Provide structured prompts, RAG patterns, and LLM integration for AI applications.
npx skills add https://github.com/plurigrid/asi --skill llm-application-dev
Please help me install this Agent Skill. Skill: llm-application-dev Source: https://github.com/plurigrid/asi/tree/main/skills/llm-application-dev Command: npx skills add https://github.com/plurigrid/asi --skill llm-application-dev
Accelerate building applications powered by Large Language Models through prompt engineering, retrieval-augmented generation (RAG), and robust API integration patterns.
Build a small chatbot by combining a structured system prompt, a user prompt, and a RAG-based retrieval step before querying the LLM.
High-intent search queries and answers about installing and using this skill.
Build LLM applications by combining structured system prompts, user queries, and optional retrieval-augmented generation (RAG) pipelines before calling OpenAI or Anthropic APIs. This Skill provides integration templates, prompt engineering patterns, and streaming response handling for production-ready deployment.
RAG augments LLM prompts with relevant documents retrieved from a searchable store, improving accuracy on domain-specific queries. Use RAG when your LLM needs current, proprietary, or specialized knowledge beyond its training data—common in chatbots, Q&A systems, and automation workflows.
Streaming delivers LLM output incrementally rather than waiting for complete generation, enabling responsive UIs and real-time user feedback. This Skill includes patterns for streaming with OpenAI and Anthropic APIs to handle token-by-token output efficiently.
Yes. This Skill provides structured prompt patterns—including few-shot examples and chain-of-thought techniques—compatible with both OpenAI and Anthropic APIs. Both platforms support system prompts, user messages, and context injection for consistent LLM behavior.
Document chunking splits large texts into searchable segments; embeddings convert chunks into numerical vectors stored in a searchable index. This Skill enforces modular patterns for chunking strategy, embedding generation, and index queries to construct accurate context for LLM prompts.
Production LLM applications require API error handling, rate limiting, input validation, and output guardrails to prevent misuse. This Skill emphasizes robust error handling and secure API usage patterns to ensure reliable, safe AI-powered features.
vecearBuild document embedding and retrieval pipelines for scalable semantic search.
reggiechan74Configure OpenTelemetry exporters to monitor Claude Code usage and costs.
rukikotooQuery the econometrics RAG knowledge base to retrieve relevant document chunks.
fakhriaditiarahmanDeploy, fine-tune, and monitor LLMs with vLLM, TGI, and Ollama.
