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 ontology-of-everything/SemanticSkills --skill html-slidesgit clone --depth 1 https://github.com/ontology-of-everything/SemanticSkillsWrote 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/ontology-of-everything/semanticskills/html-slides)<a href="https://agentmods.dev/skills/ontology-of-everything/semanticskills/html-slides"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/html-slides/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/ontology-of-everything/semanticskills/html-slides"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/html-slides.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00082 | $0.02198 |
| Opus 5 | $0.00041 | $0.01099 |
| Sonnet 5 | $0.00016 | $0.00440 |
| Haiku 4.5 | $0.00008 | $0.00220 |
Grade A, and why
html-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.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
演示文稿生成（多风格）
概论
把一句话需求做成一份明文单文件 HTML 演示（1920×1080，内联 CSS，≤120 行运行时 JS）。
代码与文档分离：assets/core/ 放基础 CSS、运行时 JS 与页型骨架画廊，assets/<style>/ 放风格变量与专属组件，references/ 下的 md 只讲规则并指向这些文件。
视觉由风格插拔：核心只用 CSS 变量名，风格给取值、字体、专属页型与素材。首版收录 generic（默认兜底）、huawei（官方胶片分析）、apple（经验版）；新增风格按 references/styles/_template.md 建一份 md + 一个 assets/<style>/ 目录即可。
仅显式调用：用户写 $html-slides（或同名斜杠命令）或点名本技能时启用；泛泛聊 PPT 不触发。不做的事：不代用户编造数据与引文；不安装依赖；PPTX 只在用户要求时导出并明说是哪一档（见输出格式）。
原则
每条只在指向的文件里定义细则，本节不重述。
- 先对齐再动手：主题与大纲未经用户确认不写页面 →
process.md§1–2 - 标题即观点且点名技术：内容页标题是有判断的句子并含关键技术 / 方法名；全部标题连读 = 论证链 →
style-guide.md§4 - 固定三页：第 1 页封面、第 2 页目录、末页致谢，目录随当前大纲重建 →
page-patterns.md§1 - 每页塞进 1080：
section固定尺寸 +overflow:hidden，超出被无声裁切；交付前?debug零红框 →deck-format.md§5 - 字号按场景分档：授课散文 ≥21px；汇报 / 自读短语卡 ≥18px；表格、轴标签、图内文字 15px 图元豁免 →
style-guide.md§3 - 连续 3 页换视觉家族，密页后接轻页；两个以上耦合维度用复合页型不拆薄 →
page-patterns.md§2 - 同级卡片同构：同组同角色卡片的底 / 边 / 圆角 / 字体层级完全一致，只有文案说明了差异才允许单卡高亮 →
style-guide.md§5 - 语言朴实可核验：不写套话、广告词、自造比喻，页面上不写「点击查看」类操作提示 →
style-guide.md§4 - 字不如表，表不如图：机制 / 流程 / 架构页以图表为主表达；初版放类型化占位，终版落地并清零
data-todo→visuals.md - 动画只手动推进，汇报与自读默认静态 →
motion.md - 风格只改变量与专属组件：
assets/core/与骨架不出现具体色值；取值一律来自assets/<style>/vars-*.css→deck-format.md§3 - 图片经 data URI 内联，deck 拷走即用；素材来自
assets/<style>/或用户提供 →deck-format.md§4
流程
七阶段，三个「讨论」是硬闸门；细则与场景适配表见 process.md。
| # | 阶段 | 产出 | 闸门 |
|---|---|---|---|
| 1 | 主题讨论 | 五问一次问完（听众 / 场合时长 / 目标 / 素材 / 风格与交付）→ 需求共识一段 | 用户确认 |
| 2 | 大纲规划 | 章 / 问题 / 分钟 / 页数表；确认后落盘 <deck>.plan.md |
用户确认 |
| 3 | 选择页型 | 大纲条目 → 页型 → 视觉家族 / 密度 映射表 | 随 4 给出 |
| 4 | 初版 | 逐页规划表 + <deck>.html（配图为占位块） |
— |
| 5 | 讨论修改 | 逐章引导反馈，按页记录修改清单 | 用户点头「结构定了」 |
| 6 | 终版 | 配图落地、动画节拍（仅授课）、?debug 零溢出、按需 PPTX |
— |
| 7 | 交付确认 | 微调、数字核对、交付话术 | 用户验收 |
用户催「直接做」：五问改为带默认值的一轮快答，用户只需纠偏；闸门不豁免。未指明风格 → generic，并在需求共识里写明「当前风格：通用商务，可改」。
输出格式
<deck>.plan.md（阶段 2 建、随改随更）：
# <标题> · 页面规划
风格：huawei-light · 场景：汇报 · 时长：10 min · 交付：HTML(+PPTX)
## 大纲
- 01 章名 — 本章要回答的问题（N 页）
## 逐页
| # | label | 核心观点（一句话） | 页型 | 视觉家族/密度 | 配图（类型+规格） | 拍数 |
What ships with it
30 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.
