claude-api
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.
npx skills add majiayu000/claude-skill-registry --skill claude-api-sickn33-antigravity-awesome --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
The skill is designed to help building applications that integrate with the Claude API or Anthropic SDKs. It decides when to engage based on code imports of Claude-related packages or user requests to use Claude/Anthropic tools, and provides guidance on language selection and appropriate documentation surfaces. It directs users to choose the right surface (Claude API, SDKs, or Agent SDK) and to detect project language to read the corresponding language-specific documentation.
How it works
- Detects when to trigger: it activates when the code imports
anthropic,@anthropic-ai/sdk, orclaude_agent_sdk, or when the user asks to use Claude API, Anthropic SDKs, or Agent SDK. - Defaults: for Claude model version, use model string
claude-opus-4-6and enable adaptive thinking viathinking: {type: "adaptive"}. For long inputs, streaming is defaulted to minimize timeouts, and the agent should use the SDK helper methods.get_final_message()/.finalMessage()to obtain the complete response if individual stream events aren’t needed. - Language handling: analyzes project files to determine the programming language (Python, TypeScript, Java, Go, Ruby, etc.) and directs to the corresponding language-specific Claude API resources.
- Task guidance: instructs what to read for various tasks (e.g., Quick Task Reference, Agent SDK, tool use) and which files to consult within the language-specific folders.
When to use it
Use when building with the Claude API, Anthropic SDKs, or the Agent SDK. Do not use for general coding tasks unrelated to Claude integrations. Trigger conditions specifically include imports of Claude-related SDKs or user requests for Claude/Anthropic/Agent tooling.
What it can touch
The skill references and relies on Claude API surfaces, tool-use concepts, and language-specific tool-use guidance. It notes the model selection constraints and requires adherence to the default adaptive thinking and streaming behaviors when appropriate.
Caveats
Declared risk: unknown. License: MIT. It specifies that Claude Opus 4.6 is the default model unless the user explicitly requests another, and enforces the exact model ID claude-opus-4-6 from the provided model table. It also emphasizes using the thinking configuration and streaming behavior as defaults for long inputs. No outcomes are guaranteed beyond these explicit prescriptions.
# 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. ## 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 a
- When to Use
- Defaults
- Language Detection
- Language-Specific Feature Support
- Which Surface Should I Use?
- Decision Tree
- Should I Build an Agent?
- Architecture
- Current Models (cached: 2026-02-17)
- Thinking & Effort (Quick Reference)
- Compaction (Quick Reference)
- Reading Guide
- Quick Task Reference
- Claude API (Full File Reference)
What does the claude-api skill do?
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.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill claude-api-sickn33-antigravity-awesome --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 majiayu000/claude-skill-registry, a repository with 534 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.