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 Manager Readme

ASecurity

Writes a Manager README covering how I work, what I expect, how to disagree with me, how to reach me and what I am still learning, shared as a draft the team can correct. Use for "run mgr-manager-readme", "manager readme", "how I work document", "user manual for my team", "introduce myself to my new team", "I inherited a team", "reset with my former peers", "how to work with me doc", part of the AI for Managers Pack by Polar Bear.

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

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill mgr-manager-readme --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mgr Manager Readme?

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

Security grade badge for Mgr Manager Readme
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-mgr-manager-readme/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-mgr-manager-readme)

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-manager-readme
description: Writes a Manager README covering how I work, what I expect, how to disagree with me, how to reach me and what I am still learning, shared as a draft the team can correct. Use for "run mgr-manager-readme", "manager readme", "how I work document", "user manual for my team", "introduce myself to my new team", "I inherited a team", "reset with my former peers", "how to work with me doc", part of the AI for Managers Pack by Polar Bear.
---

# Manager README

## When To Use
The team does not yet know how you will manage, you inherited a team, or you need to reset how you work with people who were your peers last month. This answers: what does my team need to know about how I work, written so they can hold me to it?

## When Not To Use
If the question is how the whole team works together (channels, hours, meeting norms), that is a team decision; run Working Agreements. If you have not yet listened to the team, run New Manager 30-60-90 Day Plan first and write this after.

## Inputs
- How you actually spend your week, and how and when you reply to messages
- What you expect from the team, in your own words
- One or two things you know you are still learning as a manager
If you have none of this, I start from your answers to the three questions below, and mark the output as a first draft.

## Approach
The manager "how I work" document is common practice with no single public originator. Its value is not the writing; it is that the team can check it against what you do. The failure it prevents: a README promising "my door is always open" from a manager whose calendar has no free hour, which teaches the team that the manager's words are decoration.

## Workflow
1. Ask three questions: how do you really reply to messages and by when, what is one thing that frustrates you in how work reaches you, and what are you still learning?
2. Write five sections in the first person, each specific enough to test: how I work, what I expect, how to disagree with me, how to reach me, what I am still learning. Replace every adjective with a behaviour ("I reply to messages within [time the user sets]", not "I am responsive").
3. "How to disagree with me": give a real channel (in the 1:1, in writing, in the meeting) and a promise about what happens after, such as a reply by a date and a reason if you do not change course.
4. "What I am still learning": name one or two honest gaps. One real gap earns more trust than five strengths.
5. Check every line against what the manager actually does this month; cut or rewrite any line that promises what the calendar or inbox contradicts. Flag lines you cannot verify.
6. Share it as a draft the team can correct, with a review date. Their corrections go in, not to a footnote.

## Output Format
```markdown
# Manager README
Draft shared on [date]. Correct me: [where to comment]. Review date: [date].
## How I work
- [behaviour, e.g. "I block [time] for focus work and move it for urgent team issues"]
## What I expect
- [expectation as an action]
## How to disagree with me
- Channel: [1:1 / in writing / in the meeting]
- What happens after: [reply by when, and what I do if I keep my view]
## How to reach me
| For | Use | I reply within |
|---|---|---|
| [urgent / routine / sensitive] | [channel] | [time set by user] |
## What I am still learning
- [honest gap], and what I am doing about it: [action]
## Changes from team corrections
- [date]: [what changed and who asked]
## Decision
[name, the manager] reviews the team's corrections and publishes the revised version by [date].
```

## Done When
- All five sections are in the first person with testable behaviours
- "How to disagree with me" names a channel and what happens after
- Every line matches what the manager does today, or is cut
- A review date and a correction route are on the page

## Quality Bar
- No adjective without a behaviour behind it
- No promise the calendar contradicts
- One or two real gaps, not a disguised strength
- Says nothing about any individual team member

## Next
Run mgr-delegation-levels (Levels of Delegation) to make decision rights explicit.

## 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 →