agentleFS
rubenviolinharubenviolinha/linkedin-job-search-skill/skills/linkedin-job-search/SKILL.md

linkedin-job-search

Skill0 starsChanged 6 months agoMITView on GitHub

Actively searches LinkedIn job listings using Playwright, scrapes job descriptions, analyzes fit against your profile, and saves top matches. Use when you want to discover new job opportunities beyond your saved jobs.

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. carsanmilcar/job-search-template★ 1same name
    2. MIt9/job-search-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no resume is provided in the message, ask the user to share it (text paste or file path).

    line 47
  2. Very specific:

    Run the scraper — the browser opens, sets the location filter, then clicks through every card, waits for the right panel to load, and reads …

    line 59
  3. Distinctive:

    Run the scraper in save mode — it navigates the same search page, clicks through cards, and clicks the LinkedIn "Save" button on each …

    line 84
  4. Distinctive:

    After outputting the table, offer:

    line 106
  5. Distinctive:

    Create output/ folder: if it doesn't exist before saving JSON

    line 116

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

linkedin-job-search

Searches LinkedIn for jobs matching a keyword + location, filters results against your profile, and saves a shortlist.

Description

Actively searches LinkedIn job listings (not just your saved ones) using a Playwright browser with your existing session. Scrapes candidates across pages, fetches full job descriptions, scores them against your profile, and outputs a filtered shortlist — ready to hand off to /job-analyzer or /resume-cover-letter-generator.

Usage

/linkedin-job-search
Keywords: Supply Chain Manager
Location: Oslo, Norway
Save top: 10
Flags: flag if Norwegian required, note if relocation expected

Or minimal:

/linkedin-job-search
Keywords: Operations Manager
Location: London, UK

Inputs

InputRequiredDefaultNotes
KeywordsYes—Job title or search terms
LocationNoWorldwideCity, region, or country
Jobs to scanNoAll on page (up to 5 pages)How many job listings to read and evaluate. Use --max-jobs N. 25 per page, so 50 = 2 pages, 75 = 3, etc.
Save top NNo10How many qualifying jobs to save on LinkedIn after evaluation
FlagsNo—Same flag syntax as /job-analyzer (e.g. "flag if visa required")

If no resume is provided in the message, ask the user to share it (text paste or file path). The resume is the source of truth for preferences — do not invent a profile.

Workflow

Phase 1 — Setup & Scrape with Descriptions

  1. Copy linkedin_search.mjs to /tmp/pw-runner/ if not already there:
    mkdir -p /tmp/pw-runner
    cp /path/to/repo/scraper/linkedin_search.mjs /tmp/pw-runner/
    cd /tmp/pw-runner && npm install playwright 2>/dev/null | tail -2
  2. Run the scraper — the browser opens, sets the location filter, then clicks through every card, waits for the right panel to load, and reads the full job description. Use --max-jobs to cap how many jobs are scanned (stops mid-page when reached):
    cd /tmp/pw-runner && node linkedin_search.mjs \
      --keywords "Supply Chain Manager" \
      --location "Oslo, Norway" \
      --max-jobs 50 2>&1
  3. Parse the JSON block after === SEARCH RESULTS === — each entry has title, company, location, url, easyApply, posted, and description (up to 3000 chars of the full JD).

Session handling: Same session as linkedin-jobs-fetch (~/.claude/linkedin-session.json). If the script reports session expired, tell the user to delete that file and re-run. If no session exists, the browser will open for manual login — instruct user to log in then run touch /tmp/linkedin-ready.

Phase 2 — Evaluate

  1. Extract user profile from provided resume: current role, skills, seniority, domain background, languages, location preference.
  2. Note any custom flags from user message (language requirements, visa, remote vs on-site, etc.).
  3. For each scraped job, assess using the description field (no separate WebFetch needed):
    • Domain fit — honest about skill gaps
    • Level fit — seniority match
    • Location fit — matches user preference?
    • Custom flags — apply ❌/⚠️/✅ markers
    • Overall fit — ⭐ to ⭐⭐⭐⭐⭐
  4. Sort by overall fit descending, pick top N URLs.

Phase 3 — Save on LinkedIn

Run the scraper in save mode — it navigates the same search page, clicks through cards, and clicks the LinkedIn "Save" button on each matching job:

cd /tmp/pw-runner && node linkedin_search.mjs \
  --keywords "Supply Chain Manager" \
  --location "Oslo, Norway" \
  --save-urls "https://www.linkedin.com/jobs/view/123/,https://www.linkedin.com/jobs/view/456/"

Parse === SAVE RESULTS === to confirm how many were saved.

Phase 4 — Output

Present shortlist as a markdown table:

RoleCompanyLocationFitFlagsEasy ApplyURL
.........⭐⭐⭐⭐✅Yes[link]

Save full shortlist to:

output/job-search-YYYY-MM-DD.json

After outputting the table, offer:

  • /job-analyzer — for deeper per-job analysis with full summaries
  • /resume-cover-letter-generator — to generate tailored PDFs for top picks

Key Rules

  • Always read actual JD — never assess a job from title alone; descriptions come from the scraper's description field, no WebFetch needed
  • Always read actual resume — ask if not provided, never invent a profile
  • Be honest about gaps — don't oversell fit
  • Never unsave — save mode skips jobs already saved (aria-label="Unsave the job")
  • Create output/ folder if it doesn't exist before saving JSON
  • Idempotent — re-running overwrites the same-date output file cleanly

Related Skills

  • linkedin-jobs-fetch — fetches jobs you've already saved on LinkedIn
  • job-analyzer — deeper analysis of a job list
  • resume-cover-letter-generator — generates tailored PDFs for top picks

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.