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 Working Agreements

ASecurity

Facilitates and writes up a team's working agreements covering channels, hours and response times, meeting norms, the escalation path and a review date. Use for "run mgr-working-agreements", "working agreements", "team norms", "how we work together", "team ground rules", "agree response times with my team", "every clash on my team is personal", part of the AI for Managers Pack by Polar Bear.

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

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill mgr-working-agreements --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mgr Working Agreements?

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

Security grade badge for Mgr Working Agreements
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-mgr-working-agreements/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-mgr-working-agreements)

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-working-agreements
description: Facilitates and writes up a team's working agreements covering channels, hours and response times, meeting norms, the escalation path and a review date. Use for "run mgr-working-agreements", "working agreements", "team norms", "how we work together", "team ground rules", "agree response times with my team", "every clash on my team is personal", part of the AI for Managers Pack by Polar Bear.
---

# Working Agreements

## When To Use
Nobody ever agreed how the team works, so every clash turns personal: a late reply reads as disrespect, a weekend message as pressure, a skipped meeting as a snub. Use this to run a session where the team writes its own rules, and to answer: what do we expect of each other, and what happens when it slips?

## When Not To Use
If it is only your own way of working you want to explain, run Manager README. If the question is AI use alone, run Team AI Playbook; if the team lacks a purpose and scope, run Team Charter. Agreements will not fix a live conflict between two people: run Conflict Resolution first.

## Inputs
- Where friction shows up today (late replies, meetings, handoffs), in your words, with no names
- The team's channels, time zones and current meeting pattern
- Any existing norms, written or assumed
If you have none of this, I start from the channel list and meeting pattern and mark the output as a first draft for the session.

## Approach
Working agreements, as set out in the Atlassian Team Playbook working agreements play: the team shares its working preferences and context, then agrees together how it will communicate, meet, give feedback and escalate, and revisits the agreement over time. The judgment is that agreements made together get kept and agreements handed down get ignored. The failure it prevents: the manager writes a tidy norms page on a Sunday night, posts it, and nothing changes because nobody chose any of it.

## Workflow
1. Ask up to three questions at once: where the friction shows up, how the team is spread across hours and places, and whether you will run the session live or in writing.
2. Draft the opening round: each person shares working preferences and context (focus hours, caring times, how they like feedback). Sharing is optional; nobody has to explain their life.
3. Build the prompts for channels and their purpose (what is urgent, what can wait, where decisions are recorded), working hours and time zones, and response times. The team sets every number; I offer questions, not defaults.
4. Add the meeting plan: which meetings are live, which become written updates, and the norms inside them (agenda ahead, cameras, who takes actions).
5. Add feedback preferences and the escalation path: what to do when an agreement is not kept, first person to person, then as a team topic, then to you.
6. Write up only what the team agreed, in plain sentences anyone could check. I set the review triggers: quarterly, and when someone joins, the team changes, or an agreement is broken.

## Output Format
```markdown
# Team Working Agreements
Agreed by: [team] | Date: [date] | Review: [date]
## Channels
| Channel | Use it for | Not for | Expected response time |
|---|---|---|---|
| [channel] | [purpose] | [exclusion] | [team sets] |
## Hours and Time Zones
- Core overlap: [team sets]
- Outside hours: [what we agree about messages and replies]
## Meeting Norms
| Meeting | Live or written | Norms |
|---|---|---|
| [meeting] | [format] | [agenda ahead, actions, other] |
## Feedback and Escalation
- How we give feedback: [agreed preference]
- When an agreement slips: [step 1] then [step 2] then [step 3]
## Review Triggers
- Quarterly on [date]; also when someone joins, the team changes, or an agreement is not kept
## Decision
[name] shares the final text with the team by [date]; the team confirms or amends it at the meeting on [date].
```

## Done When
- Every agreement was proposed or confirmed by the team, not only by you
- Each line is specific enough to tell whether it is being kept
- Response times and hours are numbers the team chose
- The escalation path starts person to person and has a review date

## Quality Bar
- Fewer agreements, kept, beat a long list nobody reads
- No agreement asks people to disclose personal reasons for their hours
- Nothing tracks who breaks an agreement; a breach becomes a team topic, never a record against a person
- Wording is behaviour ("reply within [time] on [channel]"), never attitude ("be responsive")
- The review date is real and on the calendar

## Next
Run mgr-team-retrospective (Team Retrospective (Start, Stop, Continue)) to check the agreements in practice.

## 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 →