ai-llm-patterns
Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
195 skills found
Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.
Expert skill for building and maintaining AI agents using the Claude Agent SDK, covering architecture, tool integration, MCP servers, and agentic workflows.
Secure, isolated cloud sandbox environments for executing AI-generated code, running multi-language scripts, managing file systems, and integrating tools via the E2B MCP gateway.
A unified interface for integrating and managing LLM chat providers like OpenAI, Anthropic, Google, Azure, and Bedrock within LangChain applications.
Pre-implementation confidence assessment tool for developers. Ensures 90%+ readiness via duplicate checks, architecture compliance, official docs verification, and root cause analysis.
Analyze project structures, dependencies, and patterns using parallel agent execution to generate comprehensive context documentation for rapid codebase onboarding and AI-assisted development.
Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.
TypeScript SDK agent for FX Protocol: manage leveraged positions, perform cross-chain bridges between Base and Ethereum, and interact with fxSAVE yield-bearing stablecoin features.
Automated Vercel production deployment agent that fetches logs via MCP, identifies build errors, applies fixes, and retries until success.
Architect features within the RBAC modular permissions system. Guides workspace design, permission mapping, CASL integration, and role hierarchy for secure, multi-tenant software.
Expert Solana Anchor development: build programs, manage PDAs, implement SPL tokens, handle security audits, and perform fuzz testing with Trident.
MPC-based multi-chain wallet SDK and CLI for AI agents and developers. Perform secure, threshold-signed crypto operations (send, swap, sign) across 40+ blockchains without seed phrases.