Hire an AI employee performance review writer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A per-person evidence list, every claim dated
• A draft review per person in your format
• A conversation plan that asks for their view first
• A hard message only where it is earned
• Next quarter's objectives and dated key results per person
• A list of problems to raise now rather than grade

How it does the job well

• Base people decisions on job-related evidence, applied the same way to everyone.
• Write in plain, respectful language the person affected could read.
• Keep personal data to what the task needs, and handle it privately.
• Check local employment law and company policy before advising on hiring, pay or exits.

Mistakes it avoids

• Grading someone on a problem they never heard about.
• Softening the point until it is lost.
• Writing the review from the last two weeks.
• Setting next quarter's goals without asking what the business needs.
• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.

What a good result looks like

An example, not your task: You manage people and owe each one a performance review at the end of the quarter.

• The quarter. One line with reviews written, key results hit and missed, hard messages and thin reviews.
• Evidence list. Each key result and every dated note for the person, with whether the problem was raised.
• Raise now, do not grade. Problems nobody raised during the quarter, to say in the meeting and keep out of the grade.
• Draft review. Each section of your saved format, with every claim tied to a result or a dated note.
• Conversation plan. What to praise, what to say, how to say it, and the question to ask first.
• Hard message. A written message, only where results missed and a raised problem repeated. Otherwise it says not earned.

How the work is checked

• Every claim in every review points at a result or a dated note.
• No hard message was written for a problem never raised in the quarter.
• Every review follows the saved format and its rules on what is written.
• Next quarter's goals tie to what the business needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Kim Scott and Abraham Lincoln would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Set the format once. Builds the review questions and the rules on what is written down, for counsel to check.
• Gather the evidence per person. Lists each key result and every dated note, and flags problems never raised during the quarter.
• Draft the review. Writes each section from the evidence only, in plain words that say where the person stands.
• Plan the conversation. What to praise, what to say and how, opening by asking for their view of the quarter.
• Write the hard message when earned. Only where results missed and a raised problem repeated, the written message that keeps the person.
• Draft next quarter's goals. A few objectives with dated key results per person, from what the business needs next.
• Refresh recognition yearly. A reward plan where anyone who reaches the level wins.
• Log and hand back. Saves each person's file and stops. Nothing is sent.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id quarterly-performance-review-keeper only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/quarterly-performance-review-keeper/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Each person's objectives and key results for the quarter, marked hit or missed (from your goals doc or tracker)
• Your one-on-one notes, wins and problems for each person, with dates (advised; the Weekly one-on-one prep keeper's person files work)
• The numbers each person owned this quarter (advised)
• One paragraph on what the business needs next quarter
• The review format you saved on the first run, checked with counsel (optional on the first run, it builds one)

Helpful context (optional)

• Each person's own written view of their quarter, if your format asks for one
• Peer feedback collected under your format's rules

Tools and access

• Claude Code: It can keep one private folder per person and read the one-on-one files from the quarter.
• Any good chat AI: Paste the agent and one person's goals and notes at a time. Keep the files private.
• Any good chat AI: Planning, questioning and structuring are text work any strong chat AI does well with this skill.
• A spreadsheet: Lets you track each key result against its date and share it with the team.
• Any good chat AI: Placing the situation and writing the plan is text work any strong chat AI does well.
• A calendar: Book the talk and the follow-up date straight away.
• Any good chat AI: Rewriting a message in a set tone is text work any strong chat AI does well.
• Your email or chat app: Read the draft in the same place it will be seen, so the length and tone fit.
• Any good chat AI: Turning goals and a budget into levels and praise lines is text work any strong chat AI does well.
• A shared spreadsheet: A visible tracker lets people see their own progress toward each level.

Functions and deliverables

• Employee performance review writer: Draft employee reviews from goals, results and dated notes. Get conversation plans, evidence gaps and proposed next-quarter goals.
  • A per-person evidence list, every claim dated
  • A draft review per person in your format
  • A conversation plan that asks for their view first
  • A hard message only where it is earned
  • Next quarter's objectives and dated key results per person
  • A list of problems to raise now rather than grade
• Objectives and key results writer: Write team goals and key results for the quarter. Give it your team and aim. You get a few objectives with dated, numbered key results.
  • A few short objectives
  • Key results for each, with a number and a date
  • A link from each to the level above
  • A list of what you will not do, and a note on how to use the set
• Feedback conversation planner: Plan a feedback conversation that gets heard. Describe the person and the problem. You get what to praise, what to say and how to say it.
  • Which box on the chart you are in now, and what to change
  • One piece of specific praise to open with
  • The behaviour and effect, in words to say
  • Questions to ask and a follow-up date
• Hard feedback message writer: Share what happened, who needs feedback and the change you want. Get a clear, respectful draft focused on one behaviour.
  • A draft message you can send or say
  • The one behaviour it asks to change, in plain words
  • A list of the true praise it used and where that came from
  • A note on how you could save face for them
• Recognition plan designer: Plan a team recognition and reward program where anyone who reaches a goal level wins, with prizes people want and a public moment.
  • A review of who wins now and why that matters
  • Levels and goals that anyone can reach on their own
  • Prizes, public moments and praise lines for each level
  • A budget check and a pay fairness check
• HR partner: Get an HR partner that drafts job posts, interview kits, onboarding plans, review plans and policies. Check key items with a lawyer before use.
  • Ready-to-edit HR documents
  • Interview kits with scoring guides
  • Onboarding or review checklists
  • A rollout checklist with owners
  Source: sickn33.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Kim Scott: Prepare feedback using Kim Scott’s recorded approach. Ask for criticism, describe the work clearly and follow up with care.
  • Your problem worked on the way Kim Scott would: their questions, their method, their push-back
  • The answer or the work, in Kim Scott's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Abraham Lincoln: Work through team conflict, hard choices and plain speeches using Abraham Lincoln’s recorded approach. Start with facts and a shared goal.
  • Your problem worked on the way Abraham Lincoln would: their questions, their method, their push-back
  • The answer or the work, in Abraham Lincoln's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You manage people and owe each one a performance review at the end of the quarter.
• Your last reviews were written from memory and it showed.
• You want next quarter's goals to come from where the business is going, not from last quarter's list.
• A review is due for a person whose problem you noted twice, and you are not sure it is fair to grade it.

Limits to check before starting

• Someone is facing a warning, a dismissal or a legal complaint. That needs your HR lead or counsel, not a review draft.
• You have no dated notes and no key results for the quarter. It will say the review is thin. Start with the One-on-one agenda and feedback planner and come back next quarter.
• You want to prepare this week's one-on-one. Use the One-on-one agenda and feedback planner.
• You only need next quarter's goals for one person. Use the Objectives and key results writer on its own.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Open the agent in Claude, ChatGPT or Gemini, or paste it into a new chat. In Claude Code, add it as a skill or save it in .claude/agents so it can keep one folder per person.
• On the first run, approve the review format and have counsel check it before you share any review. It is saved and reused.
• Paste one person's goals and dated notes at a time, or point it to their folder. Add your paragraph on next quarter. Leave out anything you would not want in a review file.
• Read each review against its evidence. Every claim should point to a result or a dated note. Change what you disagree with.
• Hold the meetings yourself, and ask for their view first. Approve next quarter's goals with each person, then save them for the next run.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/quarterly-performance-review-keeper for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.