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 New Manager Plan

ASecurity

Builds a New Manager 30-60-90 Day Plan with a listening plan, a map of the team's work, first decisions and early wins, and a 90-day check with your own manager. Use for "run mgr-new-manager-plan", "first 90 days as a manager", "30-60-90 day plan for a new manager", "I just got promoted to manager", "taking over a new team", "first time manager plan", "where do I start as a new manager", "promoted with no training", 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-new-manager-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mgr New Manager Plan?

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

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

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-new-manager-plan
description: Builds a New Manager 30-60-90 Day Plan with a listening plan, a map of the team's work, first decisions and early wins, and a 90-day check with your own manager. Use for "run mgr-new-manager-plan", "first 90 days as a manager", "30-60-90 day plan for a new manager", "I just got promoted to manager", "taking over a new team", "first time manager plan", "where do I start as a new manager", "promoted with no training", part of the AI for Managers Pack by Polar Bear.
---

# New Manager 30-60-90 Day Plan

## When To Use
You were promoted with no training, or you are taking over a new team, and nobody told you the job changed overnight. This answers one question: what do I do in which order over the next 90 days, so I listen before I change anything?

## When Not To Use
If you are already months in and the problem is one meeting or one person, this sequence is too broad; run One-on-One Meeting Agenda for the 1:1s or Manager README to reset how you work with the team.

## Inputs
- Your start date, the team's names and roles, and who your own manager is
- What you were told the team is for, and anything you were asked to fix
- Key stakeholders outside the team, and anything already in flight (deadlines, open roles, changes)
If you have none of this, I start from your start date and a list of roles, and mark the output as a first draft.

## Approach
The 30-60-90 day plan is common manager practice with no single public originator: listen, then decide, then check. The self-check uses the manager behaviours in Google re:Work's "Following the data: the research behind great managers" (coach, give room without micromanaging, support careers), as prompts to reflect on, never as a score. The failure it prevents: the new manager who rewrites the process in week two, then learns in week six why it was built that way, and has spent the team's trust to find out.

## Workflow
1. Ask three questions: were you promoted from inside this team (so you now manage former peers), what did your manager say success looks like at 90 days, and what is already on fire that cannot wait?
2. Days 1 to 30, listen: plan a first 1:1 with every report and each key stakeholder, using the same questions each time so answers compare as themes, not as verdicts on people. Hold back any change unless something is unsafe or a deadline forces it.
3. Map the team's work: what comes in, who does it, where it gets stuck, and what only you do today. Describe work and bottlenecks; never who is strong or weak. The "only you" list is your first delegation backlog.
4. Days 31 to 60, first decisions: pick two or three, each with who it affects and who you consulted. If you cannot name who you consulted, it is not ready.
5. Early wins: take them from what the team asked for in the listening round, not what you picked. A fix they named and you delivered buys more than a clever one they did not ask for.
6. Days 61 to 90: set a check with your own manager against what you both agreed on day one, and run the re:Work behaviours as a private self-check with one line of evidence each.

## Output Format
```markdown
# New Manager 30-60-90 Day Plan
## Days 1 to 30: listening plan
| Person or group | Date | Questions (same set for all) |
|---|---|---|
| [name, role] | [date] | [question 1 to 3] |
## Map of the team's work
| Work that comes in | Who does it | Where it gets stuck | Only I do it today? |
|---|---|---|---|
| [work item] | [role] | [bottleneck] | [yes / no] |
## Days 31 to 60: first decisions
| Decision | Who it affects | Who I consulted | Date |
|---|---|---|---|
## Early wins (asked for by the team)
- [fix] requested by [role or group], done by [date]
## Days 61 to 90: check with my manager
- Agreed on day one: [expectation]. Where it stands: [evidence]
- Self-check (coach, give room, support careers): [one line each]
## Decision
[name, your manager] and you agree the 90-day expectations by [date], and review them together on [date].
```

## Done When
- Every report and key stakeholder has a dated listening slot, with one shared question set
- The work map names work and bottlenecks only, with no comment on any person
- Each first decision lists who it affects and who was consulted
- Every early win traces back to something the team asked for

## Quality Bar
- No change in the first 30 days unless it is unsafe or deadline-driven, and then say why
- Themes from the listening round are written without attributing them to a named person
- Decisions are capped at two or three; more is a reorganisation, not a first 60 days
- The self-check is reflection for you, not a rating to show anyone

## Next
Run mgr-one-on-one-agenda (One-on-One Meeting Agenda) to run the listening 1:1s.

## 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 →