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 agentmods add skills/nhype/presentation-generation-skill/generate-presentationnpx skills add nhype/presentation-generation-skill --skill generate-presentationgit clone --depth 1 https://github.com/nhype/presentation-generation-skillWrote 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/nhype/presentation-generation-skill/generate-presentation)<a href="https://agentmods.dev/skills/nhype/presentation-generation-skill/generate-presentation"><img src="https://agentmods.dev/badge/skills/nhype/presentation-generation-skill/generate-presentation.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00036 | $0.02715 |
| Opus 5 | $0.00018 | $0.01358 |
| Sonnet 5 | $0.00007 | $0.00543 |
| Haiku 4.5 | $0.00004 | $0.00271 |
Grade A, and why
generate-presentation 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 3d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Presentation
You are a presentation designer. Your job is to create beautiful, professional presentation slides that match the visual style found in the references/ folder.
Workflow
Follow these steps exactly in order:
Step 1: Gather Content
Ask the user what the presentation should contain. The user may:
- Provide a topic and let you generate the content
- Provide a URL — fetch it with the WebFetch tool and extract the key content
- Provide a markdown file path — read it with the Read tool and use its structure as slide content
- Provide the content directly as text
- Provide a combination of the above
If $ARGUMENTS is provided, use it as the starting point. Detect the input type:
- If it ends in
.mdor.markdown— treat it as a markdown file path. Read the file with the Read tool and use its content to generate slides. Use headings (#,##) as slide titles/breaks, and body text as slide content. - If it starts with
http://orhttps://— treat it as a URL. Fetch it with WebFetch and extract key content. - Otherwise — treat it as a topic description and generate content from it.
Markdown file conventions: When the source is a markdown file, interpret its structure as follows:
# Top-level heading→ Presentation title (first slide)## Second-level heading→ New slide title (each##starts a new slide)### Third-level heading→ Section heading within a slide- Bullet lists (
-or*) → Slide bullet points - Numbered lists (
1.,2.) → Ordered content on a slide - Bold text (
**text**) → Emphasized/highlighted text on slides - Regular paragraphs → Slide body text (keep concise, split long paragraphs)
---(horizontal rule) → Explicit slide break (alternative to using##)- Images (
) → Include the referenced image on the slide if the file exists
If the markdown has no ## headings, split content into logical slides automatically (aim for one key idea per slide).
Ask clarifying questions if needed:
- How many slides? (if not obvious from the markdown structure)
- What is the target audience?
- Any specific points to emphasize?
What ships with it
2 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.
- 3d ago First seen · 263 lines · 36 tokens per session scan A 0a3f1598b68f
generate-presentation is a skill published in the GitHub repository nhype/presentation-generation-skill (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,715 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
graphic-ebook
Creates professionally designed B2B SaaS e-books in HTML + CSS, exported as print-ready PDF. 3–10 pages, 9 style presets, 11 page layout types. Trigger when user says "create an ebook", "design a lead magnet", "make a PDF guide", "build a gated content piece", "write a B2B ebook", "design a white paper", "create a…
slides-grab-export
Stage 3 conversion skill usable in Codex and Claude Code. Convert approved HTML slides to PDF or per-slide PNG reliably, and to experimental / unstable PPTX/Figma outputs on a best-effort basis.
marp-slides
Author MARP markdown slide decks exportable to PDF, PPTX, and HTML via marp-cli. Covers Marpit directives, custom CSS themes, SVG chart recipes, and dashboard components. Triggers on: "marp", "marp deck", "markdown slides", "slides from markdown", "marp-cli", "pdf from markdown", "pptx from markdown".
image-vision
Inspect attached or local images and visually analyze PDFs with vision. Use for photos, screenshots, scans, charts, diagrams, OCR, handwriting, UI inspection, or any task that depends on pixels, layout, or other non-structural page content.
paper2xhs
把学术论文 PDF 转成小红书多图帖(标题 + 正文 + 标签 + 封面 + 论文主图/主实验结果配图)。你主导设计的协调式:机械活(MinerU 解析 PDF、生成封面与配图、半自动发布)交给 scripts/ 下的小工具,论文理解、选题角度、文案撰写由你亲自完成并在关键点与用户确认。当用户说“论文转小红书”、“paper2xhs”、“把这篇论文发小红书”、“论文转社交媒体”、“PDF 转小红书帖子”时触发。.
arcdeck-skill
Convert academic PDF papers into polished, narrative-driven PowerPoint presentations using 13 specialized AI agents orchestrated by Claude Code. Based on Rhetorical Structure Theory (RST) discourse parsing with a multi-agent critique-revise-judge refinement loop. Every slide is visually rich -- text-only slides get…