菜单
Collect recent public job postings from Jumpit (점핏) by keyword. Use when the user wants to gather, scan, or monitor Jumpit developer listings for a role, stack, or company. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Collect recent public job postings from Apple's careers site (jobs.apple.com), default Korea, by keyword and location. Use when the user wants to gather, scan, or monitor Apple job listings for a role or region. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.
Collect recent public job postings from Career.co.kr (커리어) by keyword. Use when the user wants to gather, scan, or monitor Career.co.kr listings for a role, stack, or company. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.
Collect current public job postings from CJ Careers (CJ 그룹 채용). Use when the user wants to gather, scan, or monitor CJ group listings (CJ ENM, TVING, CJ제일제당, CJ푸드빌 등). Read-only — no login, save, or apply. Prints a normalized JSON array of postings.
Collect current public job postings from Coupang (쿠팡) careers. Use when the user wants to gather, scan, or monitor Coupang listings by keyword or location. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.
Collect recent public job postings from Daijob (daijob.com) — bilingual/English jobs in Japan. Use when the user wants to gather, scan, or monitor Daijob listings by keyword. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.
Collect recent public job postings from Dev Korea (dev-korea.com), English-friendly Korea tech jobs, by keyword. Use when the user wants to gather, scan, or monitor Dev Korea listings for a role, stack, or company. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.
| name | jumpit-collect |
| description | Collect recent public job postings from Jumpit (점핏) by keyword. Use when the user wants to gather, scan, or monitor Jumpit developer listings for a role, stack, or company. Read-only — no login, save, or apply. Prints a normalized JSON array of postings. |
Collect recent public postings from Jumpit's own public positions API and return
normalized JSON (docs/SCHEMA.md). Self-contained: this skill's collect.py
carries its own fetch + parse and depends only on curl_cffi, beautifulsoup4,
lxml.
null; titles,
companies, locations, deadlines, and tech-stack tags are copied verbatim.If collect.py fails with ModuleNotFoundError, install the deps yourself
(pip install curl_cffi beautifulsoup4 lxml) and retry — do not ask the user
to install anything.
pip install curl_cffi beautifulsoup4 lxml # or: pip install -r requirements.txt
python3 skills/jumpit-collect/collect.py --query "데이터 엔지니어" --limit 20
--query, -q — search keyword (default 개발자).--limit, -n — max postings (default 20).--pretty — indent the JSON.Output: a JSON array on stdout; a one-line count on stderr. Each item has
source, external_id, url, title, company, location, employment_type, posted_at, deadline, salary, snippet, collected_at.
SRC-JOB-JUMPIT — https://jumpit.saramin.co.kr/ (collectible_open,
re-verified 2026-07-07). The site's own API is the stable interface — prefer
it over scraping the JS-rendered HTML.GET https://jumpit-api.saramin.co.kr/api/positions?sort=reg_dt&highlight=false&keyword=<q>.
It returns XML (parsed with BeautifulSoup's xml mode): each job is a
<positions> node with a direct <id> child. external_id is that id;
canonical detail URL is /position/<id>.closedAt deadline, job category, and tech-stack tags
(folded into snippet); it does not expose employment type, posted date, or
salary, so those are null. Keyword-matched titles may wrap the match in
<span> markup — the collector strips it.<positions>
node fields against a live fetch (do not hardcode a specific company).