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 comic-makergit 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/comic-maker)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/comic-maker"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/comic-maker/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/comic-maker"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/comic-maker.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 | $0.00115 | $0.02409 |
| Opus 5.5 | $0.00046 | $0.00964 |
| Sonnet 5.5 | $0.00023 | $0.00482 |
| Haiku 4.5 | $0.00012 | $0.00241 |
Grade A, and why
comic-maker 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
漫画小课堂(comic-maker)
一个固定的老师角色,用一期漫画讲清一个概念。当前助手(Claude 或 Codex)写故事和每页提示词、交付前逐页看图;出图交给 Codex 内置 imagegen 原样执行;脚本负责检查和核对。
下文 S 指本 skill 的脚本目录:
S=<本 SKILL.md 所在目录>/scripts
默认配置
风格:小课堂(styles/classroom.md);画风跟着角色参考图走
比例:3:4(提示词第二句写 A vertical 3:4 manga comic page…,见「提示词铁律」;实测 1086×1448)
主角:默认角色(~/.comic-maker/characters/<角色ID>/,settings.py 管理);讲 AI 时配角用 AI Helper 小机器人
每期:封面「开课」+ 正文 4–7 页 + 结尾「下课」
出图:Codex 内置 imagegen(scripts/render_codex.py),默认用你 Codex 自己配置的模型
第 0 步:角色(每次开工先看)
python3 $S/settings.py get default(打印出角色档 JSON = 有默认角色;报「没有默认角色」= 还没有):
- 有默认角色:告诉用户「本期老师是 X(系列名),要换说一声」,直接往下做。
- 没有(第一次用):先跑
python3 $S/doctor.py自检,再按templates/character.md准备角色——- 有自己的 IP:给一张图 + 名字,写角色档(字段表在
templates/character.md),给用户确认后保存。 - 没有:问三件事(画什么、配饰、画风,默认彩铅水彩)→ 出 3–4 个候选 → 用户挑 → 保存。
- 有自己的 IP:给一张图 + 名字,写角色档(字段表在
- 「这期用团团」:
settings.py get <角色ID>读那个角色,只这期用;「以后都用团团」:settings.py use <角色ID>。
启动:先定协作模式
- 快速模式(用户说「直接做」「你定」「随便选个主题」):不逐项问,直接给故事线表格 + 每页布局,一次展示后出图;只在出图后请用户看。
- 确认模式(默认):在这几处停下来等用户:① 新建角色时,角色档(名字、外貌、系列名);② 故事线和布局;③ 第一次用 / 刚换角色时的封面试图。其余不打断。
工作流程
步骤 1:物料理解
- 用户给了文章 / 文件:先读完,提炼核心定义和 3–5 个关键点;数字、事实只用原文的。
- 只给了主题:基于常识讲,事实拿不准的不写进对白。
- 原文里的真人(作者朋友、名人)不画成角色;产品名可以写成字,但不要画品牌标志。
步骤 2:故事线 + 布局(用户拍板一次)
- 按
templates/story-structure.md选结构(问题-方案 / 教程 / 故事),默认 6–9 页(用户指定页数就照用户的,3–5 页用「压缩版」),第一页固定封面「开课」、最后一页固定结尾「下课」(见styles/classroom.md「系列固定页」)。 - 每页按
templates/layout-patterns.md选布局,ASCII 示意。 - 每格写:画面(谁在做什么、具体道具)、对话气泡、旁白 / 标注。
- 原则:每格是一个场景不是信息点;有连贯故事线(问题 → 解决 → 结果);元素丰富;字不多不少(每页 2–5 处指定文字)。
步骤 3:写提示词
- 按
templates/prompt-template.md写,每页一个文件:<任务目录>/prompts/00.txt、01.txt …(00 = 封面)。角色英文名、外貌、系列名从角色档原样填入;<hand>按角色换成 paw / hand / wing;不讲 AI 的主题删掉 AI 小机器人那一行。 - 好例子:
examples/mcp/(MCP 一期 8 页,示例角色橘子,3 张缩略图),写新一期前先看一份。 - 每份写完对照模板末尾的自检表。
步骤 4:出图 + 核对
python3 $S/render_codex.py <任务目录> --check # 只检查提示词(出图前也会自动查)
python3 $S/render_codex.py <任务目录> --only 00 --title "系列名 · 主题" # 第一次用 / 刚换角色:先出封面看角色像不像(确认模式等用户说像再继续;快速模式自己看像就继续)
python3 $S/render_codex.py <任务目录> --title "系列名 · 主题" # 出 prompts/ 里还没出的页
What ships with it
24 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/character/juzi-prompt.txt 518 B
- examples/character/juzi.jpg 195 KB
- examples/mcp/00.jpg 262 KB
- examples/mcp/00.txt 1.5 KB
- examples/mcp/01.txt 1.5 KB
- examples/mcp/02.jpg 292 KB
- examples/mcp/02.txt 1.5 KB
- examples/mcp/03.txt 1.4 KB
- examples/mcp/04.txt 1.7 KB
- examples/mcp/05.txt 1.4 KB
- examples/mcp/06.txt 1.4 KB
- examples/mcp/07.jpg 273 KB
- examples/mcp/07.txt 1.3 KB
- README.md 1.5 KB
- scripts/_data.py 3.1 KB runs code
- scripts/doctor.py 3.2 KB runs code
- scripts/mark.js 3.7 KB runs code
- scripts/render_codex.py 17 KB runs code
- scripts/settings.py 3.6 KB runs code
- styles/classroom.md 3.4 KB
- templates/character.md 4.5 KB
- templates/layout-patterns.md 5.1 KB
- templates/prompt-template.md 7.9 KB
- templates/story-structure.md 2.9 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 · 111 lines · 115 tokens per session scan A a06e183ff336
comic-maker is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (784 stars, last pushed 13d ago), licensed MIT. It adds 115 tokens to every session and 2,409 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.