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.
496 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.
FHIR API development guide for building compliant healthcare endpoints. Includes resource validation, coding systems, and standard error handling.
Create professional technical diagrams and flowcharts using LaTeX TikZ with standardized Google Material and Anthropic-inspired design themes.
Executes SQL queries against the WordPress development database for inspection, troubleshooting, and audit log analysis.
Manage Vibesafe units to scan, generate, test, and verify AI-written code with cryptographically-secure hash-locked checkpoints.
An intelligent gateway that analyzes, scores, and routes user requests across 27 agents, 27 skills, and 14 MCPs to optimize Claude Code execution.
Standardized structure and templates for project documentation, including READMEs, API references, CLI guides, and directory layouts.
Guidance on React Server Components (RSC) in Next.js, covering server/client component boundaries, data fetching, and composition patterns.
Initialize and configure Trigger.dev in your project. Essential for setting up the SDK, project configuration, directory structure, and your first background task.
Retrieve real-time library documentation, code examples, and technical guidance using the Context7 API for frameworks like React, FastAPI, and Next.js.
A systematic workflow to instrument, evaluate, and monitor LLM applications using TruLens, supporting frameworks like LangChain, LangGraph, and LlamaIndex.
Intelligent tool selector for code search. Routes queries between semantic (claudemem) and native tools (Grep/Glob) to optimize efficiency, token usage, and search accuracy.