CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Nx

mindrally/skills
383 installs128 stars
Summary

This gets Claude up to speed on Nx monorepo conventions and workflows. You'll want it when you're scaffolding projects, setting up module boundaries, or debugging why your build cache isn't hitting. It covers the practical stuff like project.json configuration, nx affected commands for CI, and the tag-based dependency constraints that keep your architecture clean. The guidance on keeping apps thin and pushing logic into libs is solid advice that actually matters at scale. Honestly most useful when you're either setting up a new workspace or onboarding someone who needs to understand why your monorepo is organized the way it is.

Install to Claude Code

npx -y skills add mindrally/skills --skill nx --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

Nx Monorepo Development

You are an expert in Nx, the smart, fast, and extensible build system for monorepos.

Project Structure

  • Organize projects following Nx conventions:
    • apps/ - Application projects (web apps, APIs, mobile apps)
    • libs/ - Library projects (shared code, features, utilities)
  • Use consistent naming patterns: scope-type-name (e.g., shared-ui-button)
  • Group related libraries under feature folders

Workspace Configuration

Configure nx.json for workspace-wide settings:

{
  "targetDefaults": {
    "build": {
      "dependsOn": ["^build"],
      "cache": true
    },
    "test": {
      "cache": true
    }
  },
  "defaultBase": "main"
}
  • Use project.json for project-specific configuration
  • Define proper tags for enforcing module boundaries

Project Configuration

Each project should have a project.json:

{
  "name": "my-app",
  "sourceRoot": "apps/my-app/src",
  "projectType": "application",
  "tags": ["scope:web", "type:app"],
  "targets": {
    "build": { },
    "serve": { },
    "test": { }
  }
}
  • Define clear project types: application or library
  • Use tags for enforcing dependency constraints

Code Generation

  • Use Nx generators for consistent code scaffolding:
    • nx g @nx/react:app my-app - Generate React application
    • nx g @nx/react:lib my-lib - Generate React library
    • nx g @nx/react:component my-component --project=my-lib - Generate component
  • Create custom generators for project-specific patterns
  • Use --dry-run to preview changes before execution

Module Boundaries

Enforce boundaries using ESLint rules:

{
  "@nx/enforce-module-boundaries": [
    "error",
    {
      "depConstraints": [
        { "sourceTag": "type:app", "onlyDependOnLibsWithTags": ["type:lib", "type:util"] },
        { "sourceTag": "type:lib", "onlyDependOnLibsWithTags": ["type:lib", "type:util"] },
        { "sourceTag": "scope:web", "onlyDependOnLibsWithTags": ["scope:web", "scope:shared"] }
      ]
    }
  ]
}
  • Define clear dependency rules between project types
  • Use scopes to separate domain boundaries

Caching and Performance

  • Enable computation caching for faster builds
  • Configure Nx Cloud for distributed caching and task execution
  • Use affected commands to only run tasks for changed projects:
    • nx affected:build
    • nx affected:test
    • nx affected:lint
  • Define proper inputs and outputs for accurate caching

Task Execution

  • Run tasks with Nx CLI:
    • nx build my-app - Build specific project
    • nx run-many -t build - Build all projects
    • nx affected -t test - Test affected projects
  • Use task pipelines for proper dependency ordering
  • Configure parallel execution for independent tasks

Testing Strategy

  • Use Jest for unit testing with Nx presets
  • Configure Cypress or Playwright for E2E testing
  • Implement component testing for UI libraries
  • Use nx affected:test in CI for efficient test runs

CI/CD Integration

  • Use Nx Cloud for distributed task execution
  • Configure GitHub Actions with Nx:
    - uses: nrwl/nx-set-shas@v4
    - run: nx affected -t lint test build
    
  • Implement proper caching strategies
  • Use nx-cloud record for capturing metrics

Best Practices

  • Keep applications thin; move logic to libraries
  • Create shared utility libraries for common code
  • Use barrel exports (index.ts) for clean imports
  • Implement proper type exports from libraries
  • Document library purposes and public APIs
  • Use Nx Console VS Code extension for visual project management
  • Leverage the project graph for understanding dependencies: nx graph
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
First SeenJun 3, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k