Job-relevant assessments that are fair and time-boxed
Designs practical work-sample tasks with clear instructions and a scoring rubric. Minimizes bias while respecting candidate time.
Create a skill called "Work Sample Builder". Inputs: - Role, level, and what the job actually does day-to-day - Time budget (max 60–120 minutes unless explicitly paid/compensated) - What tools are allowed (AI allowed or not; clarify) - Confidentiality constraints (no proprietary data) Output: 1) A work-sample prompt (candidate instructions) 2) Deliverable format (what to submit) 3) Time expectations and fairness note 4) Scoring rubric with anchored examples 5) Reviewer guide: how to evaluate consistently 6) Accessibility check (avoid unnecessary obstacles) Keep it directly job-related. Avoid trivia.
Describe what the role actually does day-to-day. The skill designs a task
that tests real work, not trivia.
Sort the pile fast without losing signal
Scores and ranks resumes against job requirements with consistent criteria. Highlights strongest evidence, flags mismatches, and gives you a clear advance/reject call.
Catch low-intent and irrelevant applications early
Detects patterns consistent with low-intent, irrelevant, or mass-generated applications and routes them appropriately. Reduces recruiter workload without increasing false negatives.
Don't help — own it end-to-end
Transfers a whole household domain (medical, school forms, groceries) to dad with clear standards and reminders. Partial delegation creates more work for the "manager." Full ownership reduces it.
Wikipedia-grade AI pattern removal
Comprehensive AI writing cleanup based on Wikipedia's WikiProject AI Cleanup guidelines. Catches 24+ distinct patterns including inflated symbolism, em dash overuse, rule of three, copula avoidance, and sycophantic tone.