Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Mgr Stay Interview

ASecurity

Prepares a stay interview with a question set on what keeps someone here, a listening notes page in their words, and a stay plan of actions the manager owns with dates. Use for "run mgr-stay-interview", "stay interview", "stay interview questions", "why do my good people leave", "keep my best people", "retention conversation", "I did not see the resignation coming", part of the AI for Managers Pack by Polar Bear.

2 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsrustgoperformance

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill mgr-stay-interview --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mgr Stay Interview?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Mgr Stay Interview
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-mgr-stay-interview/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-mgr-stay-interview)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: mgr-stay-interview
description: Prepares a stay interview with a question set on what keeps someone here, a listening notes page in their words, and a stay plan of actions the manager owns with dates. Use for "run mgr-stay-interview", "stay interview", "stay interview questions", "why do my good people leave", "keep my best people", "retention conversation", "I did not see the resignation coming", part of the AI for Managers Pack by Polar Bear.
---

# Stay Interview

## When To Use
Good people leave and you did not see it coming. The quiet, reliable ones looked low maintenance until the resignation landed. It answers, before it is too late: what keeps this person here, what would make them go, and what will you change?

## When Not To Use
If you cannot or will not act on anything you hear, do not ask; a stay interview with no follow-up does more harm than none. For growth and next steps use Career Conversation, and for themes from a whole group use Skip-Level Meeting.

## Inputs
- The person's role, how long they have been on the team, and anything they have already said about what they enjoy or find hard (no guesses about their mood)
- What you can actually change: work, schedule, projects, recognition, learning
If you have none of this, I start from the role alone and mark the output as a first draft.

## Approach
The stay interview, as described in SHRM's public article "How to conduct stay interviews: 5 key questions". Its themes, paraphrased here: what people look forward to, what they are learning and want to learn, why they stay, when they last thought about leaving and why, and what the manager could do differently. The manager listens far more than talks and turns what they hear into a plan. The failure it prevents: the manager asks "are you happy here?", hears "yes, fine", and learns the truth in the exit interview.

## Workflow
1. Ask: how long have they been with you? What have they said about what they enjoy or find hard? What can you genuinely change in the next months?
2. Set it up as its own meeting, never tacked onto a performance review or a 1:1 about a problem. Draft a two-line invitation that says why and that nothing is being evaluated.
3. Question set: one or two open questions per theme (looking forward to, learning, why they stay, last time they thought of leaving, what you could do), in your own words. Put the leaving question in the middle, once trust is there.
4. Probes: after each answer, "give me an example" or "tell me more". Plan to talk for a small share of the time; the user sets how long the meeting runs.
5. Listening notes: in their words, not your interpretation, shared with them afterwards so they can correct them.
6. Stay plan: actions for the manager only, each with a date, split into "can do now" and "will ask about". Strike anything you cannot deliver, and say what you will try, not what you promise.

## Output Format
```markdown
# Stay Interview Plan
**Person:** [name] · **Date:** [date] · **Length:** [set by you]
**Invitation:** [two lines on why, and that nothing is evaluated]
## Question set
| Theme | Question | Probe |
|---|---|---|
| What they look forward to | [open question] | Give me an example |
| Learning, now and wanted | [open question] | Tell me more |
| Why they stay | [open question] | Give me an example |
| Last time they thought of leaving | [open question] | What was happening then? |
| What I could do differently | [open question] | Tell me more |
## Listening notes (their words)
| Theme | What they said |
|---|---|
| [theme] | [notes] |
## Stay plan (manager actions)
| Action | Can do now or will ask about | By when | Told them by |
|---|---|---|---|
| [action] | [now / ask] | [date] | [date] |
## Decision
[manager name] decides which actions to commit to by [date] and tells [name] what will and will not change by [date].
```

## Done When
- The meeting is separate from any performance conversation
- Every theme has an open question and a probe; notes are in the person's words, to be shared
- Every stay plan action belongs to the manager and has a date

## Quality Bar
- Questions are written fresh, not copied from the source article
- No question asks the person to rate their happiness or loyalty
- Nothing promises pay, promotion or changes outside the manager's control, and the notes never feed a performance record
- Claude prepares the questions and the plan; it never scores flight risk or lists who might leave.

## Next
Run mgr-recognition-note (Employee Recognition Note), since feeling unseen often comes up.

## About the makers

This pack is made by Polar Bear, a consultancy built by ex-McKinsey founders with a dream to make AI work for People, not instead of them. We help our clients build people systems and AI-first ways of working, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

Attribution

polar-bear-orgpolar-bear-org
View sourceSee grades on GitHubMore from polar-bear-org →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →