Index of every page on this site: llms.txt
All skills
ai-job-search-dev avatar

/job-scraper

@d2afe00
Run it yourself

Finds new job postings matching your profile via the portal-search CLIs installed in .agents/skills/ (copied from community-portals or built with /add-portal), with WebSearch as the fallback. Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, /scrape

Use this Skill: https://skilld.dev/gh/ai-job-search-dev/ai-job-search/job-scraper

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

search-queries.md

≈1.6k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Search Queries for Job Scraper

<!-- SETUP: Customize these queries based on your skills, target roles, and location -->

Installed portal CLIs (primary for /scrape)

/scrape discovers every portal skill under .agents/skills/*/SKILL.md and runs its CLI first. None ship with AI Job Search: copy the ones for your market from community-portals (e.g. linkedin-search, freehire-search under portals/global/), or build one with /add-portal. You do not need a matching site: line below for those CLIs to run.

The site: query templates in this file are the WebSearch fallback — for portals without a CLI, company career pages, or when a CLI fails.

Language scope: write every query category in every language listed in your CLAUDE.md Languages table (typically 1-2, sometimes more). A posting requiring a language you have not declared, as a job condition, is excluded before scoring; a posting requiring a higher level than you declared in a language you do work in is flagged for your own judgment, not excluded — see 04-job-evaluation.md's Language Gate, the single source of truth for this rule. Translate each category's keywords rather than machine-translating word-for-word (e.g. "Frontend Developer" -> "Desarrollador Frontend", not a literal word-for-word translation) if you work in more than one language.

Search Sites

Primary (your market's job boards - scaffold one with /add-portal):

  • [YOUR_JOB_BOARD] - your market's largest general job board
  • linkedin.com/jobs - LinkedIn job listings (filter: [YOUR_COUNTRY] / [YOUR_CITY]); also covered by the community linkedin-search CLI once installed
  • [YOUR_INDUSTRY_JOB_BOARD] - a niche/industry board for your field (optional)
  • [YOUR_ADDITIONAL_JOB_BOARD] - another major board for your market (optional)

Secondary (company career pages via Google):

  • Direct Google searches with site: filters for known target companies

Query Categories

Queries are grouped by priority. Write each category in every language from your Languages table (see Language scope above). Combine each query with your location terms (e.g. your city, region, or metro area) where the site supports it.

Each priority has two kinds of block. Plain terms blocks are what the portal CLIs consume: one term per line, one CLI call per term, no OR, no site: prefix, and no location (the CLI's location flag, or the city in --query where that portal's SKILL.md says so, carries it). Quote a multi-word phrase only if the portal's Query syntax: line says quoting is honoured. WebSearch-only blocks are Google syntax (site:, quotes, OR) for the fallback path and are never passed to a CLI.

Organize by function, not job title. The same underlying work carries different titles across companies and markets (a "Data Scientist" role at one employer may be posted as "Insights Analyst" or "Data Consultant" at another). Name each priority category after the function it covers, and list several plausible job titles as query variants within that category rather than betting an entire priority tier on one exact title string.

Priority 1: [YOUR_PRIMARY_ROLE_TYPE]

These match your strongest and most desired career direction.

Plain terms (portal CLIs)
[YOUR_PRIMARY_JOB_TITLE_1]
[YOUR_PRIMARY_JOB_TITLE_2]
[YOUR_KEY_SKILL]
WebSearch-only (site: fallback)
site:[YOUR_JOB_BOARD] "[YOUR_PRIMARY_JOB_TITLE_1]" [YOUR_CITY]
site:[YOUR_JOB_BOARD] "[YOUR_PRIMARY_JOB_TITLE_2]" [YOUR_CITY]
site:[YOUR_JOB_BOARD] "[YOUR_KEY_SKILL]" [YOUR_CITY]
site:linkedin.com/jobs "[YOUR_PRIMARY_JOB_TITLE_1]" [YOUR_COUNTRY]

Priority 2: [YOUR_DOMAIN_EXPERTISE]

These match your domain expertise.

