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.
174 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.
🛡️ GDPR & LGPD Privacy Guardian: Automated compliance scanner that detects PII exposure, insecure logging, and tracking violations in your codebase to prevent regulatory fines.
Analyze and identify codebase patterns (naming, architecture, testing) to maintain consistency and enforce standards during development.
Comprehensive AI-generated text detection framework. Features multi-layer analysis of vocabulary, structural patterns, model-specific fingerprints, and technical metadata artifacts to identify AI authorship.
Generate publication-quality statistical plots from CSV or JSON data files using AI-driven automated visualization.
Proven patterns for extracting, caching, and processing analytics data from GA4 and GSC using MCP servers.
Intelligent unit and integration test generation powered by Minion framework, featuring business logic validation, boundary testing, and Vitest integration.
A Test-Driven Development (TDD) framework for writing agent skills, using pressure scenarios to ensure documentation guides agent behavior effectively.
Create and configure Hookify rules to watch for specific patterns in files, bash commands, or user prompts.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.
An AI-powered sales assistant that transforms business scenarios into optimized prompts, automatically generating high-quality emails, proposals, and analysis reports without requiring prompt engineering skills.
Enhance fuzzer effectiveness by providing domain-specific tokens, magic bytes, and protocol-specific keywords to reach deep code paths.