← All skill packs

Claude Code: Development & Security Skills

Skill pack
6 skills0 selected
scheune10-codingSkills in this pack

Architecture patterns from the Claude Code CLI for building AI-powered developer tools. Covers tool registry systems, permission models, agent orchestration (sub-agents, swarms, teams), skill/plugin architectures, CLI-as-React-app (Ink), deferred tool loading, bridge patterns for IDE integration, and conversation state management. Triggers on: build CLI agent, tool system design, agent orchestration pattern, skill system architecture, permission system, IDE bridge, CLI React, Ink framework, AI developer tool, agent tool registry, or any question about building AI-powered CLI tools or agent systems.

English

Recommend the right LLM agent framework for a given use case. Covers framework comparison (LangChain, LangGraph, CrewAI, AutoGen, Agno, Dify, n8n, Semantic Kernel, Haystack, LlamaIndex), decision criteria (complexity, team size, vendor lock-in, self-hosting), and migration paths. Triggers on: which AI framework, agent framework comparison, LangChain vs, CrewAI vs, AutoGen vs, LangGraph vs, which LLM framework, agent orchestration, multi-agent framework, AI framework selection, or any question about choosing an AI/LLM agent framework.

English

Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.

English

Design and architect RAG (Retrieval-Augmented Generation) pipelines. Covers vector DB selection, chunking strategies, hybrid retrieval (vector + knowledge graph), semantic caching, ingestion pipeline design, embedding model selection, and production deployment patterns. Triggers on: RAG, retrieval augmented generation, vector database, embeddings, chunking, FAISS, Qdrant, Milvus, pgvector, Weaviate, Pinecone, knowledge graph, Neo4j, semantic search, document Q&A, ingestion pipeline, reranking, hybrid search, or any question about building a RAG system.

English

Security checklist specifically for SaaS applications built with Next.js, Supabase, and Stripe. Covers authentication hardening, Row Level Security, Stripe webhook verification, secrets management, CSRF/CSP/CORS headers, input validation, rate limiting, DSGVO/GDPR compliance, and common anti-patterns found in real SaaS templates. Triggers on: SaaS security, Supabase security, Stripe security, SaaS checklist, secure SaaS, harden SaaS, SaaS audit, Next.js security, Supabase RLS audit, payment security, or any security review of a SaaS application.

English

트리거: "fastapi 만들어줘", "fastapi codegen", "fastapi 코드 생성", "fastapi 라우터 생성", "fastapi api 만들어줘" 수행: Python FastAPI 프로젝트의 Router·Pydantic Schema·Service·Dependency 계층을 자동 생성한다. async/await 패턴, 전역 에러 핸들러, 표준 응답 모델(JSONResponse), 타입 힌트를 완전히 적용한다. 출력: 디렉토리 구조 안내 + 각 파일 코드 블록 + 실행 방법 안내.

Korean

Includes Claude Code Patterns, LLM Framework Advisor, PR Review Expert, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills6CategorysecurityStars0

What’s included

Claude Code Patterns

Architecture patterns from the Claude Code CLI for building AI-powered developer tools. Covers tool registry systems, permission models, agent orchestration (sub-agents, swarms, teams), skill/plugin architectures, CLI-as-React-app (Ink), deferred tool loading, bridge patterns for IDE integration, and conversation state management. Triggers on: build CLI agent, tool system design, agent orchestration pattern, skill system architecture, permission system, IDE bridge, CLI React, Ink framework, AI developer tool, agent tool registry, or any question about building AI-powered CLI tools or agent systems.

LLM Framework Advisor

Recommend the right LLM agent framework for a given use case. Covers framework comparison (LangChain, LangGraph, CrewAI, AutoGen, Agno, Dify, n8n, Semantic Kernel, Haystack, LlamaIndex), decision criteria (complexity, team size, vendor lock-in, self-hosting), and migration paths. Triggers on: which AI framework, agent framework comparison, LangChain vs, CrewAI vs, AutoGen vs, LangGraph vs, which LLM framework, agent orchestration, multi-agent framework, AI framework selection, or any question about choosing an AI/LLM agent framework.

PR Review Expert

Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.

RAG Pipeline Architect

Design and architect RAG (Retrieval-Augmented Generation) pipelines. Covers vector DB selection, chunking strategies, hybrid retrieval (vector + knowledge graph), semantic caching, ingestion pipeline design, embedding model selection, and production deployment patterns. Triggers on: RAG, retrieval augmented generation, vector database, embeddings, chunking, FAISS, Qdrant, Milvus, pgvector, Weaviate, Pinecone, knowledge graph, Neo4j, semantic search, document Q&A, ingestion pipeline, reranking, hybrid search, or any question about building a RAG system.

Saas Security Checklist

Security checklist specifically for SaaS applications built with Next.js, Supabase, and Stripe. Covers authentication hardening, Row Level Security, Stripe webhook verification, secrets management, CSRF/CSP/CORS headers, input validation, rate limiting, DSGVO/GDPR compliance, and common anti-patterns found in real SaaS templates. Triggers on: SaaS security, Supabase security, Stripe security, SaaS checklist, secure SaaS, harden SaaS, SaaS audit, Next.js security, Supabase RLS audit, payment security, or any security review of a SaaS application.

Fastapi Codegen

트리거: "fastapi 만들어줘", "fastapi codegen", "fastapi 코드 생성", "fastapi 라우터 생성", "fastapi api 만들어줘" 수행: Python FastAPI 프로젝트의 Router·Pydantic Schema·Service·Dependency 계층을 자동 생성한다. async/await 패턴, 전역 에러 핸들러, 표준 응답 모델(JSONResponse), 타입 힌트를 완전히 적용한다. 출력: 디렉토리 구조 안내 + 각 파일 코드 블록 + 실행 방법 안내.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Claude Code Patterns skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • License details are not provided in these listings. Check the author’s terms before using the skills.
Claude Code: Development & Security Skills | Agent Skills Atlas