Agent skill · software engineering · yonatangross
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
Why this skill is useful
Adds executable scripts and detailed integration patterns for LLMs that enhance tool use, streaming, and fine-tuning capabilities beyond standard knowledge.
What it needs
Requires fastapi, langchain installed locally. About 5k tokens when loaded. Last updated 2026-08-06. 215 stars on the source repository.
What this skill does
LLM Integration Patterns for integrating LLMs into production applications: tool use, streaming, local inference, and fine-tuning. Each category has individual rule files in rules/ loaded on-demand. Quick Reference Category Rules Impact When to Use ---------- ------- -------- ------------- Function Calling 3 CRITICAL Tool definitions, parallel execution, input validation Streaming 3 HIGH SSE endpoints, structured streaming, backpressure handling Local Inference 3 HIGH Ollama setup, model selection, GPU optimization Fine-Tuning 3 HIGH LoRA/QLoRA training, dataset preparation, evaluation Context Optimization 2 HIGH Window management, compression, caching, budget scaling Evaluation 2 HIGH LLM-as-judge, RAGAS metrics, quality gates, benchmarks Prompt Engineering 4 HIGH CoT, few-shot, versioning, DSPy optimization, ReAct, cost optimization Total: 20 rules across 7 categories Quick Start Function Calling Enable LLMs to use external tools and return structured data. Use strict mode schemas (2026 best practice) for reliability. On Claude keep the tools array stable across turns so the prompt cache holds; add tools mid-session with an inline tooladdition (beta inline-tools-2026-09-15, Claude API only, available on Sonnet 5.5 but not on Sonnet 5) instead of swapping subsets (https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes). For large tool sets, use a non-deferred tool search tool with deferloading: true on the rest, never deferloading alone (a request cannot have every tool deferred). Forced toolchoice (any or a named tool) returns a 400 on Sonnet 5.5, Opus 5.5, Fable 5.1 and Mythos 5.1; use auto with strict: true tools. Validate all inputs with Pydantic/Zod, and return errors as tool results. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills yonatangross/llm-integration