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 aAAaqwq/AGI-Super-Team --skill content-typographygit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/content-typography)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/content-typography"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-typography/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/aaaaqwq/agi-super-team/content-typography"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-typography.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 | $0.00128 | $0.02618 |
| Opus 5 | $0.00064 | $0.01309 |
| Sonnet 5 | $0.00026 | $0.00524 |
| Haiku 4.5 | $0.00013 | $0.00262 |
Grade A, and why
content-typography 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.
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.
中文内容视觉排版
这不是“选个字体” skill。 这是把一句标题排成更好读、更有冲击、更像成熟内容团队做的版式。
核心目标
解决 5 个问题：
- 读不清：字太小、太密、背景打架
- 不聚焦：所有字一样重，没有主次
- 不耐看：分行乱、对齐飘、留白脏
- 不转化：重点词没被打出来，3 秒内抓不住人
- 不适配平台：XHS、公众号、抖音的视觉逻辑混用
先判断：你在排什么
先把需求分成 3 类：
A. 冲击型封面
适用：小红书、抖音图文封面、B站缩略图 目标：3 秒抓眼 + 一眼看懂主题 特点：
- 文案短
- 主标题权重极高
- 允许更强对比和更激进分行
B. 编辑型封面
适用：公众号首图、掘金封面、知识星球横幅 目标：专业、清晰、可信 特点：
- 字数可稍多
- 重信息秩序
- 留白和对齐比“炸裂”更重要
C. 海报型排版
适用：活动海报、课程卡片、知识总结长图头图 目标：层级完整 + 结构稳定 特点：
- 通常有标题、副标题、标签、时间/身份信息
- 需要严格层级，不要只会把标题放大
排版工作流
输入：原始标题 + 核心观点 + 平台 + 画面背景
↓
Step 1: 压缩标题（砍废字，只留钩子）
↓
Step 2: 标出主关键词（1-3个）
↓
Step 3: 决定信息层级（主标题 / 副标题 / 标签）
↓
Step 4: 设计分行（按意思断，不按字数硬切）
↓
Step 5: 选字重 / 对齐 / 留白 / 强调色
↓
Step 6: 按平台规格微调
Step 1：先压缩标题，不要直接排
原则
- 能删的虚词全删
- 一张封面只讲 1 个主判断
- 标题尽量保留“冲突 / 利益 / 反常识 / 结果”之一
例子
原句：
试了 6 个 AI 编程工具之后，说几句大实话
压缩后可变成：
6个AI编程工具实测6个AI编程工具，说点真话AI编程工具，别再瞎吹了
原句：
为什么 90% 的 AI Agent 其实都是噱头
压缩后可变成：
90% AI Agent是噱头AI Agent，大多是包装别再神化AI Agent了
Step 2：找主关键词，只打 1-3 个
不要每个词都强调。
优先强调：
- 数字：
90%、6个 - 冲突词：
封禁、噱头、真相、别再 - 赛道词：
AI Agent、AI编程、小红书
强调规则
- 强调词最多 1-3 个块
- 同一行里最好只有 1 个视觉重心
- 如果已经用颜色强调，就别再给这个词加描边、投影、emoji 三连击
Step 3：信息层级
默认只用 3 层：
L1 主标题
- 画面里最先被看到
- 通常占 60-80% 视觉注意力
- 可以 1-2 行
L2 补充信息
- 用来补语义，不抢主标题
- 例如：
实测 / 避坑 / 2026 / 一线经验
L3 标签 / 身份 / 场景说明
- 最弱一层
- 例如：
内容创业、AI工具、亲测
铁律：不要出现 4 个以上同级信息块。 一旦同级元素太多，画面会散。
Step 4：分行规则
1. 按意思断，不按字数断
好：
90% AI Agent
是噱头
差：
90% AI
Agent是
噱头
2. 第一行放“抓人词”
优先把最强的信息放在第一行左上或视觉中心。
3. 行数优先级
- 冲击型封面：2 行最佳，3 行上限
- 编辑型封面：1-2 行最佳
- 海报型：视结构而定，但主标题仍应控制在 2-3 行内
4. 避免这些断法
- 数字和量词拆开：
6/个 - 专有名词拆开：
AI/Agent - 情绪短语拆开：
别再/被骗了
Step 5：字体与字重
默认建议（中文内容封面）
- 中文标题：思源黑体 / 阿里巴巴普惠体 / HarmonyOS Sans / 苹方 / 优设标题黑 同类风格都行
- 原则：先选中性、清晰、粗壮的无衬线体，别一上来玩花字
字重规则
- 主标题：Bold / Heavy
- 副标题：Regular / Medium
- 标签：Regular / Medium
一个版面里最多两种字重策略
推荐：
- 主标题 Heavy
- 其他全部 Medium
What ships with it
2 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 · 128 tokens per session scan A dcc5dfefd248
content-typography is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed 2d ago), licensed MIT. It adds 128 tokens to every session and 2,618 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
fidelity-gate
Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.
crossbreed
Structural recombination of existing designs. Takes 2-3 prototypes or design approaches and spawns N agents to create HYBRID designs, each with a different "dominant parent" whose architecture leads while grafting specific elements from the others.
mapping-user-journeys
Use when mapping user journeys is required during ux work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
prototyping-critical-flows
Use when prototyping critical flows is required during ux work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
reviewing-visual-regressions
Use when reviewing visual regressions is required during ux work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
designing-invisible-interfaces
Use when designing invisible interfaces within creativity lifecycle boundaries, especially when does the artifact make the owned decision for designing invisible interfaces explicit and bounded?.