- agents/openai.yaml 284 B
- assets/apple/style.css 1.2 KB
- assets/apple/vars-dark.css 619 B
- assets/apple/vars-light.css 606 B
- assets/core/base.css 3.6 KB
- assets/core/runtime.js 6.0 KB runs code
- assets/core/skeletons.html 13 KB
- assets/generic/vars-dark.css 569 B
- assets/generic/vars-light.css 578 B
- assets/huawei/kv-dark-lightpath.jpeg 610 KB
- assets/huawei/kv-light-planet.jpeg 157 KB
- assets/huawei/logo-horizontal.png 22 KB
- assets/huawei/logo-huaweicloud.png 9.1 KB
- assets/huawei/patterns.html 6.9 KB
- assets/huawei/petal-red.png 160 KB
- assets/huawei/style.css 1.8 KB
- assets/huawei/vars-dark.css 657 B
- assets/huawei/vars-light.css 604 B
- references/.gitkeep 0 B
- references/deck-format.md 5.8 KB
- references/motion.md 3.8 KB
- references/page-patterns.md 6.3 KB
- references/process.md 8.1 KB
- references/style-guide.md 7.0 KB
- references/styles/_template.md 2.1 KB
- references/styles/apple.md 3.0 KB
- references/styles/generic.md 1.8 KB
- references/styles/huawei.md 6.5 KB
- references/visuals.md 5.1 KB
- tools/export_pptx.py 4.2 KB runs code
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.
- yesterday First seen · 95 lines · 82 tokens per session scan A 6fae3016f31c
html-slides is a skill published in the GitHub repository ontology-of-everything/SemanticSkills (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 2,198 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 2026-09-10.
Other skills, from other repositories
photographic-icon-set-generator
Generates consistent, locked-style sets of photographic, textured, or 3D-material-rendered icons via Ideogram — 3D-rendered, claymation, hand-painted, or isometric-with-material-texture icon packs that hold a shared style recipe across every icon in the batch. Use when the user asks for "3D icon set," "claymation…
brand-identity-sheet
Generates a single polished "brand identity sheet" image — a Dribbble-style board showing a UI card with the wordmark, a grid of textured app icons, pill-shaped buttons, a giant central wordmark treatment, and a secondary lockup with a brand glyph — and actually renders it via the ideogram MCP tools, not just drafts a…
character-model-sheet
Generates a single polished "character model sheet" image — a multi-panel character design board showing a full-body turnaround (front / 3-4 / side / back), a head & detail close-up sheet (face, hair/headwear, hands/props), a color palette, an overview text block (name, role, personality, wardrobe), and an optional…
moodboard-generator
Generates a single polished "moodboard" image — a 3×3 grid brand-exploration board (Color Palette, Typography, Logo Exploration, Iconography Style, Photography & Graphics, Material Samples, Abstract Patterns, Mood Imagery, Application Mockup) — and actually renders it via the ideogram MCP tools, not just drafts a…
concept-grid-generator
Generates a single "concept grid" image — a labeled comparison sheet showing several DISTINCT motif/icon concepts as tiles side by side, one locked palette and one locked rendering technique held constant across every tile — and actually renders it via the ideogram MCP tools, not just drafts a prompt. Use whenever the…
logo-prompting
Living reference for writing logo and brand-mark image-generation prompts (Ideogram-first, via ideogram-pack:ideogram-core-workflow-a). Use whenever the user asks for a logo prompt, a wordmark/icon direction, or wants feedback on a logo image-gen prompt they've drafted — even if they just paste a prompt and say "is…