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 Skip Level Meeting

ASecurity

Plans a Skip-Level Meeting in either direction, with an agenda, a question set, a way to share themes without naming anyone, and a dated follow-up. Use for "run mgr-skip-level-meeting", "skip-level meeting", "skip level agenda", "meeting with my boss's boss", "questions for a skip-level", "my director wants to meet my team", "prepare for a skip-level", part of the AI for Managers Pack by Polar Bear.

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

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill mgr-skip-level-meeting --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mgr Skip Level Meeting?

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

Security grade badge for Mgr Skip Level Meeting
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-mgr-skip-level-meeting/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-mgr-skip-level-meeting)

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-skip-level-meeting
description: Plans a Skip-Level Meeting in either direction, with an agenda, a question set, a way to share themes without naming anyone, and a dated follow-up. Use for "run mgr-skip-level-meeting", "skip-level meeting", "skip level agenda", "meeting with my boss's boss", "questions for a skip-level", "my director wants to meet my team", "prepare for a skip-level", part of the AI for Managers Pack by Polar Bear.
---

# Skip-Level Meeting

## When To Use
You run skip-levels with your reports' reports, or you are preparing for one with your boss's boss. Either way, the question is the same: how do I make this meeting useful to everyone without it going around the manager in the middle?

## When Not To Use
If you want one person's reasons to stay, run Stay Interview; a group meeting across levels will not surface them. If you need leadership to decide something specific, write a Managing Up Brief first and bring it.

## Inputs
- Which mode: you run it (with your reports' reports) or you attend it (with your manager's manager).
- The group or person, the time available, and anything already on the table.
- For running one: notes from past skip-levels, if any.
If you have none of this, I start from the mode and the length of the meeting, and mark the output as a first draft.

## Approach
The skip-level meeting is common management practice: a leader meets people two levels away to hear how the work really goes. Its value is listening across a gap; its risk is going around the middle manager, who then learns about the complaints from the grapevine. This skill keeps the middle manager informed, keeps the meeting on the work, and turns what was heard into themes nobody can trace back to one person.

## Workflow
1. Ask up to three questions: which mode, what you most want to learn or say, and how many mentions a theme needs before you report it (you set this number).
2. The middle manager first. Running one: tell your direct report before the invite goes out, say why, and agree what you will share back. Attending one: tell your own manager you have been asked and what you plan to raise.
3. Agenda, listening-heavy. Running: a short opening on why you are there and what happens to what you hear, then questions, then what you will do. Attending: what you want them to know, what you want to ask, and one thing you need.
4. Question set about the work: what gets in the way, what they would change, what leadership should know and does not. Nothing that asks people to assess their manager or a colleague.
5. Themes without names. Group what you heard, drop any detail that identifies a person (role, project, a phrase only one person uses), and keep a theme only if it reaches your threshold.
6. Follow-up: what you will do, what you will tell the group, and the date. Share the themes with the middle manager before or with the group.

## Output Format
```markdown
# Skip-Level Meeting Plan
**Mode:** [running / attending] **With:** [group or role] **Date:** [date] **Length:** [time]
**Middle manager told:** [name], on [date], agreed to share back [what]
## Agenda
| Part | Purpose | Time |
|---|---|---|
| [opening] | [why we meet, what happens to what is said] | [time] |
| [questions] | [listen] | [time] |
## Questions
- [question about the work]
## Themes heard
| Theme | Mentions | What it asks of leadership |
|---|---|---|
| [theme, no identifying detail] | [count, at or above threshold] | [ask] |
## Decision
[Your name] decides which themes to act on and tells [group] and [middle manager] by [date].
```

## Done When
- The middle manager is named in the plan with the date they were told.
- No question invites a verdict on a named person.
- Every theme meets the threshold and carries no identifying detail.
- The follow-up has a date and says who hears what.

## Quality Bar
- Listening time outweighs talking time in the agenda.
- Nothing said in the room becomes an evaluation of the middle manager.
- Anything that sounds like a grievance or a safety concern goes to HR, not into a theme.
- Promise only what you can deliver, with a date.
- Themes, never names: Claude never attributes a comment to a person.

## Next
Run mgr-change-announcement (Change Announcement) for when leadership's decisions land on your team.

## 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 →