linkedin-jobs-search

Files (3)

• SKILL.md
• job-detail.py · scripts/
• search-jobs.py · scripts/

SKILL.md (first lines)

# LinkedIn — Job Search

> keywords + location + filters → paginated job list with full details

## Language

All process output to user (progress updates, process notifications) follows the user's language.

## Objective

Search LinkedIn job listings with full filter support, extract complete job data with full field coverage.

## Prerequisites

- The browser is open and the LinkedIn session is active (logged in). A LinkedIn jobs search page such as `https://www.linkedin.com/jobs/search/` must have been visited at least once so the CSRF token cookie is set.

## Pre-execution Checks

### 1. Tool Readiness

If browser-act has been confirmed available in the current session → skip this step.

Invoke `browser-act` via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.

### 2. Login Verification

If login status for LinkedIn has been confirmed in the current session → skip this step.

Otherwise: open `https://www.linkedin.com` and observe the page:
- User avatar or "Me" menu visible → logged in, continue
- Sign in / Join button visible → not logged in, inform user that LinkedIn login is required first

User refuses or cannot log in → terminate execution.

## Capability Components

> This Skill's operational boundary = what the user can manually do in their browser. It accesses LinkedIn through the user's logged-in browser, only reading data already available to the user. JS code is encapsulated in Python files under the `scripts/` directory, invoked via `eval "$(python scripts/xxx.py {params})"`. `$(...)` is bash syntax; it is recommended to use the bash tool for execution.

### API: Search LinkedIn jobs (list page)

`eval "$(python scripts/search-jobs.py '{keywords}' '{location}' --count {count} --start {start} --work-type {work_type} --job-type {job_type} --experience {experience} --time-posted {time_posted} --company-ids {company_ids})"`

Parameters:
- `keywords`: job title or search keywords (e.g., `software engineer`, `data analyst`)
- `location`: location name (e.g., `United States`, `New York`, `San Francisco Bay Area`)
- `--count`: results per API call, default `25`, max `100`
- `--start`: pagination offset, default `0`. Increment by `count` for each page
- `--work-type`: work arrangement filter — `1`=On-site, `2`=Remote, `3`=Hybrid (optional)
- `--job-type`: contract type filter — `F`=Full-time, `P`=Part-time, `C`=Contract, `T`=Temporary, `I`=Internship, `V`=Volunteer (optional)
- `--experience`: experience level filter — `1`=Internship, `2`=Entry, `3`=Associate, `4`=Mid-Senior, `5`=Director (optional)
- `--time-posted`: recency filter — `r86400`=24h, `r604800`=7 days, `r2592000`=30 days (optional)
- `--company-ids`: comma-separated LinkedIn company numeric IDs (optional, e.g., `76987811,1441`)

Output example:
```json
{
  "total": 36015,
  "start": 0,
  "count": 5,
  "jobs": [
    {
      "id": "4416832078",
      "title": "Lead Frontend Software Engineer",
      "company": "RowsOne",
      "location": "Boca Raton, FL",
      "workType": "Remote",
      "jobUrl": "https://www.linkedin.com/jobs/view/4416832078",
      "companyUrl": "https://www.linkedin.com/company/rowsone"
    }
  ]
}
```

Error handling: If `{"error": true}` is returned, check that the browser is still logged in to LinkedIn and navigate to `https://www.linkedin.com/jobs/search/` to refresh the session, then retry once.

### API: Get full job details

`eval "$(python scripts/job-detail.py '{job_id}')"`

Parameters:
- `job_id`: numeric LinkedIn job posting ID (from `id` field in search results)

Output example:
```json
{
  "id": "4416832078",
  "title": "Lead Frontend Software Engineer",
  "company": "RowsOne",
  "companyUrl": "https://www.linkedin.com/company/rowsone",
  "location": "Boca Raton, FL",
  "workType": "Remote",
  "contractType": "Full-time",
  "experienceLevel": "Mid-Senior level",
  "listedAt": "2026-05-26T16:14:30.000Z",
  "applicantCount": 37,
  "description": "Lead Frontend Engineer (React / Next.js)...",
  "salary": null,
  "jobUrl": "https://www.linkedin.com/jobs/view/4416832078"
}
```

Error handling: HTTP 404 means job has been removed or ID is invalid. If `{"error": true, "message": "HTTP 403"}`, the LinkedIn session may have expired — navigate back to LinkedIn and verify login, then retry.

### Composite: Full job extraction (search list + detail for each job)

For complete output with all fields (description, contract type, experience level, posted date):

1. Run search component to collect job IDs and basic info
2. For each job ID, run the detail component
3. Merge results by job ID

Batch script template (bash):
```bash
#!/bin/bash
SESSION="fb_explore"
KEYWORDS="software engineer"
LOCATION="United States"
TOTAL_ROWS=50
COUNT=25

From browser-act/skills, MIT.

More from browser-act/skills