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 skillmds/skillmd --skill ip-diagram-creatorgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/ip-diagram-creator)<a href="https://agentmods.dev/skills/skillmds/skillmd/ip-diagram-creator"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ip-diagram-creator/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/skillmds/skillmd/ip-diagram-creator"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ip-diagram-creator.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 | $0.00228 | $0.04026 |
| Opus 5.5 | $0.00091 | $0.01610 |
| Sonnet 5 | $0.00046 | $0.00805 |
| Haiku 4.5 | $0.00023 | $0.00403 |
Grade A, and why
ip-diagram-creator 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 4d 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.
This is a copy
100% identical to ip-diagram-creator — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
个人 IP 图解创作器
用你的 IP 形象,生成专属内容图解。
底层原则:先定角色,再拆内容,最后生成图解。
本 Skill 不是头像生成器,也不是自由风格生图器。它的目标是把用户授权提供的个人材料转成一套可长期复用的极简手绘图解角色,再用这个角色和执行 Agent 一起参与内容表达。
推荐运行环境
推荐在支持图片读取、较高推理强度和图像生成工具的 Agent 环境中使用。这样可以直接完成图片读取、角色建档、三张角色资产生成、内容图解生成和返修。
如果当前环境支持 image_gen、GPT Image 2 或其他图像生成工具,可以在用户明确说“生成 / 出图 / 直接做图”时直出图片。建议在角色建档、长文拆解、知识卡设计和角色一致性返修时使用较高推理强度。
如果当前环境没有图像生成工具,不要假装已经出图。改为输出可复制到图像生成工具的完整 prompt,并附返修 prompt。
环境判断
每次开始前先判断当前能力:
- 如果有图像生成工具:
- 用户明确说“生成 / 出图 / 直接做图”时,可以直接生成。
- 每张图单独生成,不要把多张图拼成一张,除非用户明确要卡组总览。
- 调用前仍要构造完整 prompt,便于返修和复用。
- 如果没有图像生成工具:
- 不直接声称生成了图片。
- 输出可复制到常见图像生成模型的完整 prompt。
- 同时输出返修 prompt。
- 如果用户需要多张资产,分别输出
01_角色主锚图、02_角色规范说明图、03_动作_表情_小比例场景扩展图三个 prompt。
- 如果当前模型或环境不能读取图片:
- 先让用户补充外形描述,或要求上传可读取图片。
- 不能凭空捏造强相似角色。
- 如果用户使用低推理或非图像模型:
- 优先交付结构化角色提取卡、内容确认卡和完整 prompt。
- 不强行承诺复杂图文编排、角色一致性或图片已生成。
用户侧语言
对用户使用这些说法:
- 极简手绘图解角色
- 白底手绘图解
- 动作隐喻
- 图内信息量
- 长文配图
- 图文号知识卡
- 手机海报
- 方法拆解图
- 分镜故事图
- PPT 演讲模式
- 整页 PPT 页面图
- 导演规划卡
- page card
- Agents
- 执行 Agent
- AI 劳动力
- 执行者
- 用户
- 反馈来源
用户可见标题、标签、说明和推荐文本里不要写内部代称。需要表达辅助角色时,按语义写成 Agents、执行 Agent、执行者、用户、失败案例、风险提示或反馈来源。
知识卡模式里,辅助执行 Agent 不是可有可无的装饰。凡是步骤、流程、方法论、对比、案例、风险、行动工单类内容,默认安排 2-6 个执行 Agent,分别承担执行、反馈、错误示范、搬运卡片、标记风险、递交结果等动作;用户 IP 负责主讲、拆解、批注或调度。只有纯观点海报、极简封面或用户明确要求“不要小人 / 不要 Agent”时,才减少或移除。
入口判断
先判断用户处在哪个入口:
A. 用户还没有角色
用户给了本人照片、主页截图、头像、简介、账号资料,或说“帮我做个人 IP 图解角色”时,先进入角色建档。
读取:
references/identity-and-character.mdreferences/visual-language.md
不要要求用户按表格填写。先从现有材料里提取信息;只有缺少阻塞生成的关键信息时,才追问一个问题。
B. 用户已有角色
用户已经有角色主锚图、角色规范说明图、动作 / 表情 / 小比例场景扩展图、角色档案、头像或主形象时,跳过角色建档,直接进入内容理解。
读取:
references/content-workflow.mdreferences/modes-and-sizes.md
C. 用户只做资产
用户只要头像、动作库、表情、道具组件或视觉组件时,按角色资产任务处理,不进入内容编排。
D. 用户给内容但没有角色
先提醒需要角色建档。如果用户只想用通用无身份角色,不要强行使用本 Skill 的个人 IP 流程。
E. PPT 演讲模式
用户已有角色,或明确以自己 / 某个 IP 角色为主视觉,并要求做 PPT、课件、直播分享页、主题演讲、整套演讲页面、按大纲/逐字稿逐页出图时,进入 PPT 演讲模式。
读取:
references/ppt-presentation-mode.md
如果没有确认 IP 角色,先回到角色建档。PPT 演讲模式不服务没有个人 IP 前提的普通商业汇报。
What ships with it
5 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.
- 4d ago First seen · 321 lines · 228 tokens per session scan A aa245fceaeb7
ip-diagram-creator is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 228 tokens to every session and 4,026 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ip-diagram-creator, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
get-context
Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…