开发与测试
anthropic-claude-development
Expert guidance for Anthropic Claude API development including Messages API, tool use, prompt engineering, and building production applications with Claude models.
Mindrally · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add Mindrally/skills --skill anthropic-claude-development技能说明
name: anthropic-claude-development description: Expert guidance for Anthropic Claude API development including Messages API, tool use, prompt engineering, and building production applications with Claude models.
Anthropic Claude API Development
You are an expert in Anthropic Claude API development, including the Messages API, tool use, prompt engineering, and building production-ready applications with Claude models.
Key Principles
- Write concise, technical responses with accurate Python examples
- Use type hints for all function signatures
- Follow Claude's usage policies and guidelines
- Implement proper error handling and retry logic
- Never hardcode API keys; use environment variables
Setup and Configuration
Environment Setup
import os
from anthropic import Anthropic
# Always use environment variables for API keys
client = Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY"))
Best Practices
- Store API keys in
.envfiles, never commit them - Use
python-dotenvfor local development - Set up separate keys for development and production
- Configure proper timeout settings for your use case
Messages API
Basic Usage
from anthropic import Anthropic
client = Anthropic()
message = client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1024,
system="You are a helpful assistant.",
messages=[
{"role": "user", "content": "Hello, Claude!"}
]
)
print(message.content[0].text)
Streaming Responses
with client.messages.stream(
model="claude-sonnet-4-20250514",
max_tokens=1024,
messages=[{"role": "user", "content": "Write a story"}]
) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)
Model Selection
- Use
claude-opus-4-20250514for complex reasoning and analysis - Use
claude-sonnet-4-20250514for balanced performance and cost - Use
claude-3-5-haiku-20241022for fast, efficient responses - Consider task complexity when selecting models
Tool Use (Function Calling)
Defining Tools
tools = [
{
"name": "get_weather",
"description": "Get the current weather in a given location",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g., San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The unit of temperature"
}
},
"required": ["location"]
}
}
]
response = client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1024,
tools=tools,
messages=[{"role": "user", "content": "What's the weather in London?"}]
)
Handling Tool Calls
import json
def process_tool_use(response, messages, tools):
# Check if Claude wants to use a tool
if response.stop_reason == "tool_use":
tool_use_block = next(
block for block in response.content
if block.type == "tool_use"
)
tool_name = tool_use_block.name
tool_input = tool_use_block.input
# Execute the tool
tool_result = execute_tool(tool_name, tool_input)
# Continue the conversation
messages.append({"role": "assistant", "content": response.content})
messages.append({
"role": "user",
"content": [{
"type": "tool_result",
"tool_use_id": tool_use_block.id,
"content": json.dumps(tool_result)
}]
})
# Get final response
return client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1024,
tools=tools,
messages=messages
)
return response
Vision and Multimodal
Image Analysis
import base64
# From URL
message = client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1024,
messages=[{
"role": "user",
"content": [
{
"type": "image",
"source": {
"type": "url",
"url": "https://example.com/image.jpg"
}
},
{
"type": "text",
"text": "Describe this image in detail."
}
]
}]
)
# From base64
with open("image.png", "rb") as f:
image_data = base64.standard_b64encode(f.read()).decode("utf-8")
message = client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1024,
messages=[{
"role": "user",
"content": [
{
"type": "image",
"source": {
"type": "base64",
"media_type": "image/png",
"data": image_data
}
},
{
"type": "text",
"text": "What do you see?"
}
]
}]
)
Prompt Engineering for Claude
System Prompts
- Be clear and specific about the assistant's role
- Include relevant context and constraints
- Specify output format when needed
- Use XML tags for structured instructions
system_prompt = """You are a technical documentation writer.
<guidelines>
- Write clear, concise documentation
- Use proper markdown formatting
- Include code examples where appropriate
- Follow the Google developer documentation style guide
</guidelines>
<output_format>
Always structure your response with:
1. Overview
2. Prerequisites
3. Step-by-step instructions
4. Examples
5. Troubleshooting
</output_format>
"""
Prompting Best Practices
- Use XML tags to structure complex prompts
- Provide examples for few-sho