standard-4-3-layout-skill

standard-4-3-layout-skill is a skill for Claude Code, Codex from arcsin1/oh-my-ppt. It costs 68 tokens per session (1,083 once invoked), scanned A, original, Apache-2.0.

A set of rules for arranging presentation pages on a 4:3 canvas, which is closer to square than modern widescreen slides. It defines common layouts, spacing, content density, and checks for 1600-by-1200-pixel pages.

In plain words
What is it for?
Use it when creating, rearranging, or checking standard 4:3 presentation pages, including slides with charts, tables, diagrams, or two-by-two layouts.
Why use it?
It helps prevent crowded slides, weak reading order, and content being squeezed into the wrong area. It gives the agent a consistent structure before it writes or repairs a page.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating, rearranging, or checking standard 4:3 presentation pages, including slides with charts, tables, diagrams, or two-by-two layouts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arcsin1/oh-my-ppt/standard-4-3-layout-skill
About the project

Oh My PPT is a local-first desktop application that uses AI to create, edit, present, and export editable HTML-based slide presentations. It is for people making presentations, lessons, stories, reports, or pitches who want to describe their content and then adjust the resulting pages, visuals, animations, and layouts.

arcsin1/oh-my-ppt · 1,946 stars · on GitHub · ohmyppt.cc

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.

Any agent
npx skills add arcsin1/oh-my-ppt --skill standard-4-3-layout-skill
Clone the repo
git clone --depth 1 https://github.com/arcsin1/oh-my-ppt

Made for: Claude Code, Codex.

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 standard-4-3-layout-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcsin1/oh-my-ppt/standard-4-3-layout-skill/github.svg)](https://agentmods.dev/skills/arcsin1/oh-my-ppt/standard-4-3-layout-skill)
Your own site
<a href="https://agentmods.dev/skills/arcsin1/oh-my-ppt/standard-4-3-layout-skill"><img src="https://agentmods.dev/badge/skills/arcsin1/oh-my-ppt/standard-4-3-layout-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for standard-4-3-layout-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/arcsin1/oh-my-ppt/standard-4-3-layout-skill"><img src="https://agentmods.dev/badge/skills/arcsin1/oh-my-ppt/standard-4-3-layout-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00068 $0.01083
Opus 5 $0.00034 $0.00541
Sonnet 5 $0.00014 $0.00217
Haiku 4.5 $0.00007 $0.00108

Measured 6d ago against content hash 7cba68703bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

standard-4-3-layout-skill 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 6d ago.

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.

resources/skills/standard-4-3-layout-skill/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Standard 4:3 Layout Skill

This skill is the layout source of truth for standard-4-3 pages, usually 1600x1200.

A 4:3 page is a square-ish presentation canvas. It supports readable talk-track slides, balanced data + insight pairs, compact matrices, and diagrams with generous margins. Its best layouts use depth through hierarchy, not by spreading many columns across the width.

Deep details live in the references:

  • references/catalog.md - named 4:3 presentation patterns and 1600x1200 zone skeletons.
  • references/checklist.md - P0/P1/P2 structural self-check for delivery.

Preflight

Before writing HTML, decide:

  1. Message - the one sentence this slide should make the audience remember.
  2. Primary object - chart, table, matrix, diagram, hero number, conclusion block, image, or comparison.
  3. Reading path - title/claim -> primary object -> interpretation/action.
  4. Density - low for cover/quote/hero number, medium for most slides, high only for compact tables or matrices.
  5. Pattern - use a structure from references/catalog.md as a starting point when it helps the reading path; it is not a closed template menu, and a fresh composition is welcome when it serves the page thesis.
  6. Budget - estimate width and height together; 4:3 failures are often width pressure, not only height pressure.

Use the canvas dimensions from the prompt. If custom dimensions are supplied, preserve the same square-ish relationships.

Canvas Grammar

  • Favor one-column, two-zone, 2x2, or center + rail structures.
  • Two real content columns are usually enough. Three columns work only for short metric chips or labels.
  • Keep side margins and gutters generous enough for projection readability.
  • Use row-based tables and grouped insight rows when information has several dimensions.
  • Use grid/flex document flow for text-bearing modules. Independent text/content modules occupy their own cells and must not overlap or escape the canvas. Absolute positioning is only for background accents, connector lines, non-text decoration, and intentional image/video background composition; text or transparent panels may intentionally sit over media.
  • Independent content modules must retain an actual nonzero gap. Compact spacing is valid when it suits the composition.
  • Body copy, ordinary labels, and card descriptions default to at least 24px (Tailwind text-2xl or text-[24px]). Only a genuinely high-density bounded module may use 21px after restructuring; mark it data-ppt-density="high" and compensate its grid/flex footprint if it is scaled. Headings are at least 32px (text-3xl or larger) with no upper cap; auxiliary source/footer text is at least 16px. These floors preserve the same displayed 18px / 16px / 24px / 12px semantic minimums on this 1200px-high canvas.

Read the full file on GitHub · 74 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago Changed · +1 lines 7cba68703bf6
  2. 11d ago First seen · 73 lines · 68 tokens per session scan A caa30f595343

Subscribe to this mod's changes

standard-4-3-layout-skill is a skill published in the GitHub repository arcsin1/oh-my-ppt (1,946 stars, last pushed 5d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,083 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

mermaid-diagram

Use when the user asks for a flowchart, architecture diagram, sequence diagram, ER diagram, state machine, gantt chart, or any visual that fits Mermaid syntax. Hope Agent's chat renders Mermaid blocks natively, so the diagram appears inline.

shiwenwen/hope-agent · 55 tokens

visual-design

A design skill for turning content into complete, self-contained HTML pages and visual materials such as websites, banners, posters, reports, resumes, and portfolios. It follows a defined visual design system and does not use outside images or code libraries.

Pinvou/pinvou-agent · 152 tokens

impeccable

Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.

Peiiii/nextclaw · 47 tokens

ui-ux-pro-max

Use when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset and Python search runtime.

Peiiii/nextclaw · 45 tokens

nextclaw-skin-studio

A studio for browsing, applying, creating, refining, switching, inspecting, and removing custom NextClaw skins. A skin changes an app's visual appearance and can include CSS, JavaScript, images, SVG, layout changes, and motion.

Peiiii/nextclaw · 115 tokens

codex-slides

Create, research, revise, restyle, present, inspect, and export Codex Slides slide decks from Codex, including scenario workflows, project Design Files, and always-on brand design systems. Use when the user asks for a presentation, PPT/PPTX, slide deck, research brief converted into slides, an existing deck edit, a…

nexu-io/codex-slides · 101 tokens