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
17351 gtm-reporting aimonk2025/google-tag-manager-automation
GTM Reporting - Documentation & Impact Analysis Generate comprehensive documentation and analyze the reporting impact of your GTM tracking implementation. Core Mission Transform technical tracking implementation into business-focused documentation that: Explains what was implemented (technical docs) Shows what insights are now possible (reporting impact) Recommends specific reports to build (GA4 configurations) Defines high-value audiences (remarketing/segmentation) Translates events into busine...
 42
17352 debugging lobbi-docs/claude
Debugging When to use this skill Encountering runtime errors or exceptions Code produces unexpected output or behavior Performance degradation or memory issues Intermittent or hard-to-reproduce bugs Understanding unfamiliar error messages Post-incident analysis and prevention Instructions Step 1: Gather Information Collect all relevant context about the issue: Error details : Full error message and stack trace Error type (syntax, runtime, logic, etc.) When did it start occurring? Is it reproduci...
 42
17353 grief-companion erichowens/some_claude_skills
Grief Companion A compassionate guide for those navigating loss. This skill provides grief education, memorial creation support, practical guidance for difficult tasks, and ongoing companionship through the non-linear journey of bereavement. Core Philosophy Grief is not a problem to be solved—it's a process to be honored. This skill: Never rushes healing or implies timelines Validates all forms of grief (death, divorce, job loss, health changes) Acknowledges that grief is non-linear and unpr...
 42
17354 radix-primitives yonatangross/orchestkit
Unstyled, accessible React components for building high-quality design systems. Overview - Building custom styled components with full accessibility - Understanding how shadcn/ui works under the hood - Need polymorphic composition without wrapper divs - Implementing complex UI patterns (modals, menus, tooltips) Primitives Catalog Overlay Components | Dialog | Modal dialogs, forms, confirmations | AlertDialog | Destructive action confirmations | Sheet | Side panels, mobile drawe...
 42
17355 writer-agent hoangvantuan/claude-plugin
Writer Agent Transform documents and URLs into styled article series. Quick Reference Reference Purpose Load at Step DP T1 T2 T3 directory-structure.md Output folder layout Step 1 ✓ ✓ ✓ ✓ decision-trees.md Workflow decision guides On confusion only ✓ ✓ ✓ ✓ retry-workflow.md Error recovery procedures On error only - ✓ ✓ ✓ large-doc-processing.md Handling documents >50K words Step 3 (if >20K) - - ✓ ✓ article-writer-prompt.md Subagent prompt templates Step 4 - ✓ ✓ ✓ context-extractor-prompt.md Cont...
 42
17356 essay-polish clyderankin/essay-skills
Essay Polish You are the final step in a professional essay pipeline. The heavy lifting is done. Now you're bringing out the shine—rhythm, word choice, consistency—and giving your honest assessment of the finished work. Prerequisites The essay should have passed through: /essay-review with a "Ready for polish" verdict, OR /essay-revise addressing all critical issues from the review If the essay hasn't been reviewed, warn the user: "I can polish this, but I'd recommend running /essay-review first...
 42
17357 router-main vasilyu1983/ai-agents-public
Router: Main Universal entry point for the shared skill library. Use this router when the request is ambiguous, cross-domain, or you need a fast handoff to the best domain router. Routing Workflow Restate the user goal in 1 sentence (what "done" looks like). Choose the primary router. If confidence is below 0.8 or multiple routers tie, ask 1 clarifying question before routing. For multi-domain requests, run a short chain (max 2 routers at a time) and tell the user what you're doing. Router Sel...
 42
17358 probe simota/agent-skills
Probe Probe is the dynamic security testing specialist. Use it to prove exploitability in running systems, validate static findings from Sentinel, design penetration test plans, and produce actionable DAST reports. Trigger Guidance Use Probe when the task involves: OWASP ZAP, Burp Suite, Nuclei, DAST, penetration testing, or runtime exploit verification Validating whether a static finding is actually exploitable Testing authentication, authorization, session handling, rate limiting, GraphQL, OAu...
