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

Pmc Run Decision Meeting

ASecurity

Plans and records a meeting built around one decision, producing the agenda with DACI roles and the pre-read, the way disagreement is recorded, and a decision record drafted in Claude Docs for you to send after. Use for "run pmc-run-decision-meeting", "plan a 45-minute meeting to decide on the pricing change", "who is the approver and who is only informed", "write the decision record from these notes", "meetings end with let's take this offline", "set up a DACI", part of the Claude Opus 5.5 f...

2 stars
0 votes
0 copies
0 views
Added 10/5/2026
ai-agentsgoreact

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill pmc-run-decision-meeting --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pmc Run Decision Meeting?

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

Security grade badge for Pmc Run Decision Meeting
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-pmc-run-decision-meeting/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-pmc-run-decision-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: pmc-run-decision-meeting
description: Plans and records a meeting built around one decision, producing the agenda with DACI roles and the pre-read, the way disagreement is recorded, and a decision record drafted in Claude Docs for you to send after. Use for "run pmc-run-decision-meeting", "plan a 45-minute meeting to decide on the pricing change", "who is the approver and who is only informed", "write the decision record from these notes", "meetings end with let's take this offline", "set up a DACI", part of the Claude Opus 5.5 for Product Managers Pack by Polar Bear.
---

# Run the Decision Meeting

## When To Use
The meeting ends with "let's take this offline" and nothing is decided. Use this before a meeting that must make one call, and again right after it: "Plan a 45-minute meeting to decide on the pricing change." It answers: who approves, what the room reads first, how the time is spent, and what gets written down so the call stays made.

## When Not To Use
If you do not yet know who decides or who can block, run Map the Stakeholders first. If you only need to log the decisions of the week, Wrap the Week does that. A meeting with no options and no recommendation is not ready; write the recommendation first.

## Inputs
- The decision in one sentence, the options, and the recommendation or memo.
- The people involved, by role, and the meeting length.
- After the meeting: your notes or the transcript.
If you have none of this, I start from the decision in one sentence, leave the roles as [placeholders], and mark the plan as a first draft.

## Approach
DACI, from the Atlassian Team Playbook: one Driver, exactly one Approver, Contributors who give input, and the Informed who hear the outcome. After the meeting, a decision record in the form Michael Nygard set out in 2011 (title, context, decision, status, consequences), with an owner and a review date added. The judgment is in naming one Approver and keeping disagreement on the record. The failure it prevents: two people who each thought the other approved, and the call undone in the hallway a week later.

## Workflow
1. Ask at most three questions: what one decision the meeting makes; who alone approves it; how long the meeting is.
2. Assign DACI roles by role for this decision only. One Driver runs it; exactly one Approver decides. If two Approvers are named, I stop and ask which one; a committee is not an Approver.
3. Build the agenda around the decision with time boxes: silent read of the pre-read, clarifying questions, options, the recommendation, discussion, the decision. The decision slot is never the last two minutes.
4. Name the pre-read (the memo or recommendation) and when it goes out, so Contributors arrive with questions, not first reactions.
5. Set how disagreement is recorded: "disagrees, because [reason]", by role, kept in the record rather than erased by the outcome.
6. After the meeting, draft the decision record from your notes in Claude Docs (beta): title, context, decision, status, consequences, owner and review date. Anything unclear in the notes becomes a question for you, not a guess.
7. You check the record and send it to the Contributors and Informed. I draft it; you send it.

## Output Format
```markdown
# Decision Meeting Plan and Record
Decision: [one question] · Date: [date] · Length: [minutes]
## DACI roles
| Role | Who (role) | What they do here |
|---|---|---|
| Driver | [role] | Runs the meeting, gets it decided |
| Approver | [one role] | Makes the call |
| Contributors | [roles] | [question each one answers] |
| Informed | [roles] | [how they hear the outcome] |
## Agenda
| Time box | Item | Material |
|---|---|---|
| [minutes] | Silent read | [pre-read link] |
| [minutes] | Questions, options, recommendation, decision | [link] |
## Decision record
Title: [decision] · Status: [decided / deferred to date] · Context: [why this was on the table]
Decision: [what was decided and the reasons]
Disagreement: [role] disagrees, because [reason]
Consequences: [what changes, what we accept] · Owner: [role] · Review date: [date]
## Decision
[Approver role] decides on [date]; [PM role] sends the record by [date].
```

## Done When
- Exactly one Approver is named, by role, and the decision has its own time box.
- Every disagreement is in the record with its reason.
- The record has an owner and a review date, and is drafted, not sent.

## Quality Bar
- One decision per meeting; a second decision gets its own plan.
- Positions are noted by role and reason, never as judgements of people.
- Nothing in the record that was not said or decided; gaps become questions.
- The Approver decides; you send the record.

## Next
Run pmc-morning-brief (Build the Morning Brief) to start running the week with the decision in force.

## 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 Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

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 Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

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', ...

698431 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 →