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 wechat-deliverygit 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/wechat-delivery)<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/wechat-delivery"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/wechat-delivery/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/wechat-delivery"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/wechat-delivery.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 | $0.00129 | $0.04542 |
| Opus 5.5 | $0.00052 | $0.01817 |
| Sonnet 5.5 | $0.00026 | $0.00908 |
| Haiku 4.5 | $0.00013 | $0.00454 |
Grade A, and why
wechat-delivery 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 1mo 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公众号内容交付 / WeChat Desktop Delivery
把"在公众号发一篇文章"从纯人肉 10h 流程改造成 30 min（Mavis）+ 30s（用户粘贴） 的标准化端到端交付。
🔗 相关资源（双向互链）
| 端 | 路径 | 用途 |
|---|---|---|
| 公共方法论 | pretty-skills/内容创作/杂志风公众号品鉴/（GitHub 公开） |
16 条铁律 + 4 张参考图 + 7 问自检（公开方法论） |
| 本地实操 | references/magazine-style-16-rules.md（本 skill） |
Mavis 写公众号时直接加载的 16 条铁律 |
| 7 维心法 | references/writing-craft-7d-rubric.md（本 skill） |
写完 1 分钟 7 问自检 |
| 5 段钩子 | references/wechat-hook-chain.md（本 skill） |
knowhub 5 段叙事钩子链 |
| 主题库（v3.23 待办） | pretty-skills/视觉创作/gzh-design公众号排版主题库/（GitHub 公开） |
7 套起步主题 + 5 步排版 pipeline + 10 条反模式 |
| 主题库指针 | references/theme-library-pointer.md（本 skill） |
指向 pretty-skills 主题库 case 的加载入口 |
互链原则：pretty-skill 公共 case 是「方法论源头」，本 skill references/ 是「Mavis 自动加载的可执行版本」。两者内容 90% 相同，只维护 1 处（GitHub 远端公共 case），本地 reference 引用远端路径。
核心约束：Mavis 不自动化插入公众号编辑器（React 富文本，
mavis browser工具栈打不进去）→ 改为桌面文件夹交付。
Trigger / 触发词
用户说以下任意一种情况时调用：
| 触发词 | 行为 |
|---|---|
| 写公众号 | 启动完整 5 步流程 |
| 公众号文章 | 同上 |
| （用户的公众号名） | 默认填这个公众号名 + 同上 |
| 配公众号 / 公众号配图 | 只走 Step 3 出图（用户已有正文） |
| 公众号排版 / 公众号封面 | 同上 |
不触发的场景：
- 「帮我看看这个公众号文章写得怎么样」→ 这不是交付，是 review，不在本 skill 范围
- 「公众号涨粉怎么办」→ 这是运营问题，不在本 skill 范围
- 「把网页内容转载到公众号」→ 走转载流程，需要先和用户对齐版权
5 步交付流程（v3.18 launch 验证 · 30 min）
配图硬规则（v3.21 · 公众号封面 2.35:1 + 1:1 兼容）
公众号封面有 2.35:1（消息列表）+ 1:1（转发卡片/公众号主页） 两种展示形式，必须用一张图同时满足两种效果：
| 位置 | 内容 | 比例 |
|---|---|---|
| 顶部 30% | 标题文字（深棕大字 · 居中） | 留白 |
| 中心 60% | 主体插画（手绘马卡龙 · 一图一概念） | 2.35:1 截中央 / 1:1 截中央 |
| 底部 10% | 副标题 / 副信息（小字） | 留白 |
设计原则：
- ❌ 不要装饰边框 / 阴影 / 渐变背景
- ❌ 不要底部放主体（裁剪后会丢）
- ✅ 标题字号大、字数少（≤ 10 字）
- ✅ 主体在画面垂直中心靠下（不是底部！）
- ✅ 大量留白（cream paper 背景）
参考案例：pretty-skill/assets/readme-1-banner.png（v3.22 README banner）就是按这个规则出的。
[Step 1 调研] → [Step 1.5 evidence 链] → [Step 2 写] → [Step 2.5 8 维 rubric] → [Step 3 出图] → [Step 4 桌面交付] → [Step 5 用户粘贴]
(30s) (5 min · v3.24) (30 min) (1 min · v3.24) (10 min) (10s) (30s)
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.
- 1mo ago First seen · 286 lines · 129 tokens per session scan A c598914b325b
wechat-delivery is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 4,542 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 2026-08-30.
Other skills, from other repositories
story-long-write
A Chinese-language coaching workflow for creating a long online novel from the initial idea through the outline and chapter text. It starts by defining the intended emotion, then uses research and story-planning stages to guide writing.
story-import
A Chinese-language workflow for turning an existing novel into a structured writing project that can be continued later.
story-review
A review process for finding problems in a novel’s structure, characters, wording, and world rules. It can use several reviewers or one reviewer when others are unavailable.
story-short-write
A tool for writing complete short online novels, from the initial idea through the finished manuscript. It focuses on a single main emotional effect and usually uses first-person narration.
story-long-analyze
A structured process for deeply analysing a long online novel, starting with its opening three chapters and continuing chapter by chapter.
story-short-analyze
A tool for taking apart short online fiction to explain its story idea, structure, emotional progression, reversals, and writing techniques.