claude-api

Claude API Skill (Anthropic SDK)

Step 1: Detect Language and Install SDK

Scan the project for package.json, requirements.txt, pyproject.toml, build.gradle, or go.mod to identify the language.

# Python
pip install anthropic

# Node.js / TypeScript
npm install @anthropic-ai/sdk

# Go
go get github.com/anthropics/anthropic-sdk-go

---

Step 2: Choose the Right Model

Model	Best For	Speed	Cost
claude-opus-4-5	Complex reasoning, coding, research	Slower	Higher
claude-sonnet-4-5	Balanced - most tasks	Medium	Medium
claude-haiku-3-5	Fast, lightweight tasks, classification	Fast	Lower

Default to claude-opus-4-5 for new implementations unless the user specifies otherwise or speed/cost is a constraint.

---

Step 3: Basic API Call

Python

import anthropic
import os

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

message = client.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Explain the CAP theorem in simple terms."}
    ]
)
print(message.content[0].text)

TypeScript / Node.js

import Anthropic from '@anthropic-ai/sdk'

const client = new Anthropic()  // reads ANTHROPIC_API_KEY from env

const message = await client.messages.create({
  model: 'claude-opus-4-5',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'Explain the CAP theorem in simple terms.' }
  ],
})
console.log(message.content[0].text)

---

Step 4: System Prompts and Multi-Turn Conversations

conversation_history = []

def chat(user_message: str) -> str:
    conversation_history.append({"role": "user", "content": user_message})

    response = client.messages.create(
        model="claude-opus-4-5",
        max_tokens=2048,
        system="You are a senior software engineer. Be concise and precise.",
        messages=conversation_history
    )

    assistant_message = response.content[0].text
    conversation_history.append({"role": "assistant", "content": assistant_message})
    return assistant_message