HR & RecruitingYear-End Stage Review (CN-only)#HR#year-end#talent strategy

HR Year-End Review · Talent Year-in-Review

HR year-end isn't 'hired 30 / churned 5'. Use talent-system + systemic lessons + next-year focus to show leadership People is strategic, not just HR ops.

Pain addressed · People-lead year-end reviews drown in 'numbers + culture slogans'. The CEO leaves not knowing what the People team plans to do next year.

HR Year-End Review · Talent Year-in-Review

Prompt·Advanced
Also available in 中文 →
You're my HR year-end review partner. I'm a People lead. Help me write a review where CEO / board see talent strategy, not HR ops.

# Full year of talent work
{paste_yearly_talent}
Includes hiring funnel data / churn / engagement / DEI / key launches / key decisions / personal growth. Order doesn't matter.

# Company strategy context this year
{company_strategy_context}

# Output four sections

## 1. Talent state of the year (120 words)
One judgment sentence + 3 numbers:
- "This year we grew from X to Y, 90-day churn from A to B, talent-system strongest at [C], weakest at [D]"
- No "achieved remarkable results, will continue optimizing" filler.

## 2. Systemic talent learnings (2-3, 80 words each)
Patterns surfacing across the year:
- e.g. "our hiring rubric skews senior — mid candidates always fail in final round"
- e.g. "new-hire churn clusters under 2 managers — manager calibration > onboarding revamp"
This is People's real year-end strategic value, not number reporting.

## 3. The one decision I own as wrong (80 words)
The year's most important talent decision to own:
- Not "tough market" cop-outs
- Must reach "I bet on X talent strategy; reality showed Y; root mistake was my judgment about Z"

## 4. Next year's one People strategic bet (80 words)
Not a KPI list — one strategic bet:
- e.g. "next year bet on hiring quality, not quantity, executed via [specific system change]"
- Include: measurement + kill criteria

# Boundaries
- No "build A-team / strengthen culture" filler.
- The mis-decision must reach strategic layer, not ops execution.
- Exactly one strategic bet for next year. More = undecided.
Saves ~180 min per use

Open directly on your favourite AI

One click copies the prompt and opens the platform in a new tab — just paste (⌘/Ctrl + V).

Workflow · 5 steps

  1. 1

    T-2 weeks before review: dump the year's talent data, systemic signals, key decisions, and personal growth into one block.

  2. 2

    Run in Claude or DeepSeek R1. Fill the 2 placeholders.

  3. 3

    The systemic learnings section is where strategic value sits — push the model for cross-year patterns, not isolated events.

  4. 4

    Audit the mis-decision yourself. Honest ownership, no external attribution.

  5. 5

    Send a draft to the CEO 1 week ahead. Their reaction ('next year's People strategy now feels clear') tells you it landed.

Verify before you ship

AI's "almost right" is the #1 pain. Tick these off so reviewers can't find the obvious holes. (Checkbox state stays local — we don't track it.)

Done 0 / 5 checks

Why this prompt works

This prompt isn't a generic “write me a Year-End Stage Review (CN-only)”. It folds in the concrete context a HR & Recruiting actually faces (target reader, info density, deliverable format). LLMs deliver an order-of-magnitude better answer when they get role × scenario × constraints together — they can make the right tradeoffs about what to spotlight and what to cut.

When to use

Best moment: you know roughly that you need to do a Year-End Stage Review (CN-only), but you're stuck on “how do I even ask the AI?” Muscle memory has no template. Copy this card, tweak 2-3 fields per the workflow, and get a first revisable draft in 30 seconds.

Common pitfalls

  • Send without tweaking placeholders · the draft reads as default-GPT and your reviewer spots it in 3 seconds.
  • Skip the verify checklist · “almost right” failures usually hide in a thing you assumed the model handled but it didn't.
  • Stop after the first answer · a single follow-up like “make section X tighter / more formal” usually pushes a 70 → 90.

Variants & extensions

Want to use this card more aggressively? Three extensions:

  • Swap languages: both EN/ZH prompts ship in the card — use the EN version when shipping to a Western audience.
  • Swap platforms: the same prompt has slightly different taste on ChatGPT / Claude / Kimi. The recommended-platform pill marks the best fit.
  • Stack the checklist: paste the verify checklist back into the chat and ask the AI to self-audit — error rate drops sharply.
PromptDeck Pro Bundle

Want 25 more prompts like this one?

Get the full 50-card Pro deck — multi-step chains, vertical variants, lifetime updates.

  • 50 prompts · 25 free + 25 advanced multi-step chains
  • PDF printable + Notion template
  • Lifetime updates · ~5 new prompts a month, auto-synced
  • Dual-language · EN/CN + 5 China-exclusive scenarios
Get Pro · $9 lifetime14-day refund · no questions · powered by Lemon Squeezy

Related cards