hr

# HR — People Operations

Umbrella skill for all people operations: recruiting, performance management, compensation, offer drafting, interview design, onboarding, org planning, people analytics, and policy lookup. Each mode loads its own references on demand.

**Scope**: Decisions and artifacts involving people's careers, compensation, and organizational structure. Use csuite for strategic business decisions, data-analysis for general analytics, professional-communication for non-HR business writing.

---

## Mode Detection

Classify the request into exactly one mode. If the request spans modes, choose the primary and note the secondary.

| Mode | Signal Phrases | References |
|------|---------------|------------|
| **RECRUITING** | Pipeline, candidates, sourcing, screening, hiring status, time to fill | `references/recruiting.md` |
| **PERFORMANCE** | Review, self-assessment, calibration, feedback, rating, promotion case | `references/performance-management.md` |
| **COMPENSATION** | Pay, salary, equity, comp bands, benchmarking, offer competitive, retention risk | `references/compensation.md` |
| **OFFER** | Draft offer, offer letter, comp package, signing bonus, start date | `references/compensation.md` |
| **INTERVIEW** | Interview plan, questions, scorecard, evaluation rubric, debrief | `references/recruiting.md` |
| **ONBOARDING** | New hire, first week, 30/60/90, onboarding checklist, buddy | `references/recruiting.md` |
| **ORG-PLANNING** | Headcount, reorg, team structure, span of control, org design | `references/org-planning.md` |
| **PEOPLE-ANALYTICS** | Attrition, headcount report, diversity metrics, org health, flight risk | `references/org-planning.md` |
| **POLICY** | PTO, benefits, leave, expenses, handbook, remote work policy | (no reference — use user-provided policy docs) |

**Always load**: `references/llm-hr-failure-modes.md` — applies to every mode.

---

## Sensitivity Guardrails

HR content touches people's careers, livelihoods, and legal rights. These guardrails are non-negotiable.

| Rule | Rationale |
|------|-----------|
| Source compensation data from user-provided or public databases | Invented market rates cause real pay decisions. State "I don't have current market data" when you don't. |
| Focus recommendations on skills, behaviors, outcomes | "Hire more [group]" or "this candidate fits the culture" introduces bias. Focus on skills, behaviors, outcomes. |
| Include legal review disclaimer on all binding language | Offer letters, policy interpretations, and termination language need legal review. Always state this. |
| Ask for jurisdiction before advising on compliance | Employment law varies by country, state, city. Ask for jurisdiction before advising on compliance, leave, or termination. |
| Minimize PII retention; use role/level identifiers | Names, salaries, SSNs, demographics — minimize retention. Use role/level when names aren't needed. |
| Flag when output needs legal review | Offer letters, PIPs, termination docs, policy changes, accommodation decisions — always flag. |

---

## Workflow

### Mode: RECRUITING

**Framework**: DEFINE → PIPELINE → EVALUATE

**Phase 1: DEFINE** — Clarify role requirements and pipeline structure.

- Define role: title, level, team, location, hiring manager
- Establish pipeline stages: Sourced → Screen → Interview → Debrief → Offer → Accepted
- Set target metrics: time-to-fill, pipeline velocity, source mix
- Design job posting — check against `references/llm-hr-failure-modes.md` for biased language (because gendered/exclusionary language reduces qualified applicant pools by 10-40%)

**Gate**: Role defined. Pipeline stages agreed. Posting reviewed for bias.

**Phase 2: PIPELINE** — Track and manage candidates through stages.

- Report pipeline health: candidates per stage, days in stage, conversion rates
- Flag bottlenecks: stages with >2x average dwell time
- Track source effectiveness: which channels produce hires, not just applicants

**Gate**: Pipeline metrics current. Bottlenecks identified.

**Phase 3: EVALUATE** — Structure interviews and decisions.

- Generate interview plan: 4-6 competencies, behavioral questions per competency, scoring rubric (1-4 scale with anchors)
- Assign panel: map interviewers to competencies, ensure diverse perspectives
- Produce debrief template: structured format, evidence-based, no "gut feel" fields
- Score candidates against rubric, not against each other (because comparative scoring amplifies similarity bias)

**Gate**: Interview kit complete. Debrief structured. Decision evidence-based.

**Onboarding sub-mode** (after offer acceptance):

- Pre-start checklist: accounts, equipment, buddy assignment, welcome email
- Day 1 schedule: orientation, IT setup, team intros, expectations
- Week 1 plan: compliance training, documentation, shadowing, first task
- 30/60/90-day goals: measurable, role-specific milestones

---

### Mode: PERFORMANCE

**Framework**: STRUCTURE → WRITE → CALIBRATE

**Phase 1: STRUCTURE** — Select review type and load template.

| Type | Use When |
|------|----------|
| Self-assessment | Employee writing their own review |
| Manager review | Manager writing review for direct report |
| Calibration prep | Preparing rating distributions for calibration meeting |

**Gate**: Review type selected. Template loaded.

**Phase 2: WRITE** — Generate review content with behavioral specificity.

Self-assessment:
- Key accomplishments: situation, contribution, impact (measurable)
- Goals review: status + evidence per goal
- Growth areas and challenges
- Next-period goals (specific, measurable)

Manager review:
- Overall rating with 2-3 sentence summary
- Strengths with specific behavioral examples (not personality traits)
- Development areas with actionable guidance (not vague directives)
- Goal achievement ratings with observations
- Development plan: skill → current level → target → actions
- Compensation recommendation with justification

**Constraint**: Describe observabl