Building LLM-Powered Applications with Claude

Repository planning gate

When this repository's CLAUDE.md classifies the request as complex or high-impact, the primary agent must invoke plan-tasks before inspecting, designing, or changing an integration. A subagent must return control to the primary agent rather than create a competing plan or edit target files. Resume this workflow only after an approved docs/plans/PLAN_<descriptive-name>.md maps the relevant A-* to claude-api, its assigned role, worktree isolation, and verification. The guidance below implements an approved action; it never replaces user approval.

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.

Before You Start

Scan the target file (or, if no target file, the prompt and project) for non-Anthropic provider markers — import openai, from openai, langchain_openai, OpenAI(, gpt-4, gpt-5, file names like agent-openai.py or *-generic.py, or any explicit instruction to keep the code provider-neutral. If you find any, stop and tell the user that this skill produces Claude/Anthropic SDK code; ask whether they want to switch the file to Claude or want a non-Claude implementation. Do not edit a non-Anthropic file with Anthropic SDK calls.

Output Requirement

When the user asks you to add, modify, or implement a Claude feature, your code must call Claude through one of:

The official Anthropic SDK for the project's language (anthropic, @anthropic-ai/sdk, com.anthropic.*, etc.). This is the default whenever a supported SDK exists for the project.
Raw HTTP (curl, requests, fetch, httpx, etc.) — only when the user explicitly asks for cURL/REST/raw HTTP, the project is a shell/cURL project, or the language has no official SDK.