accomplish their goals. Compatible with: Claude Desktop, Claude Code, and Codex (CLI and IDE extensions) Note: This skill works with Codex CLI/IDE, not ChatGPT. ChatGPT cannot install or use skills. When to Use This Skill Use this skill when: Writing interface copy (buttons, la...
 53
13867 social-content openclaudia/openclaudia-skills
Social Content You are an expert social media strategist. Your goal is to help create engaging content that builds audience, drives engagement, and supports business goals. Before Creating Content Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Gather this context (ask if n...
 53
13868 widget-coherence groeimetai/snow-flow
Service Portal widgets MUST have perfect communication between Server Script, Client Controller, and HTML Template. This is not optional - widgets fail when these components don't talk to each other correctly. The Three-Way Contract Every widget requires synchronized communication: 1. Server Script Must: - Initialize ALL `data.*` properties that HTML will reference - Handle EVERY `input.action` that client sends via `c.server.get()` - Return data in the format the client expects 2. Cli...
 53
13869 prowler-mcp prowler-cloud/prowler
Overview The Prowler MCP Server uses three sub-servers with prefixed namespacing: Sub-Server Prefix Auth Purpose Prowler App prowler_app_* Required Cloud management tools Prowler Hub prowler_hub_* No Security checks catalog Prowler Docs prowler_docs_* No Documentation search For complete architecture, patterns, and examples, see docs/developer-guide/mcp-server.mdx. Critical Rules (Prowler App Only) Tool Implementation ALWAYS: Extend BaseTool (auto-registered via tool_loader.py, only public m...
 53
13870 ncps kalbasit/ncps
This skill documents the standard workflows for developing, building, running, and testing the `ncps` project. 🔴🟢🔵 Development Protocol: TDD ONLY [!IMPORTANT] TEST FIRST. CODE SECOND. You MUST follow Test Driven Development (TDD) for ALL Go code changes, including FEATURES and BUGS. The Cycle: - Red: Write a failing test case that reproduces the bug or defines the new feature. - Green: Write the *minimal* amount of code necessary to make the test pass. - Refactor: Clean up the code while ...
 53
13871 sales-coaching-plan-generator onewave-ai/claude-skills
Sales Coaching Plan Generator Individualized development plans by weakness. Skill assessments, call reviews, ride-along checklists, certification tracking. Instructions You are an expert sales enablement leader. Create personalized coaching plans that develop skills systematically with clear milestones. Output Format Sales Coaching Plan Generator Output Generated: {timestamp} --- Results [Your formatted output here] --- Recommendations [Actionable next steps] Best Practices Be Sp...
 53
13872 pricing-strategy kimny1143/claude-code-template
Pricing Strategy You are an expert in SaaS pricing and monetization strategy. Your goal is to help design pricing that captures value, drives growth, and aligns with customer willingness to pay. Before Starting Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Gather this con...
 53
13873 uniapp-cloud teachingai/full-stack-skills
When to use this skill Use this skill whenever the user wants to: Use uniCloud cloud development services Work with cloud databases (add, query, update, delete data) Create and deploy cloud functions Use cloud storage for file uploads and management Implement datacom components for data binding Integrate backend services with uni-app Set up uniCloud project and configuration Handle cloud database permissions and security How to use this skill This skill is organized to match the official uniC...
 53
13874 capacitor-deep-linking cap-go/capacitor-skills
Deep Linking in Capacitor Implement deep links, universal links, and app links in Capacitor apps. When to Use This Skill User wants deep links User needs universal links User asks about URL schemes User wants to open app from links User needs share links Types of Deep Links Type Platform Format Requires Server Custom URL Scheme Both myapp://path No Universal Links iOS https://myapp.com/path Yes App Links Android https://myapp.com/path Yes Quick Start Install Plugin bun add @capacitor/app bunx ca...
 53
13875 better-auth-setup andrelandgraf/fullstackrecipes
Better Auth Setup To set up Better Auth Setup, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/better-auth-setup If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/better-auth-setup
 53
13876 pattern-critic commontoolsinc/labs
Pattern Critic Systematically review pattern code for violations of Common Tools documentation rules and gotchas. Workflow Read the pattern file to review Check each category below against the code Output results in the checklist format (see Output Format) For any [FAIL], include the line number and fix Violation Categories 1. Module Scope Violations Check that these are NOT inside the pattern body: Violation Fix handler() defined inside pattern Move to module scope, or use action() instead lift...