 42
17359 altinity-expert-clickhouse-memory altinity/skills
Memory Usage and OOM Diagnostics Diagnose RAM usage, memory pressure, OOM risks, and memory allocation patterns. Quick Diagnostics 1. Current Memory Overview with (select value from system.asynchronous_metrics where metric = 'OSMemoryTotal') as total, (select value from system.asynchronous_metrics where metric = 'MemoryResident') as resident, (select value from system.asynchronous_metrics where metric = 'OSMemoryFreeWithoutCached') as free_without_cached, (select value from sys...
 42
17360 financial-news aws-samples/sample-strands-agent-with-agentcore
Financial Market Available Tools stock_quote(symbol) : Get current stock quote with key metrics. symbol (string, required): Stock ticker symbol (e.g., "AAPL", "GOOGL", "MSFT") stock_history(symbol, period?) : Get historical stock price data for charting and trend analysis. symbol (string, required): Stock ticker symbol period (string, optional, default: "1mo"): Time period (e.g., "1mo", "3mo", "6mo", "1y", "5y") financial_news(symbol, count?) : Get latest financial news articles for a stock. sym...
 42
17361 effector-playbook neolite/effector-playbook
Concise ruleset for writing correct and testable Effector code. Each rule has a short rationale and examples. When to Apply Use this skill when: - Implementing or refactoring Effector models and flows - Debugging race conditions, stale reads, or effect errors - Writing SSR-safe logic or tests with scopes - Enforcing architecture via linting or reviews - The project already uses Effector and you need to analyze or improve its architecture - The user asks to design or review an Effector-b...
 42
17362 kor-ui korsoftwaresolutions/ui
KorUI Library KorUI (@korsolutions/ui) is a minimal-dependency, cross-platform UI library for React Native and Expo. Flexible components with beautiful default styling, compound component patterns, and comprehensive theming support. Core Principles Beautiful Defaults : Components ship with production-ready styling and a flexible variant system Compound Components : All components follow Root + sub-component pattern Variant System : Each component offers multiple style variants Minimal Dependenci...
 42
17363 tuzi-xhs-images tuziapi/tuzi-skills
Xiaohongshu Infographic Series Generator Break down complex content into eye-catching infographic series for Xiaohongshu with multiple style options. Usage Auto-select style and layout based on content /tuzi-xhs-images posts/ai-future/article.md Specify style /tuzi-xhs-images posts/ai-future/article.md --style notion Specify layout /tuzi-xhs-images posts/ai-future/article.md --layout dense Combine style and layout /tuzi-xhs-images posts/ai-future/article.md --style notion --layout list Dire...
 42
17364 discord-automation davepoon/buildwithclaude
Discord Automation via Rube MCP Automate Discord operations through Composio's Discord/Discordbot toolkits via Rube MCP. Toolkit docs : composio.dev/toolkits/discord Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Discord connection via RUBE_MANAGE_CONNECTIONS with toolkits discord and discordbot Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys nee...
 42
17365 coo-social-media lotosbin/claude-skills
No SKILL.md available for this skill. View on GitHub
 42
17366 copywriting dengineproblem/agents-monorepo
Copywriting You are an expert conversion copywriter. Your goal is to write marketing copy that is clear, compelling, and drives action. Before Writing 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 not provided): 1. Page Purpose What type of pag...
 42
17367 exaggeration-mastery dylantarre/animation-principles
Exaggeration Mastery The Truth Beyond Realism Exaggeration isn't about making things unrealistic—it's about making things feel true. A perfect photographic copy of motion often feels dead on screen. Animation requires pushing beyond literal reality to capture the essence of movement, emotion, and intent. Core Theory The camera lies: Film loses dimension, haptic feedback, and environmental immersion. What reads clearly in real life often flattens on screen. Exaggeration compensates for this lo...
 42
17368 htmx-expert oimiragieo/agent-studio
Htmx Expert htmx additional instructions When reviewing or writing code, apply these guidelines: Use semantic HTML5 elements Implement proper CSRF protection Utilize HTMX extensions when needed Use hx-boost for full page navigation Implement proper error handling Follow progressive enhancement principles Use server-side templating (e.g., Jinja2, Handlebars) htmx and django best practices general When reviewing or writing code, apply these guidelines: Use Django's template system with HTMX at...
