llm-application-patterns
Use when building LLM applications: prompt engineering, structured output, agents, RAG integration, memory management, or production deployment. Framework-agnostic patterns using raw SDK calls.
npx skills add majiayu000/claude-skill-registry --skill llm-application-patterns-jlaws-dotfiles --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# LLM Application Patterns ## Architecture Pattern Selection | Pattern | Use When | Complexity | |---------|----------|-----------| | **Single prompt** | Classification, extraction, simple Q&A | Low | | **Chain/pipeline** | Multi-step transformations, routing | Medium | | **RAG** | Knowledge retrieval from docs | Medium | | **Agent with tools** | External actions, multi-step reasoning | High | | **Multi-agent** | Complex workflows, specialized sub-tasks | Very High | **Decision rule**: Use the simplest pattern that solves the problem. A single well-structured prompt beats a complex chain 80% of the time. ## Prompting Strategies ### Strategy Selection | Task Type | Strategy | Avoid | |-----------|----------|-------| | Classification | Few-shot with labels | CoT (overthinks simple tasks) | | Reasoning / Math | CoT with verification | Zero-shot (unreliable) | | Multi-step tasks | ReAct / tool-use | Single-shot (misses steps) | | Extraction | Structured output + schema | Free-form (inconsistent) | | Creative | System prompt + constraints | Over-constraining | ### Few-Shot Prompting ```python SENTIMENT_PROMPT = """Classify the sentiment as positive, negative, or neutral. Review: "The fo
- Architecture Pattern Selection
- Prompting Strategies
- Strategy Selection
- Few-Shot Prompting
- Chain-of-Thought (CoT)
- Structured Output
- ReAct / Tool Use
- Memory / Context Management
- RAG Integration
- Chunking Strategy
- Retrieval Pipeline
- Prompt Versioning
- Evaluation Harness
- Production Guardrails
What does the llm-application-patterns skill do?
Use when building LLM applications: prompt engineering, structured output, agents, RAG integration, memory management, or production deployment. Framework-agnostic patterns using raw SDK calls.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill llm-application-patterns-jlaws-dotfiles --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.