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 Return To Work Conversation

ASecurity

Plans a supportive return-to-work conversation with a welcome plan, open questions, support and adjustments to consider, what stays confidential, and the note the person agrees to. Use for "run mgr-return-to-work-conversation", "return to work meeting", "someone is back after sick leave", "welcome back after absence", "a report is struggling with things outside work", "back to work interview questions", "phased return conversation", part of the AI for Managers Pack by Polar Bear.

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

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill mgr-return-to-work-conversation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mgr Return To Work Conversation?

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

Security grade badge for Mgr Return To Work Conversation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-mgr-return-to-work-conversation/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-mgr-return-to-work-conversation)

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-return-to-work-conversation
description: Plans a supportive return-to-work conversation with a welcome plan, open questions, support and adjustments to consider, what stays confidential, and the note the person agrees to. Use for "run mgr-return-to-work-conversation", "return to work meeting", "someone is back after sick leave", "welcome back after absence", "a report is struggling with things outside work", "back to work interview questions", "phased return conversation", part of the AI for Managers Pack by Polar Bear.
---

# Return-to-Work Conversation

## When To Use
Someone is back after absence, or life outside work is hitting work and you do not know how to raise it without it feeling like an attack. Use it before the first conversation after leave, sickness or a run of family emergencies. It answers: how do I welcome them back, find out what would help, and write down only what they want written?

## When Not To Use
This is not a performance conversation: if there is a work gap to address, that is Difficult Conversation Prep, later and separately. If the question is how the team covers the work, Team Capacity Planning fits better.

## Inputs
- How long they were away, and anything they chose to tell you
- What changed in the team and the work while they were gone
- Your organisation's absence or return policy, if you have it
If you have none of this, I start from the date they are back and mark the output as a first draft.

## Approach
This follows Acas guidance on return-to-work meetings: hold them in private, check the person is ready, share what changed, ask what they want colleagues to know, and consider support such as flexible working, a phased return, adjustments or an occupational health referral. The judgment is to support, not to penalise. The failure it prevents: a "welcome back" that becomes an interrogation of whether the absence was real, and a report who never tells you anything again.

## Workflow
1. Ask at most three questions: how long they were away, what they have already shared with you, and when and where the meeting can happen privately.
2. Setting: a private, confidential conversation, agreed with them in advance, not ambushed on the first morning.
3. Welcome plan: the first minutes are about them being back, then what changed while they were away (people, priorities, decisions), in plain lines.
4. Questions: open and about the work ("what would make this week manageable?"). I never draft a question about symptoms, diagnosis or whether they were really ill.
5. Ask what they would like colleagues to know, and record their exact answer.
6. Support to consider: flexible working, a phased return, reasonable adjustments, an occupational health referral. Each is marked "check with HR or a qualified adviser"; I do not state what they are entitled to.
7. Agreed note: only what the person agreed to record, shared with them, with a follow-up date.

## Output Format
```markdown
# Return-to-Work Meeting Plan
## Setting
[Where, when, agreed with them on (date)]
## Welcome and What Changed
- [change in people, priorities or decisions]
## Questions
- [open question about the work and what would help]
## Support to Consider
| Option | Check with | Status |
|---|---|---|
| [phased return, flexible hours, adjustment, occupational health] | HR or a qualified adviser | [to raise / agreed] |
## What Stays Confidential
[What they asked to keep private]
## What Colleagues Are Told
[Their words, as agreed]
## Agreed Note
[Only what they agreed to record]
## Decision
[name] confirms the agreed support with HR by [date] and checks in with the person on [date].
```

## Done When
- The meeting is private and agreed in advance
- No question touches symptoms, diagnosis or whether the absence was genuine
- Every support option is marked for HR or a qualified adviser
- The note holds only what the person agreed, and they get a copy

## Quality Bar
- No health or diagnosis detail in the note beyond what the person agrees.
- No absence scoring or counting against trigger points.
- What colleagues hear is the person's choice, in their words.
- Claude prepares the welcome and the questions; it never questions whether an absence was genuine or records health details.

## Next
Run mgr-capacity-check (Team Capacity Planning) to rebalance work around the return.

## 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 →