The foundation the hiring audits build on. The skill finds your careers page and the ATS behind it, paginates to the very end so no posting is missed, sweeps job boards and archived pages for posted and removed dates, and visits every open posting to capture the title, all metadata, and the full description. It then parses out shared boilerplate, extracts structured fields (salary, location, work arrangement, employment type, job family, pay grade, seniority), derives a standardized seniority ladder and classification list from the corpus, and flags every posting for traditional software skills versus AI skills, with quoted phrases behind every flag. The result is one canonical inventory file the AI Hiring Culture Audit and the Competency and Culture JD Audit both consume.
- Find the surfaces: the careers page, the ATS behind it, the job boards, and the archives.
- Enumerate everything: paginate to the end, reconcile stated totals, keep only roles actively being hired for.
- Read every posting in full: title, metadata, and the complete description, reported in batches.
- Parse and normalize: boilerplate, structured fields, one seniority ladder, one classification list, and the AI versus traditional skill flags.
You provide
- Your company name (or nothing, if a sibling skill already established it)
- Confirmation of the surfaces found and the final inventory summary
You receive
- The canonical job postings inventory file, every open role parsed and flagged
- A standardized seniority ladder and classification list derived from your own postings
Download this skill and its install guide: https://exec-skills.paulcheek.com/skills/cheek-job-postings-scan
How to use this skill
Once installed, start a new conversation and paste this prompt. The slash command invokes the skill directly; everything after it is your opening brief, so edit it to fit.
Sample output
A completed run of this skill for a sample company, Mastercard, exactly as the deliverable would arrive. Open it in a new tab.
The samples are illustrative demonstrations of the output format, built from public information. Mastercard is not affiliated with and has not endorsed these materials.