Job Search

proficientlyjobs/proficiently-claude-skills

This automates your daily job search by scraping hiring.cafe, scoring matches against your resume and preferences, and saving the best ones with direct employer URLs. It handles the tedious parts: deduplication against your history, fuzzy matching against your LinkedIn contacts to surface network connections, and structured extraction without blowing up the context window. The fit scoring references a separate criteria doc, and it explicitly refuses to apply for you or write cover letters, instead directing you to companion skills for that. Smart constraint: it never shows you the hiring.cafe aggregator links, only the actual employer posting URLs it resolves by clicking through. If you're running a serious job search and want the busywork automated while keeping control of applications, this is the scaffolding.

skills.sh installs: 529
GitHub stars: 454
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add proficientlyjobs/proficiently-claude-skills --skill job-search --agent claude-code

Installs into .claude/skills of the current project.

Files

Job Search Skill

Priority hierarchy: See shared/references/priority-hierarchy.md for conflict resolution.

Automated daily job search using browser automation.

Quick Start

/proficiently:job-search - Run daily search with default terms from matching rules
/proficiently:job-search AI infrastructure - Search with specific keywords

File Structure

scripts/
  evaluate-jobs.md     # Subagent for parallel job evaluation
assets/
  templates/           # Format templates (committed)

Data Directory

Resolve the data directory using shared/references/data-directory.md.

Workflow

Step 0: Check Prerequisites

Resolve the data directory, then check prerequisites per shared/references/prerequisites.md. Resume and preferences are both required.

Step 1: Load Context

Read these files:

DATA_DIR/resume/* (candidate profile)
DATA_DIR/preferences.md (preferences)
DATA_DIR/job-history.md (to avoid duplicates)
DATA_DIR/linkedin-contacts.csv (if it exists — for network matching)

Extract search terms from:

$ARGUMENTS if provided
Target roles from preferences

Step 2: Browser Search

SKILL.md on GitHub

Details

Repository: github.com/proficientlyjobs/proficiently-claude-skills
First seen: Jun 3, 2026