Claude Agent SDK
Claude Agent SDK framework guide for building AI-powered applications. Provides comprehensive API knowledge, architecture patterns, and code examples for both TypeScript and Python. Use when: (1) building projects with @anthropic-ai/claude-agent-sdk, (2) creating AI agents with tool use, hooks, subagents, or MCP servers, (3) implementing multi-turn conversations, streaming responses, or session management, (4) configuring permission modes, custom tools, or agent orchestration, (5) debugging or extending existing Claude Agent SDK code, (6) user mentions "agent sdk", "claude agent", "claude-agen
Install
npx skills add liangdabiao/claudesdk-skill --skill claude-agent-sdkgit clone --depth 1 https://github.com/liangdabiao/claudesdk-skill.git /tmp/claudesdk-skill
mkdir -p ~/.claude/skills
cp -r /tmp/claudesdk-skill/.claude/skills/claude-agent-sdk ~/.claude/skills/claude-agent-sdkPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Claude Agent SDK
Build AI-powered applications that leverage Claude's agentic capabilities: tool use, multi-turn conversations, file operations, web search, and custom tool integration.
## Architecture
The SDK wraps Claude Code CLI as a subprocess. Your app sends prompts, the agent reasons and uses tools autonomously, streams back messages (text, tool calls, results). You control permissions, tools, hooks, and subagents.
```
Your App ──query()──> Claude Agent (subprocess)
^ |
| <──stream messages──── |
| (text, tool_use,
| results, etc.)
```
## Quick Start
### TypeScript
```ts
import { query } from '@anthropic-ai/claude-agent-sdk';
for await (const message of query({
prompt: 'Analyze the code in src/',
options: {
maxTurns: 30,
model: 'sonnet',
cwd: process.cwd(),
allowedTools: ['Read', 'Glob', 'Grep', 'Bash'],
}
})) {
if (message.type === 'assistant' && message.message) {
for (const block of message.message.content) {
if (block.type === 'text') console.log(block.text);
if (block.type === 'tool_use') console.log(`Tool: ${block.name}`);
}
}
if (message.type === 'result' && message.subtype === 'success') {
console.log('Done:', message.result);
console.log('Cost: $' + message.total_cost_usd);
}
}
```
### PythonDetails
- Skill name
claude-agent-sdk- Repository
- liangdabiao/claudesdk-skill
- Path
.claude/skills/claude-agent-sdk/SKILL.md- Repo updated
- 29 May 2026
FAQ
What does the Claude Agent SDK skill do?
Claude Agent SDK framework guide for building AI-powered applications. Provides comprehensive API knowledge, architecture patterns, and code examples for both TypeScript and Python. Use when: (1) building projects with @anthropic-ai/claude-agent-sdk, (2) creating AI agents with tool use, hooks, subagents, or MCP servers, (3) implementing multi-turn conversations, streaming responses, or session management, (4) configuring permission modes, custom tools, or agent orchestration, (5) debugging or extending existing Claude Agent SDK code, (6) user mentions "agent sdk", "claude agent", "claude-agen
How do I install the Claude Agent SDK skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add liangdabiao/claudesdk-skill --skill claude-agent-sdk. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Claude Agent SDK popular?
It lives in liangdabiao/claudesdk-skill, which has 35 GitHub stars and 9 forks.
Related skills
H3 Prompt Writing
44fengyungithub/dsh-short-video-studio
Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio. dsh-short-video-studio 适配版:还负责把画布上的镜头表/分镜/参考绑定重写为 H3 结构化 prompt(见文末「插件对接」适配节)。
Btpanel
43aaPanel/btpanel-skills
宝塔面板 Skill,让 AI Agent 调用宝塔面板能力,管理网站、文件、数据库、Docker、计划任务及服务器环境,完成状态查询、故障排查和安全检查等日常运维操作;支持自动部署宝塔面板与 MCP 服务,并接入 Claude Code、Codex、Cursor、WorkBuddy 等 AI Agent。当用户需要通过 AI 管理服务器、安装宝塔面板或配置宝塔 MCP 服务时使用。
Omni AI Eval
46exploreomni/omni-agent-skills
Evaluate Omni AI accuracy using Omni's built-in eval system — define a prompt set, run a judged eval against a model (or branch), and read the accuracy-judge verdicts. Use this skill whenever someone wants to evaluate Omni AI, benchmark Blobby, run regression tests, compare AI output across branches or model-context changes, measure AI quality, run A/B tests on model changes, assess the impact of an ai_context or modeling change, or any variant of "run evals", "test Blobby", "benchmark query generation", "compare AI results", "regression test", "how accurate is the AI", or "measure the impact
Siwa Server
43builders-garden/siwa
Use this skill to implement server-side SIWA verification. For backends and APIs that need to authenticate ERC-8004 agents without signing capabilities.
Omni AI Optimizer
46exploreomni/omni-agent-skills
Optimize an Omni Analytics model for Blobby, the Omni Agent — configure ai_context, ai_fields, synonyms, sample_queries, and ai_settings. Use this skill whenever someone wants to improve AI accuracy in Omni, make Blobby smarter, add AI context or example questions, curate which fields the AI sees, personalize AI context by user attribute, diagnose context-window pruning or truncation, raise a topic's AI context budget, control which topics AI can reach, troubleshoot why Blobby gives wrong answers, or any variant of "make the AI better", "Blobby isn't answering correctly", "optimize for AI", or
Siwa
43builders-garden/siwa
SIWA (Sign-In With Agent) authentication for ERC-8004 registered agents.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.