agentsclimarketplace

Japandev collect

Skill itssosunny/job-searcher/skills/japandev-collect

잡써쳐 — 구직할 때, 여러 플랫폼을 찾아다니지 마세요. 자동으로 수집하세요. 22개 채용 플랫폼 → 하나의 정규화 JSON. Claude Code 스킬 팩, 읽기 전용, MIT.

Install
npx -y skills add itssosunny/job-searcher --skill japandev-collect

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 12 stars12 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Collect recent public job postings from Japan Dev (japan-dev.com) — IT jobs in Japan for English speakers. Use when the user wants to gather, scan, or monitor Japan Dev listings by role, stack, or company. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.

SKILL.md

2.5 KB, 573 tokens by cl100k_base, as published. Nobody here has run it

Japan Dev Collect

Collect recent public postings from Japan Dev's server-rendered /jobs listing 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 /jobs listing 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, locations, and salaries 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/japandev-collect/collect.py --query "backend" --limit 20
python3 skills/japandev-collect/collect.py --limit 20   # all listed roles
  • --query, -q — filter the listing by title/company substring (client-side).
  • --limit, -n — max postings (default 20).
  • --pretty — indent the JSON.

Output: a JSON array on stdout; a one-line count on stderr. Japan Dev exposes company, location, salary band (¥…), and a remote/onsite arrangement cleanly; residency/visa badges and technology tags land in snippet.

Notes

  • Source: SRC-JOB-JAPANDEV — https://japan-dev.com/ (collectible_open, verified 2026-07-07). The /jobs page is server-rendered and returns ~60 job cards in a single fetch.
  • Cards are li.job-item; the title/link is a.job-item__title with an href of /jobs/<company-slug>/<job-slug>. external_id is the trailing <job-slug> (stable for dedup); company is read from the logo alt.
  • --query filters the single fetched listing client-side (no server search param), so it narrows within the ~60 currently listed roles rather than querying the whole site.
  • If the layout changes and 0 postings return, re-derive the li.job-item child selectors against a live fetch (do not hardcode a specific company).

What ships with it: 1 file

8.3 KB alongside SKILL.md, 1 of them executable

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.