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 yunshu0909/yunshu_skillshub --skill scene-pptgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/scene-ppt)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/scene-ppt"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/scene-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/yunshu0909/yunshu_skillshub/scene-ppt"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/scene-ppt.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 | $0.00133 | $0.03410 |
| Opus 5.5 | $0.00053 | $0.01364 |
| Sonnet 5.5 | $0.00027 | $0.00682 |
| Haiku 4.5 | $0.00013 | $0.00341 |
Grade A, and why
scene-ppt 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
场景讲解 PPT（scene-ppt）
「做成 PPT」= 一页一张 16:9 图，不是 .pptx 文件。 图上的字不能再编辑。
本 skill 自带出图脚本和用得到的风格卡，不需要另装别的 skill。下文 S 指本 skill 的脚本目录：
S=<本 SKILL.md 所在目录>/scripts
核心：换世界，不是换皮
整套 PPT 只用一个世界讲完：世界里的角色 = 要讲的对象，世界里的器物 = 概念。比如讲 Skill：
| 世界 | AI 是谁 | Prompt 是什么 | Skill 是什么 |
|---|---|---|---|
| 后厨 | 新来的学徒 | 主厨一口气的口头交代 | 一本菜谱 + 分格备料架 |
| 中药铺 | 新来的小伙计 | 把药材一股脑倒进一锅 | 一张方子 + 百子柜 |
世界定了，每页的场景从这个世界里自然长出来（前台、后厨、备料间、试菜…），页与页自然不同。实测证据见 reference/lessons.md。
默认世界（每次开工先看）
python3 $S/settings.py get world（打印出世界 ID = 有默认；打印空行 = 还没设）。
世界 ID：classroom 小课堂、kitchen 后厨、rpg RPG 技能书、island 像素小岛、retro 50 年代复古广告、pharmacy 中药铺、captain 机长检查单、bricks 积木说明书、studio 剧组片场、library 森林图书馆、pitstop 赛车维修站（详情见 reference/worlds.md）。用户直接点名某个世界就不用开选择页，直接 set world。
| 情况 | 怎么做 |
|---|---|
| 有默认 | 告诉用户「本次用默认世界：X，要换说一声」，直接往下做 |
| 没有（第一次用） | 先 python3 $S/doctor.py 自检；再 python3 $S/world_picker.py <任务目录>/世界选择.html 打开世界选择页，用户看样张挑一个 → python3 $S/settings.py set world <世界ID> |
| 「换默认世界」 | 重新打开选择页，选完 set world |
| 「这次用 RPG」 | 只这一次，不改设置；在 outline.md 顶部写「本次世界：rpg」 |
| 选的是小课堂（classroom） | 要用户的角色：settings.py get-character（第一次用会报「没有角色」，这是正常的）。没有就 import-character ~/.comic-maker/characters/<ID>（用过漫画小课堂的话），或用用户给的 IP 图 add-character（字段见下面「角色档字段」），没有 IP 就先用漫画小课堂生成一个 |
世界库在 reference/worlds.md（映射、场景、画风、载体、作者评价、样张）。数据存在 ~/.scene-ppt/，升级 skill 不会覆盖；家目录写不进时（Codex 沙盒）自动存到当前项目的 .scene-ppt/，以后在这个项目里用会自动读到；也可以用环境变量 SCENE_PPT_HOME 指定。
几种情况叠在一起时：用户点名了世界 → 不开选择页；快速模式 → 跳过大纲拍板；用户只要几页 → 那几页就是全部，出完即交付；第一次用的试图确认只在确认模式下等用户。
角色档字段（只有小课堂世界需要）
| 字段 | 怎么写 | 用在哪 | 例子 |
|---|---|---|---|
| 角色ID | 英文小写 | 文件夹名 | tuantuan |
--ref |
角色图，png / jpg / webp 都行，最好单个角色、正面、背景干净、图里没字；会转成 ref.png |
出图时自动垫图 | 团团.png |
--name |
中文名 | 画面描述、对话 | 团团 |
--desc-cn |
中文外貌短语，不带名字，能直接接名字 | 每页主角第一次出现写「<desc_cn>」 | 戴圆框眼镜、穿米色针织背心的小熊猫 |
--name-en / --species-en / --desc-en |
英文名、物种、英文外貌（和漫画小课堂通用，本 skill 不直接用，照图写上即可） | 漫画小课堂 | Tuantuan / Red Panda / red panda with cream face markings, round glasses… |
--series |
系列名 4–6 字 | 封面系列名木牌 | 团团小课堂 |
What ships with it
60 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.
