ai-job-search-cn: Skill for Claude Code

Job Scraper

---

How It Works

This skill searches job sites using targeted queries based on your profile, deduplicates against previously seen jobs and the application tracker, and presents new matches with a quick fit assessment. For the Chinese market, it primarily uses WebSearch because major portals (BOSS 直聘, 拉勾, 猎聘, etc.) aggressively block scrapers. If you have installed optional portal CLI skills (e.g. lagou-search), the scraper can also call those.

Invocation

The user triggers this skill by saying things like:

• "Find new jobs"
• "Scrape for jobs"
• "Any new positions?"
• "/scrape"

Optional arguments:

• A focus area, e.g. "/scrape backend" or "/scrape 算法"
• "broad" to run all search categories, e.g. "/scrape broad"

---

Execution Steps

Step 0: Load State

1. Read job_scraper/seen_jobs.json (create if missing - start with {"seen": {}})
2. Read job_search_tracker.csv to extract already-applied companies+roles
3. Read search-queries.md (this directory) for the search strategy

Step 1: Search

Run WebSearch queries from search-queries.md. By default, run the top 3 priority categories. If the user said "broad", run all categories.

If the user specified a focus area (e.g. "backend"), prioritize queries from that category.

For each search:

• Use WebSearch with site-specific queries (site:zhipin.com, site:lagou.com, site:liepin.com, site:linkedin.com/jobs, etc.)
• Target your configured geographic area (Chinese cities)
• Look for postings from the last 14 days

If optional Chinese portal CLI skills are installed under .agents/skills/ (e.g. boss-search, lagou-search, liepin-search), you may also run them here with the user's configured query and location flags. If they are not installed, rely entirely on WebSearch.

Step 2: Fetch & Parse

For each promising result from Step 1:

• Use WebFetch to retrieve the job posting page
• Extract: job title, company, location, posting date (or "recent"), URL, key requirements (brief), application deadline (if listed)
• Skip if the URL or company+title combo already exists in seen_jobs.json
• Skip if the company+role already appears in job_search_tracker.csv