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 Restyle

ASecurity

Restyles a plain Claude Slides draft into one claim per slide and returns a Restyle Log with dense slides split, topic titles rewritten as sentences, bullets replaced by evidence, AI tells removed, and a before and after list per slide. Use for "run deck-restyle", "this deck reads as AI", "make the slides less generic", "fix the plain draft", "too many bullets", "split the dense slides", "one claim per slide", part of the Claude Slides for Product Managers Pack by Polar Bear.

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-restyle --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deck Restyle?

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

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

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-restyle
description: Restyles a plain Claude Slides draft into one claim per slide and returns a Restyle Log with dense slides split, topic titles rewritten as sentences, bullets replaced by evidence, AI tells removed, and a before and after list per slide. Use for "run deck-restyle", "this deck reads as AI", "make the slides less generic", "fix the plain draft", "too many bullets", "split the dense slides", "one claim per slide", part of the Claude Slides for Product Managers Pack by Polar Bear.
---

# One Claim per Slide Restyle

## When To Use
The Claude Slides draft is competent but plain and reads as AI: topic titles, five bullets a slide, three equal boxes with an icon each, an accent bar on every page. The argument is there; the slides hide it. This answers: what does each slide claim, and what evidence on the slide proves it?

## When Not To Use
If the argument itself is missing, restyling polishes nothing; go back to Ghost Deck Storyline. For a new storyline that has no slides yet, run Build in Your Design System; for figures that may be wrong, run Numbers Check first, because this skill never touches a number.

## Inputs
- The drafted deck in this conversation, or its PDF export.
- The Slide Design System, if you have one.
- Any visual evidence you own: screenshots, tables, diagrams, approved images.
If you have none of this, I start from the slide titles you paste and mark the log as a first draft.

## Approach
Assertion-evidence slides, from Michael Alley at Penn State (assertion-evidence.com): a headline written as a sentence that states the takeaway, supported by visual evidence instead of a bullet list. The judgment is in the split: a slide with two claims becomes two slides, and a slide with no claim is cut or becomes a section break. The method was built for technical talks, so agenda, title and process slides keep their plain titles. The failure it prevents: a room that reads "Customer feedback" and five bullets, and leaves without knowing what the feedback says.

## Workflow
1. Ask three questions at most: who reads or hears the deck, the slide budget, and which slides are already approved and must not move.
2. Per slide, write the one claim it makes as a sentence. Two claims means split; no claim means cut, merge or turn into a section slide. Keep the slide budget: a split pays for itself by a cut elsewhere.
3. Turn topic titles into sentence assertions of at most two lines, using only claims the draft or its sources already make.
4. Replace each bullet list with the evidence that proves the title: a chart, a table, a diagram, a screenshot or an image you supply. If no evidence exists, keep the text, mark "[evidence missing]" and say so in the log.
5. Remove the AI tells: generic icons, three equal boxes for unequal ideas, decorative accent bars, filler words ("leading", "key", "various"), vague headings, and symmetry that has no meaning.
6. Apply the design system's layouts, colour roles and source line. Fix slides one at a time in Claude Slides (beta) with direct edits or a comment on the slide, never a full regeneration, which loses approved slides and costs usage.
7. Log before and after for every slide changed, and re-read the titles alone in order: they should now tell the story.

## Output Format
```markdown
# Restyle Log
Deck: [deck name] | Slides before: [n] | Slides after: [n] | Date: [date]
## Slide by slide
| Slide | Before (title and form) | Claim | After (title and evidence) | Change |
|---|---|---|---|---|
| [n] | [topic title, bullets] | [one sentence] | [assertion title, chart of what] | [split / retitled / cut / evidence swapped] |
## AI tells removed
| Slide | Tell | What replaced it |
|---|---|---|
| [n] | [three equal boxes] | [comparison table] |
## Evidence missing
| Slide | Claim | Evidence needed | Who can supply it |
|---|---|---|---|
| [n] | [claim] | [data, screenshot] | [role] |
## Titles-only read
1. [title]
## Decision
[Deck owner] approves the restyled slides and decides on each "[evidence missing]" slide by [date].
```

## Done When
- Every content slide has one claim, written as a sentence title.
- No bullet list remains where evidence exists.
- Every split, cut and retitle appears in the log with its before.
- The titles-only read tells the story without the bodies.

## Quality Bar
- A new title states only what the draft or its sources already say.
- Evidence is real: no invented chart data, no stock picture standing in for proof.
- Slide count stays within the budget the user set.
- Changes are made slide by slide; nothing approved is regenerated.
- Restyling changes form, never a claim or a number.

## Next
Run deck-pre-read (Pre-Read Slidedoc) when the deck will be read without you in the room.

## 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 →