Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Building LLM-Powered Applications with Claude
This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.
## Defaults
Unless the user requests otherwise:
For the Claude model version, please use Claude Opus 4.6, which you can access via the exact model string `claude-opus-4-6`. Please default to using adaptive thinking (`thinking: {type: "adaptive"}`) for anything remotely complicated. And finally, please default to streaming for any request that may involve long input, long output, or high `max_tokens` — it prevents hitting request timeouts. Use the SDK's `.get_final_message()` / `.finalMessage()` helper to get the complete response if you don't need to handle individual stream events
---
## Language Detection
Before reading code examples, determine which language the user is working in:
1. **Look at project files** to infer the language:
- `*.py`, `requirements.txt`, `pyproject.toml`, `setup.py`, `Pipfile` → **Python** — read from `python/`
…
The line at the top of this page pins the label git:20260309.0790ef5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_2b4krhbx5py62i6a
GET https://markdownregistry.com/api/v1/resolve?ref=timwukp/agent-skills-best-practice/claude-api
GET https://markdownregistry.com/api/v1/blob/1ec3d558d3364ac7f768471055ded521f95bdb0f3e7239be9e4c8e0b219c587e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
timwukp/agent-skills-best-practice · skills/skills/agentcore-harness-builder/SKILL.md · Build production-ready AWS Bedrock AgentCore Harness agents end to end — declarative model + prompt, managed/BYO…
timwukp/agent-skills-best-practice · skills/skills/ai-native-sdlc/SKILL.md · Drive a change through an AI-native software development lifecycle as a loop of committed, machine-readable artifacts —…
timwukp/agent-skills-best-practice · skills/skills/algorithmic-art/SKILL.md · Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users…
timwukp/agent-skills-best-practice · skills/skills/aws-well-architected-review/SKILL.md · Reviews AWS architectures, IaC, and design docs against the AWS Well-Architected Framework's six pillars, producing a…
timwukp/agent-skills-best-practice · skills/skills/brand-guidelines/SKILL.md · Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having…
timwukp/agent-skills-best-practice · skills/skills/canvas-design/SKILL.md · Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user…
timwukp/agent-skills-best-practice · skills/skills/doc-coauthoring/SKILL.md · Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation…
anthropics/skills · skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/claude-api/SKILL.md · Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended…
nikships/droidproxy · .agents/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
rudycity/superagent · .agents/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
lichangzheng10086/doyin_ai_video · .agents/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
