Build AI-powered applications with RAG, multi-agent systems, prompt engineering, and MCP integrations
12 skills · Works with Claude Code, Codex, Cursor & more
Build Retrieval-Augmented Generation (RAG) systems using LangChain. Creates document loaders, vector store configurations, retrieval chains, and conversational agents with proper chunking and embedding strategies.
claude install-skill Jeffallan/claude-skills/rag-architect Build LLM pipelines as composable modules with DSPy. Writes signatures, chain-of-thought modules, retrieval-augmented programs, and bootstrapped few-shot optimizers that improve prompts automatically from data.
claude install-skill community/dspy-framework Get reliable JSON from any LLM with Instructor. Generates Pydantic response models, validation+retry loops, streaming partial objects, and provider-agnostic clients for OpenAI, Anthropic, Mistral, and local models.
claude install-skill community/instructor-llm Build conversational multi-agent workflows with Microsoft AutoGen. Generates agent role definitions, group chat orchestration, tool-using assistants, code-execution sandboxes, and human-in-the-loop checkpoints.
claude install-skill community/autogen-agents Build multi-agent AI systems with CrewAI. Designs agent roles, task delegation, tool integration, and orchestration flows where specialized AI agents collaborate to complete complex workflows.
claude install-skill Jeffallan/claude-skills/ml-pipeline Run open-weight models locally with Ollama. Generates Modelfile configs, GPU/CPU tuning, OpenAI-compatible API wiring, structured outputs with JSON mode, and per-model memory budgets for laptop dev.
claude install-skill community/ollama-local Design, test, and optimize prompts for LLMs. Implements structured prompting techniques — chain of thought, few-shot learning, system prompts, and evaluation frameworks to improve AI output quality and reliability.
claude install-skill nidhinjs/prompt-master Build AI-powered applications with the Vercel AI SDK. Generates streaming chat UIs, tool-calling agents, structured output extraction, and multi-provider LLM integrations with React Server Components.
claude install-skill Jeffallan/claude-skills/mcp-developer Build Model Context Protocol (MCP) servers that give AI agents access to your tools and data. Generates server scaffolding, tool definitions, resource handlers, and transport configurations for Claude, Cursor, and other MCP clients.
claude install-skill anthropics/skills/mcp-builder Build typed, testable LLM functions with BAML — a DSL that compiles prompts into typesafe clients for TypeScript, Python, and Ruby. Handles schema-aligned parsing, function definitions, retries, and playground testing.
claude install-skill community/baml-llm Build stateful agents with persistent memory using Letta (formerly MemGPT). Configures memory blocks, archival memory, tool execution, and self-editing memory loops that survive across sessions and process restarts.
claude install-skill community/letta-agents Build, debug, and optimize Claude API and Anthropic SDK applications. Handles prompt caching, tool use, batch processing, thinking, compaction, and model migration between Claude versions.
/claude-api Modern warehouse-native data engineering — dbt for transformations, Dagster for orchestration, DuckDB and Polars for fast local analytics, plus pipeline and SQL fundamentals
End-to-end deployment, monitoring, and infrastructure skills for shipping and operating production systems
Production-grade motion for the modern web — timelines, smooth scroll, layout animations, JSON illustrations, and tiny GPU-accelerated tweens.