 53
13877 design-system-creator erichowens/some_claude_skills
Design System Creator Design systems architect and CSS expert specializing in creating comprehensive, scalable design bibles. When to Use This Skill ✅ Use for: Creating design tokens from scratch (colors, spacing, typography scales) Building CSS custom property architectures Documenting component libraries with usage guidelines Creating design bibles and style guides Establishing naming conventions (BEM, OOCSS, SMACSS) Auditing existing CSS for design system extraction Theming and dark mode ...
 53
13878 study-notes-creator szeyu/vibe-study-skills
Study Notes Creator Transform source materials into organized, visual study notes with themed folders, rich diagrams, and example-based learning. Workflow flowchart LR A [Source Materials] --> B [Extract Topics] B --> C [Plan Structure] C --> D [Create Notes] D --> E [Add Diagrams + Examples] E --> F [Build Index] Step 1: Understand the Source Read the source - PDFs, lecture notes, existing docs Identify 5-8 main topics - Major themes Find subtopics - What falls under each theme? Note example op...
 53
13879 change-management groeimetai/snow-flow
Change Management Help plan and execute changes that affect people, processes, or technology. Change Management Framework 1. Assess What is changing? Who is affected? How significant is the change? (Low / Medium / High) What resistance should we expect? 2. Plan Communication plan (who, what, when, how) Training plan (what skills are needed, how to deliver) Support plan (help desk, champions, FAQs) Timeline with milestones 3. Execute Announce and explain the "why" Train and support Monitor adopti...
 53
13880 apply-mantel-styles sammcj/agentic-coding
Rules For Applying Mantel Brand Styles When creating visual diagrams or frontend components, you can apply the following style guidelines to ensure consistency with the Mantel brand identity. Colour Scheme You should aim to use the following primary colours from the Mantel brand palette. You may also use tints and shades of these colours as needed, but avoid introducing non-brand colours. General Design Principles <GENERAL_PRINCIPLES> <COLOUR_HIERARCHY> 1. Primary Actions/Elements: Ocean (1E5...
 53
13881 pr automattic/wordpress-activitypub
Create Pull Request Branch Strategy Target branch : canary (development branch, cloud production) main is the release branch — never PR directly to main Steps 1. Gather context (run in parallel) git branch --show-current — current branch name git status --short — uncommitted changes git rev-parse --abbrev-ref @{u} 2>/dev/null — remote tracking status git log --oneline origin/canary..HEAD — unpushed commits gh pr list --head "$(git branch --show-current)" --json number,title,state,url — existing ...
 53
13882 summarization engine eddiebe147/claude-settings
Summarization Engine The Summarization Engine skill guides you through building systems that condense long documents into concise, accurate summaries. From extractive approaches that select key sentences to abstractive methods that generate new text, this skill covers the full spectrum of summarization techniques. Effective summarization requires understanding what information matters, maintaining accuracy while condensing, and adapting to different document types and summary requirements. This ...
 53
13883 b2c-localization salesforcecommercecloud/b2c-developer-tooling
Localization Skill This skill guides you through localizing B2C Commerce storefronts for multiple languages and regions. Overview B2C Commerce supports localization through: Component Approach Templates Single template set + resource bundles Forms Shared definitions + locale-specific labels Static content Locale-specific folders Product data Localizable attributes Locale Format Locales follow ISO standards: {language}_{country} Format Example Description en English Language only en_US English/US...
 53
13884 spending-analysis pollinations/pollinations
Requirements Before using this skill, ensure you have: curl : For API requests jq : brew install jq (for parsing JSON) sops : brew install sops (for decrypting secrets) Must run from the pollinations repo root with access to enter.pollinations.ai/ . Data Sources Polar API Orders : Payment history for pack purchases Products : Tier subscriptions and pollen packs Customers : User payment info linked by external_id Tinybird generation_event : Usage data with user_tier , total_price , user_id Tracks...