Plain terms (portal CLIs)
[YOUR_DOMAIN_KEYWORD_1]
[YOUR_DOMAIN_KEYWORD_2]
WebSearch-only (site: fallback)
site:[YOUR_JOB_BOARD] [YOUR_DOMAIN_KEYWORD_1] [YOUR_CITY] OR [YOUR_REGION]
site:[YOUR_JOB_BOARD] [YOUR_DOMAIN_KEYWORD_2] [YOUR_COUNTRY]
site:linkedin.com/jobs [YOUR_DOMAIN_KEYWORD_1] [YOUR_CITY] [YOUR_COUNTRY]

Priority 3: [YOUR_ADJACENT_ROLE_TYPE]

Adjacent roles you could pivot into.

Plain terms (portal CLIs)
[YOUR_ADJACENT_TITLE_1]
[YOUR_ADJACENT_TITLE_2]
WebSearch-only (site: fallback)
site:[YOUR_JOB_BOARD] "[YOUR_ADJACENT_TITLE_1]" [YOUR_KEY_SKILL] [YOUR_CITY]
site:[YOUR_JOB_BOARD] "[YOUR_ADJACENT_TITLE_2]" [YOUR_KEY_SKILL] [YOUR_CITY]

Priority 4: Broader Technical / Consulting

Wider net for general technical roles.

Plain terms (portal CLIs)
[YOUR_KEY_SKILL] developer
technical consultant
WebSearch-only (site: fallback)
site:[YOUR_JOB_BOARD] [YOUR_KEY_SKILL] developer [YOUR_CITY]
site:linkedin.com/jobs "[YOUR_KEY_SKILL] developer" [YOUR_CITY]
site:[YOUR_JOB_BOARD] "technical consultant" [YOUR_DOMAIN] [YOUR_CITY]

Location Filter

When evaluating results, verify the job location is within reasonable commute distance from your home. Define acceptable areas:

  • [YOUR_CITY] and surrounding areas
  • [ACCEPTABLE_AREA_1]
  • [ACCEPTABLE_AREA_2]
  • [BORDERLINE_AREA] (borderline - ~X min by transit)
  • [TOO_FAR_AREA] (too far)

Language Filter

Your working languages and levels are in CLAUDE.md's Languages table. When filtering scraped results, apply 04-job-evaluation.md's Language Gate: a posting requiring a language you haven't declared at all is excluded; a posting requiring a higher level than you declared in a language you do work in is not excluded, flag it clearly instead (see job-scraper/SKILL.md's Step 3 "Quick Fit Assessment" for how the flag surfaces in /scrape output). Postings simply written in a language you don't work in, that don't require it on the job, are fine.

Date Filter

Only include jobs posted within the last 14 days, matching /scrape Step 1b.3: use a supported recency filter or filter the returned publication dates client-side. A future application deadline does not bypass this discovery window; /rank handles deadline expiry and urgency separately after discovery. If a posting date cannot be determined, include it but flag as "date unknown".

Adapting Queries

If the user specifies a focus area, select queries from the matching category and also generate 2-3 custom queries for that focus. For example:

  • "/scrape [focus_area]" -> relevant category queries + custom focus-specific queries

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning5mo3 checks · Risk SAFE
  • Gen Agent Trust Hub5mo

    The skill is safe to use but contains a potential indirect prompt injection surface. It fetches job postings from external websites and processes them without explicit boundary markers or sanitization, which could allow a malicious job posting to influence the agent's behavior.

  • Socket5mo

    No alerts

  • Snyk5mo

    Risk: MEDIUM · 1 issue

Signed by skilld at d2afe00. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 5 days ago
What it can do
Reads files Edits files Runs commands Network
All 14 allowed tools
ReadWriteEditGlobGrepBash(bun --version)Bash(python tools/job_key.py:*)Bash(python3 tools/job_key.py:*)Bash(python tools/scrape_state.py:*)Bash(python3 tools/scrape_state.py:*)WebFetchWebSearchAgentAskUserQuestion

README badge

README badge for ai-job-search-dev/ai-job-search/job-scraper