SkillMachine
All skills

Job Ad Writer

Document

Turn a role + team culture into a publish-ready, inclusive, ATS-friendly job ad.

Live output preview

Input Format: Input FormatOutputWatch the Output: Watch the Output

A plan is required to view this content

Choose a plan to access input format, sample outputs, and live previews.

View Plans →

About the skill

What it does

Job Ad Writer turns a role + team-culture input into a publish-ready, inclusive, ATS-friendly and legally clean job posting. It first scores the ad across 6 dimensions (Legal compliance 0.25 · Inclusivity 0.20 · ATS/findability 0.15 · Attractiveness 0.20 · Clarity 0.10 · Transparency 0.10), producing a weighted Posting Health Score (0-100) and a verdict (≥85 Publish-ready · 70-84 Improve-then-publish · 50-69 Risky · <50 or Legal=0 Rewrite). It then assembles a fully rewritten ad: standard-title headline, AIDA hook, JCM-framed responsibilities, must-have/nice-to-have split, evidence-backed EVP, transparent salary band + KVKK CTA.

A core rule is the legal override: a single discriminatory phrase zeroes the Legal dimension and forces the verdict to "Rewrite" regardless of total. Nothing numeric is fabricated — missing salary/benchmark data is reported in gaps.

When to use it

  • Writing a fresh posting for a new role.
  • Revising an ad that "gets no applicants / the wrong applicants".
  • Auditing legal & inclusivity risk (Labor Law, KVKK, İŞKUR) before publishing.
  • When non-standard "creative" titles may be invisible to ATS/candidate search.

Method / frameworks

  • AIDA — the ad is a marketing text; the headline and first two lines hold the pool within 7 seconds.
  • EVP (Employer Value Proposition) — 3-5 concrete, evidence-backed values distilled from culture; clichés rejected.
  • Gender-decoded language (Gaucher, Friesen & Kay 2011; 2025 PNAS replication) — agentic-coded words narrow the pool; neutral substitutes proposed.
  • Job Characteristics Model (Hackman & Oldham 1976) — tasks reframed for motivational potential via skill variety, task identity/significance, autonomy, feedback.
  • ATS-compliance + Realistic Job Preview (Phillips 1998 meta-analysis) — standard titles get indexed; realistic previews cut early turnover.
  • TR legal gate — Labor Law art.5/art.30, KVKK art.5-6 + disclosure, İŞKUR rules audited at critical severity.

How do I use this skill?

You don't "run" a skill — after installing it you just tell the agent your task (e.g. ask for the relevant job), and the skill kicks in by itself when its description matches.

Upload the is-ilani-yazari.zip you downloaded as-is — no packaging needed, the format is already correct (folder at root).

  1. Open Settings → Customize → Skills
  2. Upload → select the is-ilani-yazari.zip you downloaded
  3. Claude reads SKILL.md; the name + description appear. Ready ✅

Scripts run in Anthropic's code-execution environment (sandbox) — not on your machine.