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

Deck Kickoff

ASecurity

Drafts a kickoff deck in Claude Slides for a project, product or quarter, with why now, the goal and its success measure, scope in and out, roles and decision rights, risks with owners and the first milestones, built as a frame for a working session. Use for "run deck-kickoff", "kickoff deck", "project kickoff slides", "quarter kickoff deck", "product kickoff presentation", "nobody knows who decides", "kickoff that is not a script", part of the Claude Slides for Product Managers Pack by Polar...

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

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill deck-kickoff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deck Kickoff?

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

Security grade badge for Deck Kickoff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-deck-kickoff/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-deck-kickoff)

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: deck-kickoff
description: Drafts a kickoff deck in Claude Slides for a project, product or quarter, with why now, the goal and its success measure, scope in and out, roles and decision rights, risks with owners and the first milestones, built as a frame for a working session. Use for "run deck-kickoff", "kickoff deck", "project kickoff slides", "quarter kickoff deck", "product kickoff presentation", "nobody knows who decides", "kickoff that is not a script", part of the Claude Slides for Product Managers Pack by Polar Bear.
---

# Kickoff Deck

## When To Use
Kickoffs are read aloud as scripts and the team leaves without knowing who decides. Use this when a project, a product or a quarter starts and you want one session that settles the goal, the scope and the decision rights. It answers: why this, why now, what is in and out, and who decides what?

## When Not To Use
If the event is a day or two with several sessions, announcements and time for the team itself, run the Team Offsite Deck. If the work has no sponsor or no agreed goal yet, the kickoff will turn into a debate about why it exists: write the Deck Brief with the sponsor first.

## Inputs
- The sponsor's why now and the goal, from a charter, a brief, a strategy or the sponsor's notes
- Known scope, constraints, risks and any target dates
- Who attends, by role, and the session length
If you have none of this, I start from the name of the work and the sponsor's role, mark open items [open], and mark the output as a first draft.

## Approach
The project kickoff play in the Atlassian Team Playbook (atlassian.com/team-playbook/plays/project-kickoff): agree the destination with the sponsor before the meeting, open with the sponsor's remarks, then the team refines the vision (the why), the mission (the what and how) and the success tests (how we know it is done) in the room. The deck is a frame with space to work, not a script. The failure it prevents: a polished kickoff where "what is out" and "who signs off" were never said aloud, so every later request arrives as if it had always been in.

## Workflow
1. Ask at most three questions: is this a project, product or quarter kickoff; which of goal, scope and decision rights the sponsor has already settled; how long the session is.
2. Before the session: agree the destination with the sponsor in a short call, and send the draft frame by share link so the room edits rather than listens.
3. Why now and the goal: the sponsor's reason in one sentence, the goal with one success measure (metric, baseline, target, source from the Deck Context File, or [no source yet]). Leave a blank row for the team's refinements.
4. Scope as two lists: in, and out. Out is written explicitly; anything unsettled is [open] with an owner and a date.
5. Decision rights: for each key decision type (scope change, release go or no go, budget, design calls), who decides and who is consulted. Roles by responsibility, never by judgment of capability.
6. Risks with an owner each, and the first milestones with dates as confidence ranges, labelled targets until the team has estimated.
7. Hand the slide outline to Claude Slides (beta) in this conversation with the Slide Design System rules, then fix slides one at a time with direct edits or a comment on the slide rather than regenerating the deck. Edit live in the session, then share the final link.

## Output Format
```markdown
# Kickoff Deck
[Project / product / quarter]: [name] | [date] | Sponsor: [role] | Session: [length]
## Slide 1 · We are starting [name] now because [reason in one line]
## Slide 2 · Success means [measure] moves from [baseline] to [target] by [date]
- Vision (why): [line] | Mission (what and how): [line] | Team's edits: [blank]
## Slide 3 · [Number] things are in scope and [number] are explicitly out
| In | Out | Open (owner, date) |
|---|---|---|
## Slide 4 · [Role] decides scope changes; here is who decides the rest
| Decision type | Decides | Consulted |
|---|---|---|
## Slide 5 · [Number] risks could move the first milestone
| Risk | Owner | What we do about it |
|---|---|---|
## Slide 6 · The first milestone lands between [date] and [date]
| Milestone | Target range | Confidence | Depends on |
|---|---|---|---|
## Decision
[Sponsor] confirms scope and decision rights before the session closes; [lead role] circulates the edited deck and closes every [open] item by [date].
```

## Done When
- Out of scope is written down, not implied
- Every key decision type has one role that decides
- Each risk has an owner; every milestone is a range labelled a target
- Space is left on the goal and scope slides for the team's edits

## Quality Bar
- One sentence per slide title, written as a claim the room can challenge.
- No slide reads as a script; anything longer than the frame goes to a pre-read.
- Roles show responsibility, never an assessment of a person.
- Dates said in the room are targets until the team estimates.
- Claude drafts the frame; the sponsor and team decide scope and who decides.

## Next
Run deck-offsite (Team Offsite Deck) when the team needs a longer session with outcomes, decisions and time together.

## 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', ...

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 →