Install
$ agentstack add skill-itssosunny-job-searcher-lotte-recruit-collect ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Lotte Recruit Collect
Collect current public postings from Lotte Recruit's announcement list 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.
Boundaries
- Read-only. GET of the public announcement-list page only. Never log in,
save a job, message, or apply. Do not submit any form.
- No fabrication. Fields the source does not expose are
null; titles,
companies, and application dates are copied verbatim.
- A collected posting reflects the public page at run time; it is not proof the
role is still open.
Run
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/lotte-recruit-collect/collect.py --limit 20
python3 skills/lotte-recruit-collect/collect.py --query "IT" --limit 20
--query, -q— filter by title/company substring. This is a **company career
portal that serves one flat list of every open announcement and ignores a server-side keyword param, so the filter is applied client-side** to the fetched list (empty default = all open announcements).
--limit, -n— max postings (default 20).--pretty— indent the JSON.
Output: a JSON array on stdout (source, external_id, url, title, company, location, employment_type, posted_at, deadline, salary, snippet, collected_at); a one-line count on stderr.
Notes
- Source:
SRC-JOB-LOTTE— https://recruit.lotte.co.kr/ (re-verified
2026-07-07). The announcement list is server-rendered, so a plain GET of /apply/announcement/list returns every card — no browser needed.
- Cards are
liwrappingdiv.job-card-group:.cmp-nameis the Lotte-group
entity, .card-tit a is the title + /apply/announcement/detail/ link, .card-foot .date is the application period and .dday the D-day tag.
external_idis the numeric announcement id; the canonical posting URL is
/apply/announcement/detail/.
deadlineis parsed from the closing date of the application period
(… ~ 2026.07.07 → 2026-07-07). location and employment_type are null (the list card shows neither); the 신입/경력 badge and D-day are kept in snippet.
- If the layout changes and 0 postings return, re-derive the
.job-card-group
child selectors against a live fetch (do not hardcode a specific company).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: itssosunny
- Source: itssosunny/job-searcher
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.