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 h5git 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/h5)<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/h5"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/h5/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/h5"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/h5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 373 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 373 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00110 | $0.05620 |
| Opus 5 | $0.00055 | $0.02810 |
| Sonnet 5 | $0.00022 | $0.01124 |
| Haiku 4.5 | $0.00011 | $0.00562 |
Grade A, and why
教程类H5-小红书小工具 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 — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
教程类 H5 · 小红书小工具
核心理念
教程类 H5 = 离线 SPA 课程页 + AI 生图配图 + 杂志海报风视觉 + 强容器约束。
| 维度 | 跟普通 H5 的差异 |
|---|---|
| 运行环境 | 小红书"小工具"容器（不是普通浏览器）—— 受限 CSP、纯离线、强容器约束 |
| AI 能力 | ❌ 完全用不到 LLM / 联网 / 定位 —— H5 是"纯静态规则引擎" |
| 用户行为 | 读 5-10 分钟、收藏 / 转发 / 反复看，不是"用完即弃"的工具 |
| 复用价值 | 强（沉淀 1 次用 3 年）vs 互动小工具（弱，用 1 次就死） |
| 核心能力 | 文字 + 图 + 课程结构（SPA 多页） |
核心主张：教程类 H5 不是"评分小工具"——评分是用完即弃的伪需求；教程是沉淀资产。
案例：用户原始需求是"做评分小工具"，agent 推荐了 6 个候选 + 1 个推荐，被用户反馈"评分小工具很鸡肋"，最终改成"长篇讲解 + 多课程 SPA"——结构升级后价值翻 10 倍。
何时使用
- 用户要"做教程类 H5" / "小红书小工具" / "H5 课程"
- 主题是讲清楚 1 个大知识点（4 层栈 / 5 步流程 / 7 节课程 / 1 套范式）
- 想在小红书创作者中心 → 小工具发布
- 需要支持点击看详情 + 返回 + 上一节 / 下一节
不适用
- ❌ 需要 LLM / AI 推理的"智能工具"（H5 用不到 AI）
- ❌ 实时行情 / 联网 / 调 API 的"动态工具"
- ❌ 评分 / 测试 / 测评（用户反馈"很鸡肋"——沉淀价值低）
- ❌ 多 HTML 页面站点（容器只允许单页 + JS 视图切换）
5 步工作流
Step 1 · 主题规划（10 分钟）
目的：把"想讲什么"变成可执行的内容大纲。
关键决策：
| 决策 | 推荐 | 理由 |
|---|---|---|
| 课程数 | 5-7 节 | < 5 节太单薄；> 7 节读者疲劳 |
| 每节长度 | 600-1200 字 | 5 分钟读完 |
| 每节结构 | 钩子 + 4 段正文 + 金句 + 行动 | 4 段 = 4 个子主题；金句 = 记忆点；行动 = 转化 |
| 课程目录 | 顶栏 logo + 课程列表 + 鸡汤句 | 0.5 秒 get 项目定位 |
输出：1 份 outline.md（每节 1 行标题 + 1 段简介）
Step 2 · 内容准备（30-60 分钟）
目的：把大纲写成 5-7 节完整长文。
每节模板：
# 课 X · {title}
## 钩子（1 句话）
{反常识 / 痛点 / 翻转，让读者想继续看}
## 段 1 · {heading}
{150-200 字，1 个具体概念 / 数据 / 案例}
## 段 2 · {heading}
{150-200 字，承接段 1，1 个新角度}
## 段 3 · {heading}
{150-200 字，对比 / 反例 / 易混概念}
## 段 4 · {heading}
{150-200 字，落地建议 / 操作步骤 / 怎么用}
## 金句（1 句）
{短句，能复述，能截图，能传播}
## 行动（1 段）
{今天就能做的 1 件事}
关键决策：
| 决策 | 推荐 | 反例 |
|---|---|---|
| 中文写作 | 0.5 秒 get 到的动词优先 | "实现价值创造" / "赋能业务" |
| 段落长度 | 150-200 字 / 段 | < 100 字太空，> 300 字读者跳读 |
| 金句 | "X 不是 Y，是 Z" 句式 | 抽象感叹（"加油" / "努力"） |
| 行动 | 具体到"今天做 1 件事" | "持续精进" / "深度思考" |
输出：5-7 节完整长文（共 4000-8000 字）
Step 3 · 视觉准备（30 分钟）
目的：用 AI 生 4 张 16:9 配图 + 1 张 1:1 logo。
资源清单：
| 资产 | 比例 | 数量 | 用途 |
|---|---|---|---|
| 课程封面 | 16:9 | 1 张 | 首页 hero |
| 配图 | 16:9 | 3 张 | 课 1/2/3 配图（其他课程用 CSS 渐变占位） |
| logo | 1:1 | 1 张 | 小红书"图标"框 |
What ships with it
17 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/ai-knowledge-stack/00-cover.jpg 489 KB
- examples/ai-knowledge-stack/00-logo.jpg 433 KB
- examples/ai-knowledge-stack/01-hook.jpg 735 KB
- examples/ai-knowledge-stack/02-stack.jpg 733 KB
- examples/ai-knowledge-stack/03-flow.jpg 706 KB
- examples/ai-knowledge-stack/data.js 20 KB runs code
- examples/ai-knowledge-stack/index.html 609 B
- examples/ai-knowledge-stack/main.js 7.6 KB runs code
- examples/ai-knowledge-stack/README.md 4.0 KB
- examples/ai-knowledge-stack/style.css 9.9 KB
- manifest.json 2.0 KB
- README.md 4.7 KB
- templates/data.js 3.0 KB runs code
- templates/index.html 609 B
- templates/main.js 7.6 KB runs code
- templates/README.md 3.8 KB
- templates/style.css 9.9 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 · 539 lines · 110 tokens per session scan A 360282b4a5ba
教程类H5-小红书小工具 is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 5,620 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 2026-08-30.
Other skills, from other repositories
webview
Show a native macOS webview UI to the user and get structured input back. Use when an interactive macOS session needs human-in-the-loop for multi-field input, option selection from 5+ choices, approval with context, or content review — NOT for yes/no questions. Handles the full flow — spawning the webview, generating…
design-agent
You are the Design agent for this project. You own React components, page routes, design tokens, and visual layout.
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.
x-lsof
Enhanced lsof (List Open Files) with interactive UI and structured output. View open files, network connections, and processes. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
omh-codebase-uml
This is a Hermes-native codebase-uml workflow skill.
story-long-analyze
A structured process for deeply analysing a long online novel, starting with its opening three chapters and continuing chapter by chapter.