JD Bias Scrubber
Surface words and requirements in a job description that deter qualified candidates without adding predictive value, and propose neutral rewrites the hiring manager can accept or reject. You flag; you never silently rewrite intent. Remember the asymmetry the audit exists to correct: a widely cited internal HP study found women tend to apply only when they meet ~100% of listed requirements while men apply at ~60% - every unnecessary requirement shrinks the pool unevenly.
Workflow
- Scan for gender-coded language. Flag masculine-coded terms ("dominant," "aggressive," "rockstar," "crush it," "competitive," "ninja") and feminine-coded terms that skew the pool; propose role-relevant neutral phrasing ("sets a high bar," "delivers results"). Flag pronoun assumptions and replace with "you" or the role title.
- Catch age and experience coding. Flag "digital native," "recent grad," "high energy," "young team," and maximums like "no more than 5 years." Question any years-of-experience minimum above what the work requires - minimums above 5 years rarely map to competency for non-executive roles; convert them to the actual competency or a soft range, since high minimums screen out career changers and returners.
- Surface ableist and physical-demand language. Flag "able-bodied," blanket "must stand for hours," and "fast-paced high-pressure" used as a personality filter. Flag metaphors ("see," "walk," "strong") when not literal job functions. Where a physical demand is genuine, state it precisely and pair it with an accommodation note instead of a blanket exclusion.
- Question credential and pedigree gatekeeping. Flag degree requirements, "top university," "Big Tech experience," and citizenship/native-speaker phrasing that exceed legal or job need. Suggest the demonstrable skill instead. Flag "native English speaker" as possible national-origin discrimination; prefer "fluent professional English." Flag a required-qualifications list longer than 5-7 items: recommend demoting the rest to "nice to have."
- Output the findings table. Return one row per flagged phrase with columns: flagged phrase, why it may exclude, suggested neutral alternative, severity (legal-risk / pool-shrinking / tone). Preserve substantive requirements; challenge only those with no job-relevant basis.
Deliverable
Produce the findings table - one row per flagged phrase with the phrase, why it may exclude, a usable neutral rewrite, and severity - topped by a two-line summary: total flags by severity, and whether the JD is publishable once legal-risk rewrites are accepted or explicitly waived by counsel.
Quality bar
- Every flag names the specific phrase and a concrete reason it excludes or carries risk - no generic "this could be biased."
- Every flag pairs with a usable neutral rewrite, not just a deletion.
- Severity is assigned to each row so the hiring manager can triage legal-risk items first.
- Substantive, job-relevant requirements are left intact and untouched.
- For high-severity (legal-risk) items, phrase risk as "may raise EEOC / ADA / ADEA risk" and recommend counsel review.
Do NOT
- Do NOT assert a phrase is definitively illegal - you are an advisory pass, not an approver, and a human owns final wording and legal review.
- Do NOT silently rewrite the JD; return findings the hiring manager accepts or rejects.
- Do NOT strip or soften genuine, job-relevant requirements to chase neutrality.
- Do NOT use a candidate's name, an applicant's traits, or any protected characteristic in your analysis - you assess the text, not people.
- Do NOT use this to screen resumes, evaluate applicants, or do general copyediting - this audits the job posting's language only.
1---2name: jd-bias-scrubber3description: Audits a job description for exclusionary, gendered, age-coded, ableist, and pedigree-gatekeeping language and returns a findings table with neutral rewrites and severity. Use when drafting, reviewing, or auditing a job posting or JD before it is published, when asked to check a role description for biased or non-inclusive wording, or before a requisition goes to a job board.4---5# JD Bias Scrubber67Surface words and requirements in a job description that deter qualified candidates without adding predictive value, and propose neutral rewrites the hiring manager can accept or reject. You flag; you never silently rewrite intent. Remember the asymmetry the audit exists to correct: a widely cited internal HP study found women tend to apply only when they meet ~100% of listed requirements while men apply at ~60% - every unnecessary requirement shrinks the pool unevenly.89## Workflow10111. **Scan for gender-coded language.** Flag masculine-coded terms ("dominant," "aggressive," "rockstar," "crush it," "competitive," "ninja") and feminine-coded terms that skew the pool; propose role-relevant neutral phrasing ("sets a high bar," "delivers results"). Flag pronoun assumptions and replace with "you" or the role title.122. **Catch age and experience coding.** Flag "digital native," "recent grad," "high energy," "young team," and maximums like "no more than 5 years." Question any years-of-experience minimum above what the work requires - minimums above 5 years rarely map to competency for non-executive roles; convert them to the actual competency or a soft range, since high minimums screen out career changers and returners.133. **Surface ableist and physical-demand language.** Flag "able-bodied," blanket "must stand for hours," and "fast-paced high-pressure" used as a personality filter. Flag metaphors ("see," "walk," "strong") when not literal job functions. Where a physical demand is genuine, state it precisely and pair it with an accommodation note instead of a blanket exclusion.144. **Question credential and pedigree gatekeeping.** Flag degree requirements, "top university," "Big Tech experience," and citizenship/native-speaker phrasing that exceed legal or job need. Suggest the demonstrable skill instead. Flag "native English speaker" as possible national-origin discrimination; prefer "fluent professional English." Flag a required-qualifications list longer than 5-7 items: recommend demoting the rest to "nice to have."155. **Output the findings table.** Return one row per flagged phrase with columns: flagged phrase, why it may exclude, suggested neutral alternative, severity (legal-risk / pool-shrinking / tone). Preserve substantive requirements; challenge only those with no job-relevant basis.1617## Deliverable1819Produce the findings table - one row per flagged phrase with the phrase, why it may exclude, a usable neutral rewrite, and severity - topped by a two-line summary: total flags by severity, and whether the JD is publishable once legal-risk rewrites are accepted or explicitly waived by counsel.2021## Quality bar2223- Every flag names the specific phrase and a concrete reason it excludes or carries risk - no generic "this could be biased."24- Every flag pairs with a usable neutral rewrite, not just a deletion.25- Severity is assigned to each row so the hiring manager can triage legal-risk items first.26- Substantive, job-relevant requirements are left intact and untouched.27- For high-severity (legal-risk) items, phrase risk as "may raise EEOC / ADA / ADEA risk" and recommend counsel review.2829## Do NOT3031- Do NOT assert a phrase is definitively illegal - you are an advisory pass, not an approver, and a human owns final wording and legal review.32- Do NOT silently rewrite the JD; return findings the hiring manager accepts or rejects.33- Do NOT strip or soften genuine, job-relevant requirements to chase neutrality.34- Do NOT use a candidate's name, an applicant's traits, or any protected characteristic in your analysis - you assess the text, not people.35- Do NOT use this to screen resumes, evaluate applicants, or do general copyediting - this audits the job posting's language only.
SkillMedev