 42
17369 groove-utilities-memory-mistakes andreadellacorte/groove
groove-utilities-memory-mistakes Use $ARGUMENTS as the mistake description if provided (e.g. --list to show open incidents only). Outcome The workflow mistake is logged, its root cause is fixed in the relevant memory or learned file, and the lesson is graduated to .groove/memory/learned/<topic>.md . The incident is closed. Acceptance Criteria Incident is recorded with root cause and fix Permanent fix applied to .groove/memory/learned/<topic>.md Incident marked resolved Task backend Read tasks.ba...
 42
17370 balatro-mod-dev liafonx/open-balatro
Balatro Mod Development Create and debug Balatro mods with Steamodded, Lovely, and SMODS. Quick Agent Selection When researching or writing code, spawn the right sub-agent via the Task tool : Need to find... Use agent Model Search boundary Game function implementation game-source-researcher sonnet Balatro_src/ only SMODS API usage/hooks smods-api-researcher sonnet smods/ only How other mods do X mod-pattern-researcher sonnet Mods/ folder only Lovely patch syntax lovely-patch-researcher sonnet lo...
 42
17371 naturalistic-motion dylantarre/animation-principles
Naturalistic Motion Think like a biologist watching life unfold. Nothing in nature moves mechanically. Everything breathes, adjusts, responds. Life is continuous subtle motion. Core Mental Model Before animating anything alive, ask: What is this creature feeling and responding to? Living things are never truly still. They shift weight, breathe, notice, adjust. Naturalistic motion isn't about copying reality—it's about capturing aliveness. The 12 Principles Through Organic Life Secondary Ac...
 42
17372 tuzi-compress-image tuziapi/tuzi-skills
Image Compressor Compresses images using best available tool (sips → cwebp → ImageMagick → Sharp). Script Directory Scripts in scripts/ subdirectory. Replace ${SKILL_DIR} with this SKILL.md's directory path. Script Purpose scripts/main.ts Image compression CLI Preferences (EXTEND.md) Use Bash to check EXTEND.md existence (priority order): Check project-level first test -f .tuzi-skills/tuzi-compress-image/EXTEND.md && echo "project" Then user-level (cross-platform: $HOME works on macOS/Linux/WS...
 42
17373 groove-admin-claude-hooks andreadellacorte/groove
groove-admin-claude-hooks Install groove's Claude Code native shell hooks. These run outside the model — deterministic, unconditional — and complement groove's advisory markdown hooks ( .groove/hooks/start.md , end.md ). Use --disable <hook> to remove a specific hook. Use --list to show current status. Outcome Selected hooks are registered in .claude/settings.json and shell scripts are written to .groove/hooks/claude/ . Hooks fire automatically on Claude Code lifecycle events without any model i...
 42
17374 context-optimization eyadsibai/ltk
Context Optimization Techniques Context optimization extends the effective capacity of limited context windows through strategic compression, masking, caching, and partitioning. The goal is not to magically increase context windows but to make better use of available capacity. Effective optimization can double or triple effective context capacity without requiring larger models or longer contexts. When to Activate Activate this skill when: Context limits constrain task complexity Optimizing ...
 42
17375 airflow-expert personamanagmentlayer/pcl
You are an expert in Apache Airflow with deep knowledge of DAG design, task orchestration, operators, sensors, XComs, dynamic task generation, and production operations. You design and manage complex data pipelines that are reliable, maintainable, and scalable. Core Expertise DAG Fundamentals Basic DAG Structure: ``` from airflow import DAG from airflow.operators.python import PythonOperator from airflow.operators.bash import BashOperator from datetime import datetime, timedelta Default ...
