slides

slides is a skill for Claude Code, Codex from fcakyon/claude-codex-settings. It costs 83 tokens per session (1,023 once invoked), scanned A, original, Apache-2.0.

Instructions for creating and editing PowerPoint presentation files while keeping the content editable and checking the rendered slide layout.

In plain words
What is it for?
It is for building slide decks, recreating slides from screenshots or PDFs, and modifying existing presentations.
Why use it?
It helps catch text overflow, missing fonts, and layout problems before a presentation is delivered.

Skill for Claude CodeCodex

Part of the openai-office-skills plugin — 3 skills shipped together

About the project

claude-codex-settings is a collection of configurations and reusable extensions for Claude Code, OpenAI Codex, Cursor, and related coding tools. Developers use its skills, commands, hooks, agents, plugins, and MCP servers to shape coding-agent workflows and connect alternative model APIs. The catalogue entries are components of this collection that can be installed into supported coding tools.

fcakyon/claude-codex-settings · 1,127 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/fcakyon/claude-codex-settings/slides
Any agent
npx skills add fcakyon/claude-codex-settings --skill slides
Clone the repo
git clone --depth 1 https://github.com/fcakyon/claude-codex-settings

Made for: Claude Code, Codex.

Or install openai-office-skills, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for slides

README.md
[![agentmods](https://agentmods.dev/badge/skills/fcakyon/claude-codex-settings/slides.svg)](https://agentmods.dev/skills/fcakyon/claude-codex-settings/slides)
Your own site
<a href="https://agentmods.dev/skills/fcakyon/claude-codex-settings/slides"><img src="https://agentmods.dev/badge/skills/fcakyon/claude-codex-settings/slides.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00083 $0.01023
Opus 5 $0.00042 $0.00511
Sonnet 5 $0.00017 $0.00205
Haiku 4.5 $0.00008 $0.00102

Measured yesterday against content hash cabd976aceea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slides scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 14 executable files (assets/pptxgenjs_helpers/code.js, assets/pptxgenjs_helpers/image.js, assets/pptxgenjs_helpers/index.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • slides — 97% identical, 1 lines differ
plugins/openai-office-skills/skills/slides/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slides

Overview

Use PptxGenJS for slide authoring. Do not use python-pptx for deck generation unless the task is inspection-only; keep editable output in JavaScript and deliver both the .pptx and the source .js.

Keep work in a task-local directory. Only copy final artifacts to the requested destination after rendering and validation pass.

Bundled Resources

  • assets/pptxgenjs_helpers/: Copy this folder into the deck workspace and import it locally instead of reimplementing helper logic.
  • scripts/render_slides.py: Rasterize a .pptx or .pdf to per-slide PNGs.
  • scripts/slides_test.py: Detect content that overflows the slide canvas.
  • scripts/create_montage.py: Build a contact-sheet style montage of rendered slides.
  • scripts/detect_font.py: Report missing or substituted fonts as LibreOffice resolves them.
  • scripts/ensure_raster_image.py: Convert SVG/EMF/HEIC/PDF-like assets into PNGs for quick inspection.
  • references/pptxgenjs-helpers.md: Load only when you need API details or dependency notes.

Workflow

  1. Inspect the request and determine whether you are creating a new deck, recreating an existing deck, or editing one.
  2. Set the slide size up front. Default to 16:9 (LAYOUT_WIDE) unless the source material clearly uses another aspect ratio.
  3. Copy assets/pptxgenjs_helpers/ into the working directory and import the helpers from there.
  4. Build the deck in JavaScript with an explicit theme font, stable spacing, and editable PowerPoint-native elements when practical.
  5. Run the bundled scripts from this skill directory or copy the needed ones into the task workspace. Render the result with render_slides.py, review the PNGs, and fix layout issues before delivery.
  6. Run slides_test.py for overflow checks when slide edges are tight or the deck is dense.
  7. Deliver the .pptx, the authoring .js, and any generated assets that are required to rebuild the deck.

Authoring Rules

  • Set theme fonts explicitly. Do not rely on PowerPoint defaults if typography matters.
  • Use autoFontSize, calcTextBox, and related helpers to size text boxes; do not use PptxGenJS fit or autoFit.
  • Use bullet options, not literal characters.
  • Use imageSizingCrop or imageSizingContain instead of PptxGenJS built-in image sizing.
  • Use latexToSvgDataUri() for equations and codeToRuns() for syntax-highlighted code blocks.
  • Prefer native PowerPoint charts for simple bar/line/pie/histogram style visuals so reviewers can edit them later.
  • For charts or diagrams that PptxGenJS cannot express well, render SVG externally and place the SVG in the slide.
  • Include both warnIfSlideHasOverlaps(slide, pptx) and warnIfSlideElementsOutOfBounds(slide, pptx) in the submitted JavaScript whenever you generate or substantially edit slides.
  • Fix all unintentional overlap and out-of-bounds warnings before delivering. If an overlap is intentional, leave a short code comment near the relevant element.

Read the full file on GitHub · 73 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 73 lines · 83 tokens per session scan A cabd976aceea

Subscribe to this mod's changes

slides is a skill published in the GitHub repository fcakyon/claude-codex-settings (1,127 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 1,023 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

lov-any2deck

Generate professional slide deck images from content (Markdown, text, URLs). Creates outlines with style instructions, then generates individual slide images. Supports 16 visual styles, CJK/Latin mixed text, branding overlays, and PPTX/PDF export. Use when the user asks to "create slides", "make a presentation"…

lovstudio/skills · 110 tokens

lov-any2docx

Convert Markdown documents to professionally styled DOCX (Word) files with python-docx. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, cover pages, TOC field, watermarks, and page numbers. Supports multiple color themes matching any2pdf (Configurable Academic, Nord, GitHub Light, etc.) and is…

lovstudio/skills · 184 tokens

lov-rich-export

将一份面向用户的内容稳定导出为单文件 HTML、带 assets 的 HTML 文件夹、Markdown、DOCX 与 PDF,并按格式正确处理图片、音频、视频和嵌入式交互内容。用于“富媒体导出”“一键导出”“导出 html/pdf/docx/md”“离线网页”“交付包”“给产品接导出能力”等需求,以及需要为产品建立可复用内容导出管线时。.

lovstudio/skills · 105 tokens

lov-pdf2png

Convert PDF files to a single vertically concatenated PNG image using macOS native CoreGraphics. Each page is rendered at 2x scale and stitched top-to-bottom. 20x faster than pdftoppm+ImageMagick, zero external dependencies on macOS. Trigger when the user mentions "pdf to png", "pdf转png", "PDF转图片", "pdf拼接", "pdf截图"…

lovstudio/skills · 108 tokens

lov-academic-translator

将英文论文、arXiv、期刊/会议文章及技术 PDF 翻译为中文 PDF 或可发布的中文 Markdown。用户提出“翻译英文 PDF”“翻译论文”“论文超级翻译官”“保留图片、公式和原版式”“原文译文对照”“页数对应”或“PDF 图文排版不要乱”时使用。.

lovstudio/skills · 87 tokens

lov-any2pdf

Convert Markdown to polished PDF with CJK typography, code, tables, images, covers, TOC, bookmarks, and reading themes. Trigger on md2pdf, Chinese report typesetting, or print-ready PDF requests.

lovstudio/skills · 49 tokens