More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ghost job & spam posting detector

    1

    Rank the job postings you saved by how likely they are to be real and open: stale and reposted listings, 'talent pool' wording, missing pay, the same ad posted under many agency names, MLM pitches and keyword stuffing.

    $8.49

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Some listings were never going to hire you. Stop spending evenings on them.

    Keep a simple CSV of the postings you come across (title, company, and ideally posted date, location, URL, source, salary and description). Repeats are fine and actually help. The detector groups sightings of the same job, counts reposts with new 'posted' dates, measures age, and flags evergreen wording ('always accepting', 'join our talent community', 'future opportunities'), missing pay ranges and thin descriptions. Spam checks catch the same description copied under several staffing-agency names, commission-only and 'be your own boss' pitches, fees, chat-app contacts, shortened apply links and keyword-stuffed ads. Every posting gets a ghost score, a spam score and a verdict (APPLY / APPLY, VERIFY / LOW PRIORITY / SKIP) with the reasons.

    What it does

    • Groups repeat sightings and counts reposts with new posted dates
    • Age from posted/first-seen dates, including '3 weeks ago' style dates
    • Evergreen/talent-pool wording, no pay range, thin descriptions, '500+ applicants and still up'
    • Syndicated spam: near-identical text under different company names (5-word shingles, Jaccard)
    • MLM/commission-only, fees, chat-app contacts, shortened links, keyword stuffing
    • Flexible column names; ranked CSV and JSON output

    Who it's for

    Active job seekers applying at volume who want to put their effort into postings that are real and current.

    Limits

    Heuristics only. It can't know whether a requisition is really open. Repost detection needs at least two sightings of the same job with different posted dates.

    What's included

    • SKILL.md: workflow, commands, how to explain results
    • scripts/: the tool (standard-library Python)
    • references/: sources
    • examples/: sample inputs used in the demo (all made up)
    • tests/: unit tests (Python 3.8 / 3.9 / 3.13)

    Standard-library Python only. No API keys, no network calls, no installs.

    • Heuristics only. It can't know whether a requisition is really open.
    • Repost detection needs at least two sightings of the same job with different posted dates.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    ghost-job-spam-detector/**

    Fully offline. No network calls, no credential access, and it never logs into, scrapes or submits anything on job boards.

    Listedtoday

    What's inside

    Frequently Asked Questions

    No. You give it a CSV you saved or exported. It never scrapes or logs in.

    No. These are likelihood signals. Real companies repost too, so check the employer's careers page.

    Only title and company. Dates, descriptions and URLs make the scores much better.

    New in Research & Analysis