 42
17376 biddeed-2025-complete-analysis breverdbidder/life-os
BidDeed.AI 2025 Complete Analysis Skill Purpose Generate comprehensive year-end retrospective analysis across all domains: Business (BidDeed.AI/Everest Capital USA), Technical Architecture, Michael D1 Swimming, and Family & Personal Life. When to Use Annual retrospectives (year-end reviews) Strategic planning sessions (analyzing past to inform future) Investor/stakeholder presentations (demonstrating value created) Team performance reviews (autonomous AI team effectiveness) Personal reflection (...
 42
17377 follow-through-overlapping dylantarre/animation-principles
Nothing stops all at once. When a character halts, their hair keeps moving. When a car brakes, passengers lurch forward. Follow through and overlapping action capture how different parts of a system respond to forces at different rates—the principle that makes animation feel physically grounded. Core Theory: Two Related Concepts Follow Through: When the main body stops, appendages continue moving due to momentum, then settle. The termination behavior of motion. Overlapping Action: Different ...
 42
17378 1k-create-pr onekeyhq/app-monorepo
Create OneKey App PR Automates the complete PR creation workflow for OneKey app-monorepo changes. Quick Reference Step Action Commands 1 Check status git status , git branch --show-current 2 Create branch (if on x) git checkout -b <branch-name> 3 Lint fix yarn lint --fix 4 Stage & commit git add . , git commit -m "type: description" 5 Push to remote git push -u origin <branch-name> 6 Extract context Analyze conversation for intent, decisions, risks 7 Create PR gh pr create --base x --title "..."...
 42
17379 code-review sammcj/agentic-coding
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...
 42
17380 team-planex catlog22/claude-code-workflow
Team PlanEx Unified team skill: plan-and-execute pipeline for issue-based development. Built on team-worker agent architecture — coordinator orchestrates, workers are team-worker agents loading role-specific instructions from roles/<role>/role.md . Architecture Skill(skill="team-planex", args="task description") | SKILL.md (this file) = Router | +--------------+--------------+ | | no --role flag --role <name> | | Coordinator ...
 42
17381 cloudflare-deploy tech-leads-club/agent-skills
Cloudflare Deploy 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 Trees "I ne...
 42
17382 continual-learning cursor/plugins
Continual Learning Keep AGENTS.md current using transcript deltas instead of full rescans. Inputs Transcript root: ~/.cursor/projects/<workspace-slug>/agent-transcripts/ Existing memory file: AGENTS.md Incremental index: .cursor/hooks/state/continual-learning-index.json Workflow Read existing AGENTS.md first. Load incremental index if present. Discover transcript files and process only: new files not in index, or files whose mtime is newer than indexed mtime. Extract only high-signal, reusable i...
 42
17383 design-sync chmouel/lazyworktree
DESIGN.md Synchronization Check Verify that DESIGN.md accurately reflects the current codebase architecture. Current Directory Structure ! ls -la internal/ | grep '^d' DESIGN.md Directory Section ! sed -n '/^ Directory Structure/,/^ /p' DESIGN.md | head -50 Critical File References from DESIGN.md ! grep -oE 'internal/[a-z/]+\.go:[0-9]+-[0-9]+' DESIGN.md | sort -u Recent Changes Since Last DESIGN.md Update ! git log --since="$(git log -1 --format=%ai DESIGN.md 2>/dev/null || echo '1 month ago')" ...
 42
17384 github-labels laurigates/claude-plugins
GitHub Labels Reference for discovering and applying labels to GitHub PRs and issues. Discovering Available Labels List all labels with details gh label list --json name,description,color --limit 50 Search for specific labels gh label list --search "bug" Output as simple list gh label list --json name -q '.[].name' Adding Labels to PRs Single label gh pr create --label "bug" Multiple labels (repeat flag) gh pr create --label "bug" --label "priority:high" Comma-separated gh pr create --labe...
 42
17385 laravel:form-requests jpcaparas/superpowers-laravel
Promote validation and authorization to dedicated Form Request classes. Keep controllers focused on orchestration and domain intents. Commands ``` Create a request sail artisan make:request UpdateProfileRequest or: php artisan make:request UpdateProfileRequest Use in controller method signature public function update(UpdateProfileRequest $request) { $data = $request->validated(); // ... } ``` Patterns - Define `authorize()` to gate access; prefer Policies for complex chec...
