claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent
npx skills add guanyang/open-agent-hub --skill claude-api --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Describes how to build Claude/Anthropic SDK-based applications, guiding users to choose the appropriate surface (Claude API, tool use, or Managed Agents) based on project needs. It instructs to detect non-Anthropic provider markers before starting and to call Claude via official SDKs or raw HTTP as required. It also outlines default model/version settings, handling of API drift, and four integration approaches (manual loop, Tool Runner, Managed Agents, Claude Agent SDK).
How it works
The skill instructs: scan the project to identify provider usage; avoid editing non-Anthropic files; when adding Claude features, call Claude through the official SDK or raw HTTP depending on language and user request; do not guess API shapes and verify against language-specific files in the skill; follow defaults for Claude model (claude-opus-5) and streaming/adaptive thinking; use per-turn hooks and tool integration patterns if building a multi-step workflow or agent; distinguish between harness and deployment depending on the chosen approach (manual loop, Tool Runner, CMA, or Claude Agent SDK).
When to use it
Use when the user asks to implement or modify Claude/Anthropic features, including pricing, model choices, limits, caching, streaming, and MCP/agents, and when the user requests Claude/Anthropic SDK code rather than OpenAI-compatible shims. Trigger reads occur for prompts mentioning Claude/Anthropic or related aliases or when the request is LLM-shaped with unspecified provider.
What it can touch
The skill references the following: official Anthropic SDKs, anthropic, @anthropic-ai/sdk, and related namespaces; Raw HTTP options (curl, requests, fetch, httpx). It emphasizes not mixing SDKs and shims and requires consulting language-specific {lang}/ files in the skill for correct APIs. It mentions tool surfaces like Tool Runner and Claude Agent SDK as harnesses, but does not expose concrete file edits beyond coding against those SDKs.
Caveats
Mentions potential API drift between Claude model versions and the need to validate against current language-specific files in the skill. Advises not to edit non-Anthropic files when the prompt indicates a Claude/Anthropic context. License terms are referenced as per LICENSE.txt in the repository.
# 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. ## 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: 1. **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. 2. **Raw HTTP** (`curl`, `requests`, `fetch`, `httpx`, etc.) — only
- Before You Start
- Output Requirement
- Defaults
- ⚠️ API Drift — Your Training Prior May Be Stale
- Subcommands
- Language Detection
- Language-Specific Feature Support
- Which Surface Should I Use?
- Building an Agent: Four Approaches
- Should I Build an Agent?
- Architecture
- Current Models (cached: 2026-06-24)
- Claude Fable 5 (claude-fable-5) — most capable widely released model
- Authentication (Quick Reference)
What does the claude-api skill do?
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent
How do I install it?
Run `npx skills add guanyang/open-agent-hub --skill claude-api --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From guanyang/open-agent-hub, a repository with 940 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.