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 huangrichao2020/pretty-skills --skill ppt-orchestrator-pptgit clone --depth 1 https://github.com/huangrichao2020/pretty-skillsWrote 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/huangrichao2020/pretty-skills/ppt-orchestrator-ppt)<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/ppt-orchestrator-ppt"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/ppt-orchestrator-ppt/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/huangrichao2020/pretty-skills/ppt-orchestrator-ppt"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/ppt-orchestrator-ppt.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 | $0.00160 | $0.17368 |
| Opus 5 | $0.00080 | $0.08684 |
| Sonnet 5 | $0.00032 | $0.03474 |
| Haiku 4.5 | $0.00016 | $0.01737 |
Grade A, and why
ppt-orchestrator 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 13d 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 — 1,088 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT Orchestrator · 统一 PPT / 长图 / 周报 调度器
本 skill 是"统一入口 + 风格字典 + 决策树"——不做具体出图。出图本身分发到下游 skill（ai-image-to-pptx / html-ppt-viewer / mckinsey-presentation-generator / huashu-design / design-master）。
何时用这个 Skill
触发场景：
- "做 PPT / 做个演示 / 演示文稿 / 幻灯片 / slides / deck / presentation"
- "打包成 HTML / HTML 阅读器 / HTML PPT"
- "真实 .pptx / PowerPoint 文件 / 可编辑的 PPT"
- "周报长图 / 月报 / 年报 / 事件复盘长图"
- "卡脖子分析长图 / 三棱镜长图"
- 任何 N 张图打包成可演示文档的需求
不触发（让其他 skill 处理）：
- 单张海报/封面/KV →
design-master/product-visual-creator - 视频 →
remotion-video - 漫画 →
comic-generator - 小红书单张图 →
xiaohongshu-image-creator
一句话定位
做 PPT 真正难的，不是 prompt、不是模型、也不是工具，是这条闭环
→ 吃透内容 → 章节清单 → 60 行 prompt → 渲染核对 → 接受 AI 调整 → 沉淀 case
↓
6 种风格字典选一种 + 输出形式决策树选一种 + 下游 skill 执行
Step 0 · 风格 + 颜色主题讨论（用户硬规则 · 2026-07-04 沉淀）
优先级最高：做「生图 PPT」或「HTML PPT」前，必须先和用户讨论清楚风格 + 颜色主题，才能开始ppt 出图法 V2 7 步。 来源：用户 2026-07-04 15:44：「以后你做生图ppt时或者做html ppt时 务必选和我讨论清楚选哪种风格 哪种颜色主题」
触发词：「做 PPT」「打包成网页」「生图 PPT」「HTML PPT」「真实 .pptx」「演示文稿」「幻灯片」「slides」「deck」「presentation」等
必须问的 2 个问题（用 ask_user 或文字列候选均可）：
-
风格（ppt 出图法 V2 5 大类）：
- 商务科技风 🏢（B 端/产品/方法论/培训/金融）
- 博物图鉴风 📖（年度报告/系列科普/知识矩阵）
- 手绘科教风 ✏️（小红书/视频号/教学课件/C 端学习者）
- 真实生活感 📝（情感金句/朋友圈/日签）
- 城市插画风 🗺️（旅行/城市/文创）
- 反套路金句型 🎯（情感/人性/哲学/反鸡汤）
-
颜色主题（以商务科技风为例，6 个色版本——其他风格各有不同色版）：
- 蓝白灰经典版（科技/SaaS/发布会）
- 橙色主题版（课程/方法论/培训）★ 本月最常用
- 绿色主题版（金融/ESG/碳中和）
- 红色主题版（快讯/警示/紧急议题）
- 紫/蓝紫主题版（AI/前沿/神秘感）
- 黑金主题版（高端/奢侈/黑科技）
- 完整速查：
knowhub/domains/visual-creation/cases/2026-07-04-business-tech-style-variants.md
执行流程：
用户触发「做 PPT」
↓
Step 0 · 必问风格 + 颜色主题（用户硬规则） ← 优先级最高
↓ 选 1 种风格 + 1 个色版
ppt 出图法 V2 7 步（准备阶段 + 出图 + 核对）
↓
Step 7 · 沉淀 case（包含风格+颜色选择记录）
例外（用户已明确指定风格+颜色，直接干）：
- 「做手绘马卡龙的 PPT」→ 直接走手绘科教风 + 马卡龙配色
- 「橙色商务科技风的演示」→ 直接走商务科技风 + 橙色版
- 「博物图鉴风」→ 直接走博物图鉴风
反模式（绝对不要做）：
- ❌ 直接默认「手绘科教 + 马卡龙」开干（2026-07-03 xhs-sponsorship-ppt 就是这样，但用户已经接受）
- ❌ 跳过 Step 0 直接ppt 出图法 V2 7 步
- ❌ ppt 出图法 V2 出 P1 hook 之前没有确认风格（造成返工）
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.
- 13d ago First seen · 1,088 lines · 160 tokens per session scan A ca2e6590ab5a
ppt-orchestrator is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed yesterday), licensed MIT. It adds 160 tokens to every session and 17,368 once invoked, about $0.0008 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
story-cover
An image-generation workflow for creating novel covers with the book title and author name included. It determines a likely genre and style from the book information, then uses GPT-Image-2 to create the cover.
archi-ui-wireframe
Generate UI concept designs as screens/ reference artifacts. Protocol-invoked only; do not auto-trigger.
archi-design-patterns
Inline helper for structured technical design patterns. Protocol-invoked only; may run in current context.
design-agent
You are the Design agent for this project. You own React components, page routes, design tokens, and visual layout.
svg-creator
Produce SVGs that are spec-correct (W3C SVG 2), CSS-independent, accessible when meaningful, safe to render in untrusted contexts, optimized in size, and readable enough to edit.
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.