claude-api

claude-api is an agent skill published by anthropic, listed under review & testing. It lives in the anthropics/skills repository, which has 183,845 GitHub stars; we last read it on 2026-10-10.

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/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

skills is a generic installer for any repository of Claude agent skills -- it reads anthropics/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.

npx skills add anthropics/skills

Unverified means a mention in the skill’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.

Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.

What does claude-api 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/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

How do I install claude-api?

Run npx skills add anthropics/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.

Who publishes claude-api?

anthropic.

Is claude-api maintained, and what licence does it use?

Its repository has 183,845 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-09. We did not find a declared licence, so check the repository before you rely on it.

• browser-testing-with-devtoolsby addyosmani
• code-review-and-qualityby addyosmani
• code-simplificationby addyosmani
• doubt-driven-developmentby addyosmani
• vitestby antfu
• webapp-testingby anthropic

All review & testing entries →

• Introduction to agent skills (Claude Academy)
• Introduction to subagents (Claude Academy)
• Build an AI agent: a path with skills and MCP servers to practise on