 42
17386 azure-resource-manager-cosmosdb-dotnet sickn33/antigravity-awesome-skills
Azure.ResourceManager.CosmosDB (.NET) Management plane SDK for provisioning and managing Azure Cosmos DB resources via Azure Resource Manager. ⚠️ Management vs Data Plane This SDK (Azure.ResourceManager.CosmosDB) : Create accounts, databases, containers, configure throughput, manage RBAC Data Plane SDK (Microsoft.Azure.Cosmos) : CRUD operations on documents, queries, stored procedures execution Installation dotnet add package Azure.ResourceManager.CosmosDB dotnet add package Azure.Identity Curre...
 42
17387 azure-cosmos-ts sickn33/antigravity-awesome-skills
@azure/cosmos (TypeScript/JavaScript) Data plane SDK for Azure Cosmos DB NoSQL API operations — CRUD on documents, queries, bulk operations. ⚠️ Data vs Management Plane This SDK (@azure/cosmos) : CRUD operations on documents, queries, stored procedures Management SDK (@azure/arm-cosmosdb) : Create accounts, databases, containers via ARM Installation npm install @azure/cosmos @azure/identity Current Version : 4.9.0 Node.js : >= 20.0.0 Environment Variables COSMOS_ENDPOINT = https:// < account > ....
 42
17388 distance-calculator dkyazzentwatwa/chatgpt-skills
Distance Calculator Calculate geographic distances and find nearby locations using various methods. Features Point-to-Point Distance: Haversine, Vincenty, great circle Matrix Distances: All pairs distances Nearest Neighbors: Find closest N points Radius Search: Find all points within distance Batch Processing: Process CSV files Multiple Units: km, miles, meters, nautical miles Quick Start from distance_calc import DistanceCalculator calc = DistanceCalculator() Simple distance dist = calc.di...
 42
17389 ceo-skill guo-yu/skills
CEO Skill Your intelligent project management dashboard. Think like a CEO - get a bird's-eye view of all your projects, prioritized by potential value and urgency. Role Setting When this skill is invoked, you adopt the persona of: A successful businessman, marketing master, and serial entrepreneur who has: Built and exited multiple startups Deep understanding of product-market fit Expertise in go-to-market strategies and user acquisition Sharp instincts for identifying viable business oppor...
 42
17390 youtube-data zeropointrepo/youtube-skills
YouTube Data YouTube data access via TranscriptAPI.com — lightweight alternative to Google's YouTube Data API. Setup If $TRANSCRIPT_API_KEY is not set, help the user create an account (100 free credits, no card): Step 1 — Register: Ask user for their email. node ./scripts/tapi-auth.js register --email USER_EMAIL → OTP sent to email. Ask user: "Check your email for a 6-digit verification code." Step 2 — Verify: Once user provides the OTP: node ./scripts/tapi-auth.js verify --token TOKEN_FROM_STEP...
 42
17391 code-formatter-installer patricio0312rev/skills
Code Formatter & Linter Installer Establish consistent code formatting and linting across your project. Core Workflow Detect stack: Identify language/framework (JS/TS, Python, Go, Rust) Choose tools: Select appropriate formatters and linters Generate configs: Create config files with best-practice rules Add scripts: Include npm/package scripts for format/lint Configure editor: Provide VS Code, IntelliJ, Vim settings Setup pre-commit: Add git hooks for automatic formatting CI integration: Sugge...
 42
17392 laravel:api-resources-and-pagination jpcaparas/superpowers-laravel
Represent models via Resources; keep transport concerns out of Eloquent. Commands ``` Resource sail artisan make:resource PostResource or: php artisan make:resource PostResource Controller usage return PostResource::collection( Post::with('author')->latest()->paginate(20) ); Resource class public function toArray($request) { return [ 'id' => $this->id, 'title' => $this->title, 'author' => new UserResource($this->whenLoaded('author')), 'publishe...
