Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Ghost Deck Skeleton

ASecurity

Produces a ghost deck (skeleton) of empty slides with action titles and exhibit placeholders, so the storyline is agreed before any time is spent on design.

6 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agents

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-powerpoint-skills --skill ghost-deck-skeleton --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ghost Deck Skeleton?

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

Security grade badge for Ghost Deck Skeleton
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-ghost-deck-skeleton/badge)](https://www.skillsdirectory.com/skills/andreworia-ghost-deck-skeleton)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: ghost-deck-skeleton
description: Produces a ghost deck (skeleton) of empty slides with action titles and exhibit placeholders, so the storyline is agreed before any time is spent on design.
---

# Ghost Deck Skeleton

## When to use
Use this at the start of building, after the storyline is set but before any real slide is designed. Use it to align a team or a partner on the argument cheaply, before anyone spends hours formatting. Use it when scope is unclear and you want to lock the page count and the flow first.

## What it does
It produces a ghost deck, also called a skeleton deck or dummy deck: every slide present, each with its action title written and a sketch of the intended exhibit, but no real design or final data. It makes the storyline visible and editable before expensive work begins.

## Method
A ghost deck is the standard top-tier-consulting way to de-risk a deck. Build it slide by slide from the storyline.

1. One slide per leaf. Take the storyline tree and create one ghost slide for each evidence leaf, plus section dividers and the executive summary. Keep them in presentation order.

2. Write the action title now. Each ghost slide gets its final action title up front. The title chain is the deliverable being reviewed. If the titles do not argue the case, fix the storyline, not the slides.

3. Sketch the exhibit, do not build it. For each slide, write a one-line description of the intended visual: "waterfall from current to target margin", "2x2 of segments by growth and profit", "three-column comparison of options". Note the rough layout, not the styling.

4. Note the data needed. State what data each slide requires and whether you have it. This surfaces analysis gaps while they are cheap to fix.

5. Mark confidence. Tag each slide as solid, likely, or speculative. Speculative slides are candidates to cut or to flag for the partner.

6. Keep it ugly on purpose. No colors, no icons, no alignment work. The ghost deck must look unfinished so reviewers critique the logic, not the polish.

7. Review the flow as titles only. Present the title chain first. Get agreement on the argument and the page count before building anything real.

8. Convert to a build plan. Once approved, each ghost slide becomes a build ticket: title fixed, exhibit chosen, data identified.

## Inputs
- The storyline tree or pyramid.
- The decision and audience.
- Known data availability and gaps.

## Output format
Return a numbered slide list. For each slide: the action title, a one-line exhibit sketch, the data required, and a confidence tag. End with the total page count and a list of slides flagged as data-gapped or speculative.

## Example
Slide 4 of a ghost deck.
Title: "Two of five plants drive 70 percent of the quality defects."
Exhibit sketch: horizontal bar chart, defects by plant, top two highlighted.
Data needed: defect counts by plant, last 12 months. Status: have it.
Confidence: solid.

Attribution

andreworiaandreworia
View sourceMore from andreworia →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

693621 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →