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.
407 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.
Architectural governance and project standards for React 19 SPA development, ensuring consistency in stack integration, project structure, and agent execution rules.
Autonomous research specialist for verified information gathering, source evaluation, and structured synthesis.
Operate Google Tag Manager via MCP. Handles OAuth, resource discovery, and CRUD operations for tags, triggers, and variables directly from your LLM agent.
Multi-source research tool for customer inquiries, bug investigations, and account history synthesis with source attribution and confidence scoring.
Token-efficient virtual task management for AI-assisted development. Manage task lifecycles, dependencies, and TDD workflows with surgical context injection.
Comprehensive Jira interaction suite for managing issues, sprints, boards, and worklogs via CLI. Supports searching, updating, transitioning, and attachment handling. Triggers on Jira URLs and issue keys.
Expert guidance for designing and implementing high-quality tool schemas and descriptions for Julia's agent systems, ensuring reliable tool execution and reducing model hallucinations.
VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.
Build RAG systems to ground LLMs in proprietary data. Includes vector database integration, embedding strategies, hybrid search, and advanced retrieval patterns for FastAPI backends.
Orchestrate Codex CLI for efficient parallel coding, task automation, and session-managed workflows to optimize token usage and development speed.
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows within the Ruflo/Claude Flow ecosystem.