AGENT SKILL

juicebox-sdk-patterns

Apply production-ready Juicebox SDK patterns. Use when implementing robust error handling, retry logic, or enterprise-grade Juicebox integrations. Trigger with phrases like "juicebox best practices", "juicebox patterns", "production juicebox", "juicebox SDK architecture".

License 许可
MIT
最近更新
2026-11-15
Stars
★ 2.0k
Forks
233

01 前言 Front Matter

name
juicebox-sdk-patterns
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Apply production-ready Juicebox SDK patterns. Use when implementing robust error handling, retry logic, or enterprise-grade Juicebox integrations. Trigger with phrases like "juicebox best practices", "juicebox patterns", "production juicebox", "juicebox SDK architecture".
allowed-tools
Read, Write, Edit, Bash(npm:*), Bash(pip:*), Grep

03 SKILL.md 正文

Juicebox SDK Patterns

Overview

Production-ready patterns for robust Juicebox integration including error handling, retries, and caching.

Prerequisites

  • Juicebox SDK installed
  • Understanding of async/await patterns
  • Familiarity with dependency injection

Instructions

Step 1: Create Client Wrapper

// lib/juicebox-client.ts
import { JuiceboxClient, JuiceboxError } from '@juicebox/sdk';

export class JuiceboxService {
  private client: JuiceboxClient;
  private cache: Map<string, { data: any; expires: number }>;

  constructor(apiKey: string) {
    this.client = new JuiceboxClient({
      apiKey,
      timeout: 30000,
      retries: 3
    });
    this.cache = new Map();
  }

  async searchPeople(query: string, options?: SearchOptions) {
    const cacheKey = `search:${query}:${JSON.stringify(options)}`;
    const cached = this.getFromCache(cacheKey);
    if (cached) return cached;

    try {
      const results = await this.client.search.people({
        query,
        ...options
      });
      this.setCache(cacheKey, results, 300000); // 5 min cache
      return results;
    } catch (error) {
      if (error instanceof JuiceboxError) {
        throw this.handleJuiceboxError(error);
      }
      throw error;
    }
  }

  private handleJuiceboxError(error: JuiceboxError) {
    switch (error.code) {
      case 'RATE_LIMITED':
        return new Error(`Rate limited. Retry after ${error.retryAfter}s`);
      case 'INVALID_QUERY':
        return new Error(`Invalid query: ${error.message}`);
      default:
        return error;
    }
  }
}

Step 2: Implement Retry Logic

// lib/retry.ts
export async function withRetry<T>(
  fn: () => Promise<T>,
  options: { maxRetries: number; backoff: number }
): Promise<T> {
  let lastError: Error;

  for (let i = 0; i < options.maxRetries; i++) {
    try {
      return await fn();
    } catch (error) {
      lastError = error as Error;
      await sleep(options.backoff * Math.pow(2, i));
    }
  }

  throw lastError!;
}

Step 3: Add Observability

// lib/instrumented-client.ts
export class InstrumentedJuiceboxService extends JuiceboxService {
  async searchPeople(query: string, options?: SearchOptions) {
    const start = Date.now();
    const span = tracer.startSpan('juicebox.search');

    try {
      const results = await super.searchPeople(query, options);
      span.setStatus({ code: SpanStatusCode.OK });
      metrics.histogram('juicebox.search.duration', Date.now() - start);
      return results;
    } catch (error) {
      span.setStatus({ code: SpanStatusCode.ERROR });
      metrics.increment('juicebox.search.errors');
      throw error;
    } finally {
      span.end();
    }
  }
}

Output

  • Production-ready client wrapper
  • Retry logic with exponential backoff
  • Caching layer for performance
  • Observability instrumentation

Error Handling

Pattern Use Case Benefit
Circuit Breaker Prevent cascade failures System resilience
Retry with Backoff Transient errors Higher success rate
Cache-Aside Repeated queries Lower latency
Bulkhead Resource isolation Fault isolation

Examples

Singleton Pattern

// Ensure single client instance
let instance: JuiceboxService | null = null;

export function getJuiceboxService(): JuiceboxService {
  if (!instance) {
    instance = new JuiceboxService(process.env.JUICEBOX_API_KEY!);
  }
  return instance;
}

Resources

Next Steps

Apply these patterns then explore juicebox-core-workflow-a for search workflows.

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

neuropixels-analysis

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

notebooklm

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Skill与智能体开发
★ 2.0k