- examples/classroom/C1-N49.jpg 136 KB
- examples/classroom/C1-N49.txt 709 B
- examples/classroom/C2-N49.jpg 136 KB
- examples/classroom/C2-N49.txt 605 B
- examples/classroom/C3-N49.jpg 138 KB
- examples/classroom/C3-N49.txt 610 B
- examples/kitchen/K1-N24.jpg 85 KB
- examples/kitchen/K1-N24.txt 869 B
- examples/kitchen/K2-N24.jpg 81 KB
- examples/kitchen/K2-N24.txt 1002 B
- examples/kitchen/K3-N24.jpg 89 KB
- examples/kitchen/K3-N24.txt 1.1 KB
- examples/kitchen/K4-N24.jpg 70 KB
- examples/kitchen/K4-N24.txt 650 B
- examples/pharmacy/Z1-N78.jpg 106 KB
- examples/pharmacy/Z1-N78.txt 863 B
- examples/pharmacy/Z2-N78.jpg 101 KB
- examples/pharmacy/Z2-N78.txt 1.1 KB
- examples/pharmacy/Z3-N78.jpg 94 KB
- examples/pharmacy/Z3-N78.txt 748 B
- examples/rpg/R1-N50.jpg 90 KB
- examples/rpg/R1-N50.txt 543 B
- examples/rpg/R2-N50.jpg 94 KB
- examples/rpg/R2-N50.txt 833 B
- examples/rpg/R3-N50.jpg 89 KB
- examples/rpg/R3-N50.txt 773 B
- examples/rpg/R4-N50.jpg 95 KB
- examples/rpg/R4-N50.txt 793 B
- README.md 1.6 KB
- reference/lessons.md 2.0 KB
- reference/page-types.md 1.9 KB
- reference/world-samples/bricks-1.jpg 129 KB
- reference/world-samples/bricks-2.jpg 113 KB
- reference/world-samples/bricks-3.jpg 79 KB
- reference/world-samples/captain-1.jpg 208 KB
- reference/world-samples/captain-2.jpg 207 KB
- reference/world-samples/captain-3.jpg 204 KB
- reference/world-samples/classroom-1.jpg 136 KB
- reference/world-samples/classroom-2.jpg 136 KB
- reference/world-samples/classroom-3.jpg 138 KB
- reference/world-samples/island-1.jpg 150 KB
- reference/world-samples/island-2.jpg 176 KB
- reference/world-samples/island-3.jpg 133 KB
- reference/world-samples/island-4.jpg 148 KB
- reference/world-samples/kitchen-1.jpg 141 KB
- reference/world-samples/kitchen-2.jpg 133 KB
- reference/world-samples/kitchen-3.jpg 145 KB
- reference/world-samples/kitchen-4.jpg 119 KB
- reference/world-samples/library-1.jpg 209 KB
- reference/world-samples/library-2.jpg 229 KB
- reference/world-samples/library-3.jpg 194 KB
- reference/world-samples/pharmacy-1.jpg 181 KB
- reference/world-samples/pharmacy-2.jpg 173 KB
- reference/world-samples/pharmacy-3.jpg 161 KB
- reference/world-samples/pitstop-1.jpg 168 KB
- reference/world-samples/pitstop-2.jpg 180 KB
- reference/world-samples/pitstop-3.jpg 174 KB
- reference/world-samples/retro-1.jpg 216 KB
- reference/world-samples/retro-2.jpg 191 KB
- reference/world-samples/retro-3.jpg 184 KB
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 · 138 lines · 133 tokens per session scan A 06ddfd7b1f1e
scene-ppt is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (784 stars, last pushed 13d ago), licensed MIT. It adds 133 tokens to every session and 3,410 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.