 42
17393 freeze-static gravito-framework/gravito
Freeze Static Expert You are a performance-obsessed web developer specialized in static architectures. Your goal is to deliver sub-second page loads via edge networks using the Gravito @gravito/freeze ecosystem. 🏢 Strategy & Architecture 1. Build-Time Detection SOP : Use detector.isStaticSite() to toggle between Dynamic (Hydration) and Static (Native) behavior. Rule : Favor native <a> tags for navigation in static builds to eliminate JS overhead. 2. Locale-Aware Routing Rule : Every static site ...
 42
17394 router-operations vasilyu1983/ai-agents-public
Router: Operations Routes QA, testing, deployment, observability, git workflow, and documentation questions through operational skills. Routing Workflow Identify the primary user intent (what they want done). Match the intent to an operations domain (testing, debugging, resilience, observability, DevOps, git, docs). Select a primary skill and optionally 1 supporting skill if the task spans domains. If the request is mostly implementation/build work, hand off to router-engineering. If confidenc...
 42
17395 experiment simota/agent-skills
Experiment "Every hypothesis deserves a fair trial. Every decision deserves data." Rigorous scientist — designs and analyzes experiments to validate product hypotheses with statistical confidence. Produces actionable, statistically valid insights. Principles Correlation ≠ causation — Only proper experiments prove causality Learn, not win — Null results save you from bad decisions Pre-register before test — Define success criteria upfront to prevent p-hacking Practical significance — A 0.1% lift ...
 42
17396 database-replication-setup dengineproblem/agents-monorepo
Database Replication Expert Эксперт по системам репликации баз данных с глубокими знаниями архитектур репликации master-slave, master-master и кластерных решений. Основные принципы репликации Типы репликации Асинхронная : Высокая производительность, возможная потеря данных при сбоях Синхронная : Гарантия консистентности данных, повышенная задержка Полусинхронная : Баланс между производительностью и консистентностью Master-Slave : Масштабирование чтения, резервное копирование Master-Master : Геог...
 42
17397 godot-genre-rts thedivergentai/gd-agentic-skills
Genre: Real-Time Strategy (RTS) Expert blueprint for RTS games balancing strategy, micromanagement, and performance. NEVER Do NEVER pathfinding jitter — Units pushing each other endlessly. Enable RVO avoidance (NavigationAgent2D.avoidance_enabled with radius). NEVER excessive micromanagement — Automate mundane tasks (auto-attack nearby enemies, auto-resume gathering after drop-off). NEVER _process on every unit — For 100+ units, use central UnitManager iterator. Saves massive function call overh...
 42
17398 excitement-energy dylantarre/animation-principles
Excitement & Energy Animation Create animations that energize, excite, and create dynamic, high-impact experiences. Emotional Goal Excitement builds through dynamic, escalating motion. Energy comes from fast, varied animations that create momentum and keep users engaged. Disney Principles for Excitement Squash & Stretch Dynamic and impactful (20-35%). High-energy compression and extension. Objects feel springy and responsive. Anticipation Quick, building tension (100-150ms). Like a coiled...
 42
17399 vibe-matcher erichowens/some_claude_skills
Vibe Matcher A synesthete designer who translates abstract feelings and brand vibes into concrete visual language - the bridge between "I want it to feel edgy" and "Use FF006E with 800-weight Montserrat". Quick Start Minimal example to translate vibe into visual specs: User: "Make my portfolio feel edgy but still professional" Vibe Matcher: 1. Clarify domain: "Professional software engineer portfolio" 2. Confirm audience: "Technical hiring managers and recruiters" 3. Translate "edgy + profe...
 42
17400 workos-authkit-base workos/skills
WorkOS AuthKit Integration Step 1: Fetch AuthKit Documentation (BLOCKING) STOP. Do not proceed until complete. WebFetch: https://workos.com/docs/user-management/authkit This page is the source of truth for AuthKit concepts, supported frameworks, and setup requirements. If this skill conflicts with the docs, follow the docs. Step 2: Detect User's Framework Run these commands to identify the project's framework. Check each in order; use the first match. Next.js grep -q '"next"' package.json 2 > /...
 42