prompt-engineering
Design and optimize prompts for large language models (LLMs) to achieve reliable, high-quality outputs across diverse tasks.
npx skills add majiayu000/claude-skill-registry --skill prompt-engineering --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.
What it does
Design and optimize prompts for large language models (LLMs) to achieve reliable, high-quality outputs across diverse tasks.
How it works
The skill instructs engineers to use a range of prompting techniques (zero-shot, few-shot, chain-of-thought, structured output) to build LLM applications with reliable outputs. It covers multiple models (OpenAI, Anthropic, Google Gemini, open-source) and provides concrete patterns including JSON-mode structured outputs, tool use with external APIs, and prompt chaining. It includes examples across languages (Python/TypeScript) and demonstrates decision frameworks for choosing prompting approaches, plus system prompts and personas, tool use, and multi-step workflows. It also details library recommendations (LangChain, LlamaIndex, DSPy, OpenAI/Anthropic SDKs) and production best practices (versioning, cost monitoring, retries, input sanitization, testing).
When to use it
Trigger this skill when building LLM-powered applications requiring consistent outputs, mitigating unreliability or hallucinations, needing structured data from NL inputs, implementing multi-step reasoning, creating AI agents that use tools, optimizing costs/latency, migrating prompts across providers, or establishing versioning and testing workflows.
What it can touch
OpenAI/Anthropic tooling and corresponding SDKs are referenced. The skill describes tool-calling patterns and how to configure function calls, tool definitions, and responses for external integrations.
Caveats
Contains guidance on production practices (versioning, cost tracking, error handling, input sanitization, testing) as described in the skill. Limits and risks are stated in the production sections, including handling retries and safeguarding against prompt injections.
--- name: prompt_engineering router_kit: AIKit description: Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building LLM applications requiring reliable outputs, implementing RAG systems, creating AI agents, or optimizing prompt quality and cost. Covers OpenAI, Anthropic, and open-source models with multi-language examples (Python/TypeScript). metadata: skillport: category: auto-healed tags: [agents, algorithms, artificial intelligence, automation, chatbots, cognitive services, deep learning, embeddings, frameworks, generative ai, inference, large language models, llm, machine learning, model fine-tuning, natural language processing, neural networks, nlp, openai, prompt engineering, rag, retrieval augmented generation, tools, vector databases, workflow automation] - prompt_engineering --- # Prompt Engineering Design and optimize prompts for large language models (LLMs) to achieve reliable, high-quality outputs across diverse tasks. ## Purpose This skill provides systematic techniques for crafting prompts that consistently elicit desired behaviors from LLMs. Rather than trial-and-error prompt iteration, apply pro
- Purpose
- When to Use This Skill
- Quick Start
- Prompting Technique Decision Framework
- Core Prompting Patterns
- 1. Zero-Shot Prompting
- 2. Chain-of-Thought (CoT)
- 3. Few-Shot Learning
- 4. Structured Output Generation
- 5. System Prompts and Personas
- 6. Tool Use and Function Calling
- 7. Prompt Chaining and Composition
- Library Recommendations
- Python Ecosystem
mv .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md \What does the prompt-engineering skill do?
Design and optimize prompts for large language models (LLMs) to achieve reliable, high-quality outputs across diverse tasks.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-engineering --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.