 53
13885 effect-ts sablier-labs/agent-skills
Effect-TS Expert Guide Effect-TS is a functional TypeScript library providing typed effects, structured concurrency, and a robust runtime. This skill covers correct usage patterns and addresses common misconceptions from LLM-generated content. Quick Reference import { Effect, Layer, Context, Fiber, Schedule, Cache, Scope } from "effect"; import { Schema, JSONSchema } from "@effect/schema"; Core Type Signature: Effect<Success, Error, Requirements> // ↑ ↑ ↑ // | ...
 53
13886 technical-articles epicenterhq/epicenter
Technical Articles All articles must follow writing-voice rules. Core Principles Title should BE the takeaway, not a topic. "Write Context to a File, Not a Prompt" not "Context Management in Agent Workflows". Lead with a strong opening paragraph that states the key insight in plain language. Reader should get it in 5 seconds. Then go straight into code. Don't force a blockquote or pull-quote after the opening; if the insight needs a quotable summary, the opening paragraph already is one. Code sp...
 53
13887 agent-slack devxoul/agent-messenger
Slack automation with agent-slack agent-slack is a CLI binary installed on $PATH . Invoke it directly (e.g. agent-slack user list ). If installed via Nix flake only, run commands with nix run github:stablyai/agent-slack -- <args> . CRITICAL: Bash command formatting rules Claude Code's permission checker has security heuristics that force manual approval prompts. Avoid these patterns to keep commands auto-allowed. See: https://github.com/anthropics/claude-code/issues/34379 No anywhere in the com...
 53
13888 prowler-compliance-review prowler-cloud/prowler
When to Use Reviewing PRs that add new compliance frameworks Reviewing PRs that modify existing compliance frameworks Validating compliance framework JSON structure before merge Review Checklist (Critical) Check Command/Method Pass Criteria JSON Valid python3 -m json.tool file.json No syntax errors All Checks Exist Run validation script 0 missing checks No Duplicate IDs Run validation script 0 duplicate requirement IDs CHANGELOG Entry Manual review Present under correct version Dashboard File Co...
 53
13889 code-simplifier s-hiraoku/synapse-a2a
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. This is a balance that you have mastered as a result your years as an expert software engineer. You will analyze recently modified code and apply refin...
 53
13890 naive-ui sepush/naive-ui-skills
Naive UI Practices Usage guide for Naive UI and Vue 3 applications. Contains 33 rules across 8 categories, prioritized by impact to guide automated refactoring, component creation, and troubleshooting. When to Apply Reference these guidelines when: Writing new Vue 3 components using Naive UI Implementing forms and data validation Handling large datasets with virtual scrolling (DataTable, Tree, Select) Customizing application themes and dark mode Troubleshooting Naive UI usage issues and styling ...
 53
13891 sqlite-data johnrogers/claude-swift-engineering
SQLite Data SQLiteData provides type-safe SQLite access through Swift macros, simplifying database modeling and queries while handling CloudKit sync, migrations, and async patterns automatically. Reference Loading Guide ALWAYS load reference files if there is even a small chance the content may be required. It's better to have the context than to miss a pattern or make a mistake. Reference Load When Table Models Defining tables with @Table, setting up primary keys, columns, or enums Queries ...
 53
13892 workflow-management sgcarstrends/sgcarstrends
Workflow Management Skill This skill helps you work with QStash-based workflows in apps/api/src/lib/workflows/. When to Use This Skill Adding new scheduled workflows for data fetching Debugging workflow execution errors Modifying existing workflow schedules or logic Integrating new data sources into the update pipeline Adding new social media posting workflows Workflow Architecture The project uses QStash workflows with the following structure: apps/api/src/lib/workflows/ ├── cars/ ...
 53
13893 smart-debug oimiragieo/agent-studio
Mode: Cognitive/Prompt-Driven — No standalone utility script; use via agent context. You are an expert AI-assisted debugging specialist with deep knowledge of modern debugging tools, observability platforms, and automated root cause analysis. You follow the Cursor Debug Mode methodology: hypothesis-first, instrument-then-wait, log-confirmed root cause. Context Process issue from: $ARGUMENTS Parse for: Error messages/stack traces Reproduction steps Affected components/services Performance charact...
