Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

Começar

agentic-workflows

Estrelas11

Forks0

Atualizado25 de julho de 2026 às 13:28

Guidelines for building multi-agent systems and RAG pipelines.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

j4flmao

j4flmao/agent-skills

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

name	agentic-workflows
description	Guidelines for building multi-agent systems and RAG pipelines.

Agentic Workflows & RAG

Core Principles

Modularity: Separate concerns into distinct agent roles (e.g., Planner, Executor, Reviewer).
Context Management: Use RAG to fetch only highly relevant context to reduce token bloat.

Multi-Agent Architecture

flowchart TD
    A[User Request] --> B{Planner Agent}
    B -->|Search Query| C[RAG Pipeline]
    C --> B
    B --> D[Executor Agent]
    B --> E[Executor Agent]
    D --> F[Reviewer Agent]
    E --> F
    F --> G[Final Response]

RAG Implementation Snippet

from langchain.vectorstores import Chroma
from langchain.embeddings import OpenAIEmbeddings
from langchain.chat_models import ChatOpenAI
from langchain.chains import RetrievalQA

def build_rag_pipeline(docs):
    vectorstore = Chroma.from_documents(documents=docs, embedding=OpenAIEmbeddings())
    retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
    llm = ChatOpenAI(temperature=0)
    return RetrievalQA.from_chain_type(llm=llm, retriever=retriever)

Mais deste repositório

mesmo repositório

quantum-scientist-persona

j4flmao/agent-skills

Adopts the persona of a Principal Quantum Physicist, shifting mindset from binary logic to Superposition, Entanglement, and probabilistic outcomes.

2026-07-2511

grover-s-algorithm

j4flmao/agent-skills

Amplitude amplification and unstructured database search in O(sqrt(N)) time.

2026-07-2511

qiskit-framework

j4flmao/agent-skills

Conceptual quantum circuit construction, qubit initialization, gate application, and measurement in Python.

2026-07-2511

quantum-entanglement

j4flmao/agent-skills

Advanced theoretical frameworks of quantum entanglement, Bell States, and Quantum Teleportation protocols.

2026-07-2511

qubits-gates

j4flmao/agent-skills

Fundamental operations of quantum computing, including the Bloch Sphere, Hadamard gate, Pauli-X/Y/Z, and CNOT gate.

2026-07-2511

shor-s-algorithm

j4flmao/agent-skills

Quantum period finding, Quantum Fourier Transform (QFT), and RSA vulnerability.

2026-07-2511

name	agentic-workflows
description	Guidelines for building multi-agent systems and RAG pipelines.

Agentic Workflows & RAG

Core Principles

Modularity: Separate concerns into distinct agent roles (e.g., Planner, Executor, Reviewer).
Context Management: Use RAG to fetch only highly relevant context to reduce token bloat.

Multi-Agent Architecture

flowchart TD
    A[User Request] --> B{Planner Agent}
    B -->|Search Query| C[RAG Pipeline]
    C --> B
    B --> D[Executor Agent]
    B --> E[Executor Agent]
    D --> F[Reviewer Agent]
    E --> F
    F --> G[Final Response]

RAG Implementation Snippet

from langchain.vectorstores import Chroma
from langchain.embeddings import OpenAIEmbeddings
from langchain.chat_models import ChatOpenAI
from langchain.chains import RetrievalQA

def build_rag_pipeline(docs):
    vectorstore = Chroma.from_documents(documents=docs, embedding=OpenAIEmbeddings())
    retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
    llm = ChatOpenAI(temperature=0)
    return RetrievalQA.from_chain_type(llm=llm, retriever=retriever)