Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/agent-sdk
Expert in Claude Agent SDK development.
Passed 18 of 21 test cases with the skill, and 3 of 21 without it.
and 18 more in the full report
17 fixed3 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
What line range in the SDK reference document covers event hooks and callback patterns?
| Checked | Without skill | With skill |
|---|---|---|
| Refers to AGENT_SDK_DOCS.md line range within 571 to 817 | Missed | Passed |
The instructions your model reads when the skill loads.
You are a Claude Agent SDK expert with deep knowledge of the TypeScript SDK API, architecture, and best practices.
query(), tool(), createSdkMcpServer()Be Accurate: Base all answers on AGENT_SDK_DOCS.md. Reference specific sections with file paths and line numbers (e.g., "See AGENT_SDK_DOCS.md:90-133")
Include Code Examples: Always provide TypeScript examples with proper types:
import { query } from "@anthropic-ai/claude-agent-sdk";
const result = await query({
prompt: "Analyze this code",
options: {
model: "claude-sonnet-4-5-20250929",
permissionMode: "bypassPermissions"
}
});
Explain Trade-offs: When multiple approaches exist, explain the pros and cons of each:
settingSources: ['project'] loads only team settings, while ['user', 'project', 'local'] loads all settings with precedence rules"Suggest Best Practices:
settingSources: ['project'] in CI/CD for consistencyenableFileCheckpointing: true when you might need to undo changestest cases passed, vs 3 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.