AGENT SKILL

juicebox-core-workflow-a

Execute Juicebox people search workflow. Use when building candidate sourcing pipelines, searching for professionals, or implementing talent discovery features. Trigger with phrases like "juicebox people search", "find candidates juicebox", "juicebox talent search", "search professionals juicebox".

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

01 前言 Front Matter

name
juicebox-core-workflow-a
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Execute Juicebox people search workflow. Use when building candidate sourcing pipelines, searching for professionals, or implementing talent discovery features. Trigger with phrases like "juicebox people search", "find candidates juicebox", "juicebox talent search", "search professionals juicebox".
allowed-tools
Read, Write, Edit, Bash(npm:*), Bash(pip:*), Grep

03 SKILL.md 正文

Juicebox People Search Workflow

Overview

Implement a complete people search workflow using Juicebox AI for candidate sourcing and talent discovery.

Prerequisites

  • Juicebox SDK configured
  • Understanding of search query syntax
  • Knowledge of result filtering

Instructions

Step 1: Define Search Parameters

// types/search.ts
export interface CandidateSearch {
  role: string;
  skills: string[];
  location?: string;
  experienceYears?: { min?: number; max?: number };
  companies?: string[];
  education?: string[];
}

export function buildSearchQuery(params: CandidateSearch): string {
  const parts = [params.role];

  if (params.skills.length > 0) {
    parts.push(`skills:(${params.skills.join(' OR ')})`);
  }

  if (params.location) {
    parts.push(`location:"${params.location}"`);
  }

  return parts.join(' AND ');
}

Step 2: Implement Search Pipeline

// workflows/candidate-search.ts
import { JuiceboxService } from '../lib/juicebox-client';

export class CandidateSearchPipeline {
  constructor(private juicebox: JuiceboxService) {}

  async searchCandidates(criteria: CandidateSearch) {
    const query = buildSearchQuery(criteria);

    // Initial broad search
    const results = await this.juicebox.searchPeople(query, {
      limit: 100,
      fields: ['name', 'title', 'company', 'location', 'skills', 'experience']
    });

    // Score and rank candidates
    const scored = results.profiles.map(profile => ({
      ...profile,
      score: this.calculateFitScore(profile, criteria)
    }));

    // Sort by fit score
    return scored.sort((a, b) => b.score - a.score);
  }

  private calculateFitScore(profile: Profile, criteria: CandidateSearch): number {
    let score = 0;

    // Skills match
    const matchedSkills = profile.skills.filter(s =>
      criteria.skills.includes(s.toLowerCase())
    );
    score += matchedSkills.length * 10;

    // Experience match
    if (criteria.experienceYears) {
      const years = profile.experienceYears || 0;
      if (years >= (criteria.experienceYears.min || 0)) {
        score += 20;
      }
    }

    return score;
  }
}

Step 3: Handle Pagination

async function* searchAllCandidates(
  juicebox: JuiceboxService,
  query: string
): AsyncGenerator<Profile> {
  let cursor: string | undefined;

  do {
    const results = await juicebox.searchPeople(query, {
      limit: 50,
      cursor
    });

    for (const profile of results.profiles) {
      yield profile;
    }

    cursor = results.nextCursor;
  } while (cursor);
}

Output

  • Search query builder
  • Candidate scoring system
  • Paginated result handling
  • Ranked candidate list

Error Handling

Error Cause Solution
No Results Query too restrictive Broaden criteria
Slow Response Large dataset Use pagination
Score Issues Missing data Handle null values

Examples

Full Pipeline Usage

const pipeline = new CandidateSearchPipeline(juiceboxService);

const candidates = await pipeline.searchCandidates({
  role: 'Senior Software Engineer',
  skills: ['typescript', 'react', 'node.js'],
  location: 'San Francisco Bay Area',
  experienceYears: { min: 5 }
});

console.log(`Found ${candidates.length} matching candidates`);
candidates.slice(0, 10).forEach(c => {
  console.log(`${c.name} (Score: ${c.score}) - ${c.title} at ${c.company}`);
});

Resources

Next Steps

After implementing search, explore juicebox-core-workflow-b for candidate enrichment.

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