Prepare a 1:1 with a developer
What to recognize, what to ask about, and what you owe them, built from their last month of work.
How it works
- 01
Copy the prompt
Fill in the [bracketed] placeholders or leave them: the assistant asks for what is missing.
- 02
Paste it into your AI app
Claude, ChatGPT, Cursor or your own app, connected to DevStats MCP. Set up DevStats MCP
- 03
Get the deliverable
conversation-guide.md
The prompt
I have a 1:1 coming up with someone on my team. I want to show up prepared: knowing what they shipped, what got in their way, and what I should be doing for them.
## Context
- Developer: [name or login] in squad [squad] (use List Players to resolve the login)
- Period: [last 30 days], compared with the 30 days before it
- What I already know: [vacation, on-call, new to the team, led a big project, nothing special]
- This is for a supportive conversation. None of it goes into a performance review, and none of it is a ranking.
- If I left anything in [brackets], keep what reads as a default (a period, a number of days, the first of several options) and ask me for the rest in one go, before pulling any data.
- Write everything, the deliverable included, in the language of this prompt.
## Pull this data from DevStats (both periods)
1. Player Metrics for the squad — to see this person inside the squad's range, not to rank them
2. PR List filtered by this player, fields title, url, repository, size_total, cycle_time_coding, cycle_time_pickup, cycle_time_review, review_count, merged_at
3. Code Review filtered by this player — the reviews they gave
4. Issue List filtered by this player, fields key, summary, issue_type, project, cycle_time_formatted, resolved_at
5. Daily WIP filtered by this player — how many things they hold open at once
6. Activity Heatmap filtered by this player — only to spot sustained evening or weekend work
## How to analyze
- Compare the person with their own previous period, not with teammates. A drop after a steady run is worth a question. A steadily low number is often just the role: people who review, unblock and mentor merge fewer PRs.
- Count the reviews they give next to the PRs they author. Someone reviewing a lot and merging less is carrying the team's review queue. Recognize it and ask whether it is sustainable.
- Long pickup time on their PRs means the team is slow to review them. That is something I owe them, not something they owe me.
- Many branches and issues open at once means they are being pulled in several directions. The question is who is interrupting them.
- Weeks of mostly bugs and hotfixes is a growth problem, even when the numbers look great. Ask if that is the work they want.
- Large PRs are a coaching topic about slicing, not a complaint.
- Sustained evening or weekend activity is a wellbeing flag. Raise it as care. Never praise it.
- Use the context I gave. Vacation and on-call explain dips; do not turn them into findings.
## Deliver
A one-page 1:1 guide:
1. **Recognize** — two specific things worth calling out, naming the actual PRs or issues.
2. **Ask about** — three open questions, each with the observation behind it, phrased as curiosity: "I noticed X, what is going on there?"
3. **What I owe them** — things the data says the team or I should fix for them: slow reviews, interrupt load, unclear priorities.
4. **Growth topic** — one, tied to the kind of work they have been doing.
5. **Leave out** — numbers that look odd but are explained by context or are too noisy to mention.
What it returned
Download the exampleStop guessing. Start asking.
Connect DevStats MCP to your AI assistant and turn these prompts into instant answers. Copy a prompt and go.