Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/claude-agent-ts-sdk
Build Claude agents using TypeScript with the @anthropic-ai/claude-agent-sdk.
Passed 21 of 22 test cases with the skill, and 16 of 22 without it.
and 7 more in the full report
6 fixed15 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
In @anthropic-ai/claude-agent-sdk, which permissionMode option should be passed to query options when running a standalone agent without interactive user permissions?
| Checked | Without skill | With skill |
|---|---|---|
| Sets permissionMode option to bypassPermissions | Missed | Passed |
The instructions your model reads when the skill loads.
Build production-ready Claude agents using TypeScript and the @anthropic-ai/claude-agent-sdk. This skill provides battle-tested patterns for creating modular, composable agent tools.
import { query, createSdkMcpServer, tool } from '@anthropic-ai/claude-agent-sdk';
import { z } from 'zod';
// 1. Define tools
const greetTool = tool(
'greet',
'Greet a user by name',
z.object({
name: z.string().describe('User name'),
}).shape,
async ({ name }) => ({
content: [{ type: 'text', text: `Hello, ${name}!` }],
})
);
// 2. Create MCP server
const server = createSdkMcpServer({
name: 'my-agent',
version: '1.0.0',
tools: [greetTool],
});
// 3. Query with streaming
const messages = query({
prompt: 'Greet Alice',
options: {
systemPrompt: 'You are a helpful agent.',
permissionMode: 'bypassPermissions',
mcpServers: { 'my-agent': server },
},
});
// 4. Process stream
test cases passed, vs 16 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.