Work out which applicant tracking system a job uses from its application link, and give the formatting rules that system parses safely. Use when asked which ATS does this company use, will my CV get through the ATS, is my CV ATS friendly, or how should I format for Workday, Greenhouse, Lever or Taleo. Produces the detected system with the evidence, a parsing-safe formatting checklist, the file type to upload, and a check of a supplied CV against the rules.
Start a fresh conversation. Replace the highlighted placeholders.
Use ats-detector to identify the ATS from [application link] and provide address-based evidence, a parsing-safe formatting checklist, and the recommended upload file type; report an unknown system rather than guessing.
Required inputs
[application link]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: ats-detectordescription: "Work out which applicant tracking system a job uses from its application link, and give the formatting rules that system parses safely. Use when asked which ATS does this company use, will my CV get through the ATS, is my CV ATS friendly, or how should I format for Workday, Greenhouse, Lever or Taleo. Produces the detected system with the evidence, a parsing-safe formatting checklist, the file type to upload, and a check of a supplied CV against the rules."version: 1.0.0
ATS Detector
An applicant tracking system reads the CV before a person does. Each one parses differently, and the cheapest way to fail is a layout the parser scrambles: two columns, a table, a header image, contact details in a text box. This skill identifies the system from the application link and checks the CV against what that system needs.
Part of the pm-cv bundle. Used by company-tailored-cv.
What This Skill Produces
The detected system, with the evidence (the address pattern) and a confidence level
A formatting checklist for that system
The file type to upload
A CV check: each rule marked pass or fail against a supplied CV, with the fix
Required Inputs
Ask for these if not provided:
The application link (the page where the "Apply" button leads, not the company homepage)
It matches the address against the table above and prints the system and confidence. Standard library only. It does not fetch the page.
Output Format
ATS check: [company], [role]
1. System: [name] · Evidence: [the matching part of the address] · Confidence: high / medium / unknown
2. Rules for this application (checklist)
3. CV check | Rule | Pass / fail | Where | Fix |
4. Upload: [file type and file name]
Quality Checks
The evidence for the detected system is quoted from the address
An unknown system is reported as unknown, with the strict rules applied
Every failed rule has a specific fix
The file type recommendation is stated
Anti-Patterns
Guessing the vendor from the company's size or industry. Only the address is evidence.
Promising a CV will "pass the ATS". Systems rank and filter differently, and humans decide. Say it will parse cleanly.
Keyword-stuffing advice. Hidden white text and keyword blocks are detected and look worse to the human reader.
Treating a beautiful two-column design as fine. It may be fine for a human; it is a risk for the parser.