agentleFS
JiemsLBJJiemsLBJ/offer-harvester/.agents/skills/hotjob-search/SKILL.md

hotjob-search

Skill4 starsChanged 2 months agoMITView on GitHub

Searches internships on Wecruit/Hotjob employer career sites through their public job-list and job-detail endpoints. Defaults to Deloitte China and can target another verified Wecruit tenant. Triggers on: 德勤招聘, 德勤实习, Hotjob, Wecruit, 大易招聘, /scrape 德勤.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search public postings on the Wecruit generation of Hotjob career sites.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Hotjob / Wecruit Search

Search public postings on the Wecruit generation of Hotjob career sites. The default tenant is Deloitte China's internship site; reads need no login or API key. Applying is deliberately separate and uses apply_bot so login, uploads, form learning, review, and final confirmation retain their safety gates.

Commands

CommandPurpose
searchSearch open internship titles, with optional city/recency filters
detail <postId|url>Read the full duties, qualifications, deadline, and identifiers

Search flags

FlagMeaning
--query, -q <kw>Title keyword, required
--location, -l <city>Client-side city filter, such as 上海
--jobage <days>Keep postings published within N days
--page <n>1-indexed API page, default 1
--limit <n>Maximum results, default 20
--format <fmt>json (default), table, or plain
--tenant <SU...|url>Verified Wecruit tenant; defaults to Deloitte
--company <name>Employer name stored in results; defaults to 德勤

Examples

bun run .agents/skills/hotjob-search/cli/src/cli.ts search -q "数据分析" -l 上海 --limit 10 --format table
bun run .agents/skills/hotjob-search/cli/src/cli.ts search -q "人工智能" --jobage 30 --format json
bun run .agents/skills/hotjob-search/cli/src/cli.ts detail 66875e421c240e3d86dafec5 --format plain

JSON search output is { "meta": {...}, "results": [...] }. Each result has id, title, company, location, date, deadline, url, business_unit, department, category, project_name, and post_code. Expired postings are discarded. A result URL always opens that exact posting rather than a list page.

Boundaries

  • Personal, low-volume use only. These are undocumented endpoints used by the employer's public page; stop on rate limiting or a changed response contract.
  • --jobage uses the site's publishDate. An older posting with a future deadline remains open but is intentionally omitted when this filter is set.
  • A different tenant is accepted only when supplied explicitly. Set the correct employer with --company; never infer it from a business-unit field.
  • See url-reference.md when the site changes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.