Self-Improving HR Skill

Log HR-specific learnings, process issues, and feature requests to markdown files for continuous improvement. Captures policy gaps, compliance risks, recruiting bottlenecks, onboarding friction, retention signals, candidate experience problems, compensation anomalies, and offboarding gaps. Important learnings get promoted to policy documents, onboarding checklists, interview scorecards, or compliance calendars.

First-Use Initialisation

Before logging anything, ensure the .learnings/ directory and files exist in the project or workspace root. If any are missing, create them:

mkdir -p .learnings
[ -f .learnings/LEARNINGS.md ] || printf "# HR Learnings\n\nPolicy gaps, compliance risks, recruiting insights, onboarding friction, retention signals, and offboarding gaps captured during HR operations.\n\n**Categories**: policy_gap | compliance_risk | process_inefficiency | candidate_experience | retention_signal | onboarding_friction\n**Areas**: recruiting | onboarding | compensation | compliance | performance | offboarding | dei\n\n---\n" > .learnings/LEARNINGS.md
[ -f .learnings/HR_PROCESS_ISSUES.md ] || printf "# HR Process Issues Log\n\nCompliance risks, process failures, candidate experience issues, and policy violations.\n\n---\n" > .learnings/HR_PROCESS_ISSUES.md
[ -f .learnings/FEATURE_REQUESTS.md ] || printf "# Feature Requests\n\nHR tools, automation capabilities, and process improvement requests.\n\n---\n" > .learnings/FEATURE_REQUESTS.md

Never overwrite existing files. This is a no-op if .learnings/ is already initialised.

CRITICAL — PII PROTECTION: NEVER log personally identifiable information in any learnings file. This includes SSNs, salary details, medical information, performance ratings for specific individuals, home addresses, dates of birth, or any data that could identify a specific employee or candidate. Always anonymize examples. Use role titles, department names, or anonymized identifiers (e.g., "Employee A", "Candidate #12") instead of real names.