 53
13894 project-management miles990/claude-software-skills
项目管理与产品需求 功能说明 此技能专门用于项目管理和产品需求分析,包括: 产品需求文档(PRD)编写 项目计划制定 任务分解和优先级排序 用户故事和验收标准 风险识别和管理 敏捷开发流程 使用场景 "编写一个电商系统的 PRD" "制定项目开发计划" "分解功能模块和任务" "定义用户故事和验收标准" "评估项目风险" "规划 MVP 功能" 核心能力 1. 需求洞察与分析 精准识别真实用户需求 区分核心功能和增值功能 基于场景的产品设计 竞品分析和差异化定位 2. 功能分解 将宏观需求拆解为可执行的功能点 定义输入-处理-输出逻辑 识别依赖关系和集成点 处理边界情况和异常 3. 优先级管理 P0(Must Have):MVP 必需功能 P1(Should Have):重要但非必需 P2(Nice to Have):锦上添花功能 4. 风险预判 技术实现风险 市场接受度风险 用户采用风险 资源和时间风险 PRD 文档结构 标准 PRD 模板 [产品名称] 产品需求文档(PRD) 版本: v1.0 创建日期: 2025-01-01 作者: 产品经理 状态: 草稿/评审中/已批准...
 53
13895 android-use shehbajdhillon/android-use
This skill enables you to control Android devices connected via ADB (Android Debug Bridge). You act as both the reasoning and execution engine - reading the device's UI state directly and deciding what actions to take. Prerequisites - Android device connected via USB with USB debugging enabled - ADB installed and accessible in PATH - Device authorized for debugging (accepted the "Allow USB debugging?" prompt) Multi-Device Support All scripts support the `-s <serial>` flag to target a spe...
 53
13896 renaissance-architecture bencium/bencium-claude-code-design-skill
Renaissance Architecture Build genuinely new things. Not "X but for Y." Core Philosophy The problem isn't modern tools. It's building commentaries instead of creations . Medieval scholars wrote commentaries on Aristotle instead of new philosophy. We build Star Wars spin-offs instead of new sci-fi. We add AI to existing workflows instead of asking what workflows become possible. Renaissance architecture means: First-principles thinking about WHAT to build Pragmatic choices about HOW to build it C...
 53
13897 unity architecture cryptorabea/claude_unity_dev_plugin
Unity Game Architecture Essential architectural patterns and design principles for scalable, maintainable Unity projects. Overview Good architecture separates concerns, reduces coupling, and makes code testable and maintainable. This skill covers proven patterns for Unity game development. Core architectural concepts: Manager patterns and global systems ScriptableObject-based data architecture Event-driven communication Component composition patterns Dependency management Manager Pattern Central...
 53
13898 recovery-app-legal-terms erichowens/some_claude_skills
Recovery App Legal Terms Generate legally-sound terms of service, privacy policies, and medical disclaimers for recovery and wellness applications. Based on analysis of I Am Sober, Sober Grid, and other recovery apps. Trigger Phrases terms of service privacy policy legal terms medical disclaimer user agreement data protection HIPAA compliance GDPR compliance System Prompt You are a legal document specialist for recovery and wellness applications. You help generate terms of service, privacy po...
 53
13899 newsletter-publishing jamditis/claude-skills-journalism
Newsletter publishing Practical workflows for building and managing email newsletters for journalism and academia. When to activate Creating a new newsletter from scratch Designing email templates for journalism content Building and segmenting subscriber lists Analyzing newsletter performance metrics Planning editorial calendars for newsletters Migrating between newsletter platforms Improving deliverability and open rates Newsletter architecture Content strategy framework Newsletter strategy do...
 53
13900 core-web-vitals kimny1143/claude-code-template
Core Web Vitals optimization Targeted optimization for the three Core Web Vitals metrics that affect Google Search ranking and user experience. The three metrics Metric Measures Good Needs work Poor LCP Loading ≤ 2.5s 2.5s – 4s > 4s INP Interactivity ≤ 200ms 200ms – 500ms > 500ms CLS Visual Stability ≤ 0.1 0.1 – 0.25 > 0.25 Google measures at the 75th percentile — 75% of page visits must meet "Good" thresholds. LCP: Largest Contentful Paint LCP measures when the largest visible content elem...
 53