DSPy
技能 已验证 活跃Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
To empower users to build and optimize sophisticated AI systems using DSPy's declarative programming paradigm for improved reliability and maintainability.
功能
- Declarative LM programming with DSPy
- Automatic prompt optimization
- Modular RAG system development
- Agent creation and management
- Comprehensive examples and documentation
使用场景
- Building complex AI systems with multiple components
- Systematically improving LM outputs with optimizers
- Creating maintainable and portable AI pipelines
- Developing RAG systems, agents, or classifiers with higher reliability
非目标
- Manual prompt engineering
- Simple, single-step LM calls without optimization
- Building AI systems without a structured framework
工作流
- Configure LM provider
- Define task signatures
- Build modules (Predict, ChainOfThought, ReAct, etc.)
- Compose modules into pipelines or agents
- Optimize modules using training data
- Deploy and use optimized models
实践
- Declarative Programming
- Prompt Optimization
- Modular AI Design
- Agent Development
先决条件
- Python 3.8+
- pip package manager
- Access to an LM provider (OpenAI, Anthropic, Ollama, etc.)
安装
请先添加 Marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skills质量评分
已验证类似扩展
Dspy
99Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
LangChain
99Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
Langchain Framework
99LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications
Init
100创建或优化存储库的 AGENTS.md 文件，提供最少、高信号的说明，涵盖代理无法从代码库推断的不可发现的编码约定、工具怪癖、工作流偏好和项目特定规则。在为新存储库设置代理说明或 Claude 配置时，当现有的 AGENTS.md 文件过长、通用或过时，当代理反复犯可避免的错误，或当存储库工作流发生变化且需要修剪代理配置时使用。应用可发现性过滤器—省略 Claude 可从 README、代码、配置或目录结构中学到的任何内容—并应用质量门，以验证每行是否仍然准确且具有操作意义。
Moyu (摸鱼)
100감지된 과잉 엔지니어링 패턴: (1) 사용자가 명시적으로 요청하지 않은 코드나 파일을 수정할 때 (2) 요청되지 않은 새로운 추상화 계층(클래스, 인터페이스, 팩토리, 래퍼)을 생성할 때 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 주석을 추가할 때 (4) 요청되지 않은 새로운 종속성을 도입할 때 (5) 최소 편집 대신 파일 전체를 다시 작성할 때 (6) diff 범위가 사용자의 요청을 명백히 초과할 때 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만"과 같은 신호를 보낼 때 (8) 발생할 수 없는 시나리오에 대한 오류 처리, 유효성 검사, 방어적 코드를 추가할 때 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성할 때
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration