Walk in with what you saw, not what you feel about it.
A one-page prep sheet for a difficult performance conversation, built from dated examples, a clear standard, and a specific ask.
Managers put these conversations off because the concern feels vague. When they finally hold one, they bring a label like careless or disengaged, the employee disputes it, and both leave unsure what was agreed.
Performance Conversation Prep turns the label into dated observations, checks whether the standard was ever stated, picks the two or three strongest examples, and writes the opening lines. It prepares your replies to the likely pushback and sets a date for the follow-up.
What it produces.
- →A list of observed facts with dates, with the interpretations removed
- →A one-sentence standard that a third party could check
- →The first two sentences you will say, and prepared replies to three likely responses
- →A specific ask and a follow-up date
- ✦Managers who have been avoiding one conversation
- ✦New managers handling their first performance issue
- ✦Anyone who held the talk once and left it unclear
This Playbook prepares you for a conversation. It does not write the formal review. The Performance Review Writer Tool does that: it works through evidence, strengths, development areas, and goals into a full review draft. This Playbook does not include that document, and does not cover formal performance plans or dismissal.
See the Performance Review Writer Tool ($79) →- →performance-conversation-prep.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →performance-conversation-prep-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
What it does with a real question.
I manage a team of six, and I need to talk with Marcus, one of my senior analysts, on Thursday. Over the last two months he missed three of five sprint deadlines, including the March 14 client report, and he's been quiet in meetings. I've avoided saying anything because his earlier work was excellent.
Start with what you can state as fact. Three missed deadlines out of five, with the March 14 client report among them, is your evidence. "Quiet in meetings" is an impression, so leave it out of the opening or mention it only as something you've noticed and want to understand. If you lead with it, Marcus can dispute it, and he'd be right to, because nothing in it is dated or checkable.
My position: this is not yet a performance conversation, and you shouldn't treat it as one. Your own account explains why. Marcus did excellent work before, and nobody has said a word to him about the last two months. A strong senior analyst who suddenly slips and goes silent is often carrying something: a workload shift, a project he disagrees with, or something outside work. You don't know which, and guessing is how these meetings go wrong. The fairest framing is that you waited too long to ask.
For Thursday, open plainly: "I want to talk about the last two months. Three of the five sprint deadlines slipped, including the March 14 client report, and I should have raised it sooner." Then ask what has been getting in the way, and listen before you propose anything. Close with one specific ask, what you need to see on the next two sprints, and book a ten-minute follow-up in two weeks so the topic doesn't drift again.
The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude writes a polite script from your description of the problem. This asks what you actually saw, checks whether you ever set the expectation, and builds the conversation on examples the person can recognize.
How is this different from a Tool?
Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format. This Playbook prepares you for a conversation. It does not write the formal review. The Performance Review Writer Tool does that: it works through evidence, strengths, development areas, and goals into a full review draft. This Playbook does not include that document, and does not cover formal performance plans or dismissal.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.
People Playbooks are structuring aids. They are not legal or HR advice. Employment law differs between the US and the UK and between states and countries, so check anything touching dismissal, performance plans, pay, or protected characteristics with a qualified HR professional or employment lawyer.