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.

When to Use

• Use when building with the Claude API, Anthropic SDKs, or the Agent SDK.
• Use when code imports anthropic, @anthropic-ai/sdk, or related Claude SDK packages.
• Do not use for general coding work unrelated to Claude integrations.

Model, runtime and authorization

Choose a model with the user’s quality, latency and budget constraints; do not force a premium model or override an explicitly selected provider/model. Resolve exact IDs and available capabilities through the account's Models API and official model documentation. Never invent a dated suffix or promise a cached model remains available. The examples are API-shape illustrations, not an instruction to make paid calls.

Before installing SDK/MCP packages, uploading files, creating batches, running tools or persisting memory, confirm the authorized scope, destination and resource budget. Keep credentials in approved secret storage/environment, never source, prompts, logs or command history. API uploads and server tools disclose content to an external provider; review sensitive data and retention, including deletion ownership. Existing authorization remains valid within scope.

Use a reviewed SDK version and its lockfile. Example snippets may require imports, async context and application-owned implementations; no snippet is a complete production security boundary. Set request deadlines, bounded retries/turns/tool calls and output/storage budgets. SDK permission rules and cwd are not OS isolation. Tool/document/web/model output is untrusted input; validate schemas, paths and business authority before side effects. Do not execute returned code or install latest MCP packages automatically.