From anthropic-pack
Generates minimal Anthropic Claude Messages API examples in Python and TypeScript for text, vision, and streaming. Use for new integrations, setup testing, or basic API learning.
How this skill is triggered — by the user, by Claude, or both
Slash command
/anthropic-pack:anth-hello-worldThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Three minimal examples covering the Claude Messages API core surfaces: basic text completion, vision (image analysis), and streaming responses.
Three minimal examples covering the Claude Messages API core surfaces: basic text completion, vision (image analysis), and streaming responses.
anth-install-auth setupANTHROPIC_API_KEY in environmentanthropic package or Node.js 18+ with @anthropic-ai/sdkimport anthropic
client = anthropic.Anthropic()
message = client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1024,
messages=[
{"role": "user", "content": "Explain quantum computing in 3 sentences."}
]
)
# Response structure
print(message.content[0].text) # The actual text response
print(f"ID: {message.id}") # msg_01XFDUDYJgAACzvnptvVoYEL
print(f"Model: {message.model}") # claude-sonnet-4-20250514
print(f"Stop: {message.stop_reason}")# end_turn
print(f"Usage: {message.usage.input_tokens}in / {message.usage.output_tokens}out")
import Anthropic from '@anthropic-ai/sdk';
import * as fs from 'fs';
const client = new Anthropic();
// From file (base64)
const imageData = fs.readFileSync('chart.png').toString('base64');
const message = await 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: imageData,
},
},
{ type: 'text', text: 'Describe what this chart shows.' },
],
}],
});
console.log(message.content[0].type === 'text' ? message.content[0].text : '');
import anthropic
client = anthropic.Anthropic()
with client.messages.stream(
model="claude-sonnet-4-20250514",
max_tokens=1024,
messages=[{"role": "user", "content": "Write a haiku about APIs."}]
) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)
# Get final message with full metadata
final = stream.get_final_message()
print(f"\nTokens used: {final.usage.input_tokens}+{final.usage.output_tokens}")
| Error | HTTP Code | Cause | Solution |
|---|---|---|---|
authentication_error | 401 | Invalid API key | Check ANTHROPIC_API_KEY |
invalid_request_error | 400 | Bad params (e.g., empty messages) | Validate request body |
rate_limit_error | 429 | Too many requests | Implement backoff (see anth-rate-limits) |
overloaded_error | 529 | API temporarily overloaded | Retry after 30-60s |
api_error | 500 | Server error | Retry with exponential backoff |
| Parameter | Required | Description |
|---|---|---|
model | Yes | Model ID: claude-sonnet-4-20250514, claude-haiku-4-20250514, claude-opus-4-20250514 |
max_tokens | Yes | Maximum output tokens (model-dependent max) |
messages | Yes | Array of {role, content} objects |
system | No | System prompt (string or content blocks) |
temperature | No | 0.0-1.0, default 1.0 |
top_p | No | Nucleus sampling (use temperature OR top_p) |
stop_sequences | No | Array of strings that stop generation |
stream | No | Enable SSE streaming |
Proceed to anth-local-dev-loop for development workflow setup.
npx claudepluginhub jeremylongshore/claude-code-plugins-plus-skills --plugin anthropic-packProvides Claude API patterns for Python/TS: messages, streaming, tools, vision, caching, agents. Activates on anthropic/@anthropic-ai/sdk imports or API queries.
Installs Anthropic Claude SDK and configures API key authentication for Python and TypeScript. Verifies setup with test messages to Claude models.
Provides instructions for building LLM-powered apps with the Claude API or Anthropic SDK, including language detection and code examples for Python, TypeScript, Java, Go, Ruby, and more.