Prompt Engineering Patterns
Skill Verifiziert AktivMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production environments.
Funktionen
- Few-shot learning with example selection strategies
- Chain-of-Thought prompting for step-by-step reasoning
- Structured outputs using Pydantic for reliable parsing
- Prompt optimization workflows and A/B testing
- Template systems for reusable and modular prompts
- System prompt design for specialized AI assistants
Anwendungsfälle
- Designing complex prompts for production LLM applications
- Optimizing prompt performance, consistency, and token usage
- Implementing structured reasoning and few-shot learning
- Building reusable prompt templates and system prompts
- Debugging and refining prompts for improved LLM outputs
Nicht-Ziele
- Providing pre-built prompts for specific LLM tasks (focuses on patterns)
- Interacting directly with LLM APIs (demonstrates patterns)
- Managing LLM infrastructure or deployment
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add wshobson/agents/plugin install llm-application-dev@claude-code-workflowsQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Ce Brainstorm
100Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.
Moyu (摸鱼)
100자동으로 과잉 엔지니어링 패턴을 탐지합니다: (1) 사용자가 명시적으로 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(클래스, 인터페이스, 팩토리, 래퍼)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 종속성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만"과 같은 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 오류 처리, 유효성 검사, 방어적 코드 추가 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서 생성
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
Write A Skill
100Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Openclaw
100Generieren Sie Bilder und Videos aus Text mit Multi-Provider-Routing – unterstützt GPT Image 2.0 (nahezu perfekte Textdarstellung), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (vereinheitlicht fotorealistisch + Anime), Flux 2 Klein (günstige Entwürfe), Seedance 2.0 / Happyhorse 1.0 / Veo 3.1 Video und lokale ComfyUI-Workflows. Enthält 1.446 kuratierte Prompts und stilbewusste Prompt-Verbesserung. Verwenden Sie es, wenn Benutzer Bilder/Videos erstellen, Assets entwerfen, Fotos animieren, Prompts verbessern oder KI-Kunst-Workflows verwalten möchten. NICHT für: allgemeine Chats, Code-Generierung, Dokumentenerstellung, Videobearbeitung von vorhandenem Material, Audio/TTS oder Aufgaben, die nichts mit der Erstellung von KI-Bildern/Videos zu tun haben.
Arize Prompt Optimization
100Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.