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.
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.
npx skills add arcsin1/oh-my-ppt --skill oh-my-ppt-layoutgit clone --depth 1 https://github.com/arcsin1/oh-my-pptWrote 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.
[](https://agentmods.dev/skills/arcsin1/oh-my-ppt/oh-my-ppt-layout)<a href="https://agentmods.dev/skills/arcsin1/oh-my-ppt/oh-my-ppt-layout"><img src="https://agentmods.dev/badge/skills/arcsin1/oh-my-ppt/oh-my-ppt-layout/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.
<a href="https://agentmods.dev/skills/arcsin1/oh-my-ppt/oh-my-ppt-layout"><img src="https://agentmods.dev/badge/skills/arcsin1/oh-my-ppt/oh-my-ppt-layout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.04854 |
| Opus 5 | $0.00027 | $0.02427 |
| Sonnet 5 | $0.00011 | $0.00971 |
| Haiku 4.5 | $0.00005 | $0.00485 |
Grade A, and why
oh-my-ppt-layout 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oh My PPT Layout
This skill is the decision backbone for slide structure. Deep examples live in the references:
references/catalog.md— canonical 1600×900 zone skeletons and named layout patterns (the structure-choice layer you pick from before writing HTML).references/layout.md— collision-avoidance code comparison and height-budget walkthroughs.references/checklist.md— P0/P1/P2 structural self-check.
When to use
- Creating a new slide or rewriting a whole slide
- Choosing a slide composition or layout intent (cover, data-focus, comparison, etc.)
- Repairing overflow, collision, or content exceeding the canvas
When not to use
- Tiny text/style edits that do not affect layout (color, wording, single element)
1. The per-page decision path
Before writing HTML, answer these in order. The first three decide the role and density; the rest decide structure and budget.
- PPT message — what is the one sentence this page should make the audience remember within 3 seconds? Source material is evidence; the slide is an edited message.
- Role — what is this slide? (cover / data exhibit / comparison / timeline / concept / process / summary / quote / image-focus)
- Reading path — what does the audience see first → understand second → remember last?
- Content shape — which source facts support the message, which can be grouped, and which becomes compact secondary detail? A slide is a designed argument, not a document dump.
- If the page feels over-dense or would exceed 1600×900, pause before writing HTML and self-summarize: one message + a content-appropriate set of support groups/evidence rails. Only place that distilled structure on the slide; merge minor facts into labels, notes, annotations, or omitted speaker-context.
- Density — low (one hero or primary visual with limited support), medium (main + 1–2 support), or high (grid/table/matrix only when the content truly demands it)?
- Pattern + skeleton — use a named layout pattern from
references/catalog.mdwhen it clarifies the reading path or solves a known density risk; if the page risks becoming top-heavy, a canonical 1600×900 zone skeleton is a useful starting point. These are references, not a closed menu: create a fresh composition when the page thesis or style calls for it, while keeping the same semantic anchor and readable budget. - Height budget — calculate the height budget so the chart and modules fit within 900px while preserving actual gaps between independent modules (see §4).
- Self-check width/height: Before calling the write tool, estimate the final layout. Width must fit 1600px and height must fit 900px, including padding, title/subtitle, rows, gaps, chart frames, footnotes, and likely text wrapping. If either dimension exceeds the canvas, redesign the composition and check again.
What ships with it
4 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.
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.
- 6d ago Changed · +1 lines aaebde7ff100
- 12d ago First seen · 212 lines · 54 tokens per session scan A 35770cabebbc
oh-my-ppt-layout is a skill published in the GitHub repository arcsin1/oh-my-ppt (1,946 stars, last pushed 6d ago), licensed Apache-2.0. It adds 54 tokens to every session and 4,854 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.
Other skills, from other repositories
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.
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…
codex-slides-deck
Compatibility entry point for scenario-led creation, Design Files, brand systems, inspecting, revising, restyling, and exporting Codex Slides slide decks. Use when a user asks Codex to make a presentation, use project files, edit an existing deck, manage slide structure, apply brand or template rules, or export…
ai-image-generation-master
Expert-level guide to AI image generation across Midjourney, DALL-E, and Stable Diffusion covering prompt engineering for visual output, style control, composition techniques, upscaling workflows, and production pipelines for consistent, high-quality results. Use when the user asks about ai image generation master…
director-keyframe-review
A checklist for reviewing reference images that define a character or scene. It gives step-by-step checks, a Go/No-Go decision, and feedback wording for requesting changes.
curated-product-exploded-view
A product-advertising skill for an exploded view, where a product is shown separated into parts, along with its formula and acceptance checks.