AGENT SKILL

langchain-core-workflow-b

Build LangChain agents with tools for autonomous task execution. Use when creating AI agents, implementing tool calling, or building autonomous workflows with decision-making. Trigger with phrases like "langchain agents", "langchain tools", "tool calling", "langchain autonomous", "create agent", "function calling".

License 许可
MIT
最近更新
2026-11-15
Stars
★ 2.0k
Forks
233

01 前言 Front Matter

name
langchain-core-workflow-b
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Build LangChain agents with tools for autonomous task execution. Use when creating AI agents, implementing tool calling, or building autonomous workflows with decision-making. Trigger with phrases like "langchain agents", "langchain tools", "tool calling", "langchain autonomous", "create agent", "function calling".
allowed-tools
Read, Write, Edit

03 SKILL.md 正文

LangChain Core Workflow B: Agents & Tools

Overview

Build autonomous agents that can use tools, make decisions, and execute multi-step tasks using LangChain's agent framework.

Prerequisites

  • Completed langchain-core-workflow-a (chains)
  • Understanding of function/tool calling concepts
  • Familiarity with async programming

Instructions

Step 1: Define Tools

from langchain_core.tools import tool
from pydantic import BaseModel, Field

class SearchInput(BaseModel):
    query: str = Field(description="The search query")

@tool(args_schema=SearchInput)
def search_web(query: str) -> str:
    """Search the web for information."""
    # Implement actual search logic
    return f"Search results for: {query}"

@tool
def calculate(expression: str) -> str:
    """Evaluate a mathematical expression."""
    try:
        result = eval(expression)  # Use safer alternative in production
        return str(result)
    except Exception as e:
        return f"Error: {e}"

@tool
def get_current_time() -> str:
    """Get the current date and time."""
    from datetime import datetime
    return datetime.now().isoformat()

tools = [search_web, calculate, get_current_time]

Step 2: Create Agent with Tools

from langchain_openai import ChatOpenAI
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder

llm = ChatOpenAI(model="gpt-4o-mini")

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant with access to tools."),
    MessagesPlaceholder(variable_name="chat_history", optional=True),
    ("human", "{input}"),
    MessagesPlaceholder(variable_name="agent_scratchpad"),
])

agent = create_tool_calling_agent(llm, tools, prompt)

agent_executor = AgentExecutor(
    agent=agent,
    tools=tools,
    verbose=True,
    max_iterations=10,
    handle_parsing_errors=True
)

Step 3: Run the Agent

# Simple invocation
result = agent_executor.invoke({
    "input": "What's 25 * 4 and what time is it?"
})
print(result["output"])

# With chat history
from langchain_core.messages import HumanMessage, AIMessage

history = [
    HumanMessage(content="Hi, I'm Alice"),
    AIMessage(content="Hello Alice! How can I help you?")
]

result = agent_executor.invoke({
    "input": "What's my name?",
    "chat_history": history
})

Step 4: Streaming Agent Output

async def stream_agent():
    async for event in agent_executor.astream_events(
        {"input": "Search for LangChain news"},
        version="v2"
    ):
        if event["event"] == "on_chat_model_stream":
            print(event["data"]["chunk"].content, end="", flush=True)
        elif event["event"] == "on_tool_start":
            print(f"\n[Using tool: {event['name']}]")

Output

  • Typed tool definitions with Pydantic schemas
  • Configured agent executor with error handling
  • Working agent that can reason and use tools
  • Streaming output for real-time feedback

Advanced Patterns

Custom Tool with Async Support

from langchain_core.tools import StructuredTool

async def async_search(query: str) -> str:
    """Async search implementation."""
    import aiohttp
    async with aiohttp.ClientSession() as session:
        # Implement async search
        return f"Async results for: {query}"

search_tool = StructuredTool.from_function(
    func=lambda q: "sync fallback",
    coroutine=async_search,
    name="search",
    description="Search the web"
)

Agent with Memory

from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.runnables.history import RunnableWithMessageHistory

message_history = ChatMessageHistory()

agent_with_memory = RunnableWithMessageHistory(
    agent_executor,
    lambda session_id: message_history,
    input_messages_key="input",
    history_messages_key="chat_history"
)

result = agent_with_memory.invoke(
    {"input": "Remember, I prefer Python"},
    config={"configurable": {"session_id": "user123"}}
)

Error Handling

Error Cause Solution
Tool Not Found Tool name mismatch Verify tool names in prompt
Max Iterations Agent stuck in loop Increase limit or improve prompts
Parse Error Invalid tool call format Enable handle_parsing_errors
Tool Error Tool execution failed Add try/except in tool functions

Resources

Next Steps

Proceed to langchain-common-errors for debugging guidance.

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

neuropixels-analysis

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

notebooklm

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Skill与智能体开发
★ 2.0k