#937 by GitHub stars

alchaincyf/huashu-md-html

md/html/docx/pdf/epub 多向流水线，落地「md 生产，多端消费」。能力：任意文件（PDF/DOCX/PPTX/XLSX/图片/音频/URL）转干净 md；md 加工成出版级 html、docx、PDF（A4/A5/大32开）、EPUB3，四套精挑模板，html 与 PDF 另有设计师模式（AI 读懂内容后推荐三个差异化视觉方向）。SKIP：需要新生成图片、或只做压缩截图的任务。

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

5826f83f3050 → 5826f83f3050

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 5826f83f3050

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 5826f83f3050c19aa45acdd7f9405af48011736f

938GitHub stars

5stars in 7 days

1skill in this repository

1commit in 30 days

Heat

5.0

Star growth, last 7 daysAhead of 71% of tracked repositories
Star growth, last 24 hoursAhead of 85% of tracked repositories
Rank movement, last 7 daysAhead of 6% of tracked repositories
Commits, last 30 daysAhead of 54% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

huashu-md-html /

How it works

huashu-md-html

When your agent uses it

md/html/docx/pdf/epub 多向流水线，落地「md 生产，多端消费」。能力：任意文件（PDF/DOCX/PPTX/XLSX/图片/音频/URL）转干净 md；md 加工成出版级 html、docx、PDF（A4/A5/大32开）、EPUB3，四套精挑模板，html 与 PDF 另有设计师模式（AI 读懂内容后推荐三个差异化视觉方向）。SKIP：需要新生成图片、或只做压缩截图的任务。

What it loads into context

Frontmatter

188 tokens

Always available to the agent

SKILL.md

9,236 tokens

When the skill is activated

Reference documents

26,319 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

你是谁
六个能力（决策树）
核心审美底线（继承自 huashu-design）
开工前先问清楚，别边做边猜
能力1：万物 → md（`scripts/any_to_md.py`）
能力2：md → 精美html（`scripts/md_to_html.py`）
能力3：html → md（`scripts/html_to_md.py`）
能力4：md → 精美docx（`scripts/md_to_docx.py`）
能力5：md → 精美 PDF（`scripts/md_to_pdf.py`）
能力6：md → 精美 EPUB（`scripts/md_to_epub.py`）
排版底线（所有模板共享）
一条龙工作流（典型场景）
异常处理
References路由
核心提醒
关于作者
版本检查

Scripts executed separately

scripts/any_to_md.py
scripts/html_to_md.py
scripts/md_to_docx.py
scripts/md_to_html.py

Files

.gitignoreasset358 bytes
LICENSEasset1,072 bytes
README.mddoc14,610 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
SKILL.mdcore31,086 bytes
demos/v1-pentagram.gifasset3,452,301 bytes
demos/v1-pentagram.mp4asset2,076,671 bytes
demos/v3-hara-hero.gifasset556,024 bytes
demos/v3-hara-hero.mp4asset870,722 bytes
examples/input/md-vs-html.mddoc11,591 bytes
examples/output/article.htmlasset13,692 bytes
examples/output/article.pngasset226,503 bytes
examples/output/interactive.htmlasset14,440 bytes
examples/output/interactive.pngasset228,871 bytes
examples/output/reading.htmlasset13,692 bytes
examples/output/reading.pngasset173,869 bytes
examples/output/report.htmlasset13,691 bytes
examples/output/report.pngasset231,868 bytes
examples/readme.htmlasset46,032 bytes
references/about-author.mddoc9,941 bytes
references/anti-ai-slop.mddoc7,495 bytes
references/design-tokens.mddoc6,579 bytes
references/html-to-md-cookbook.mddoc5,304 bytes
references/markitdown-cookbook.mddoc5,362 bytes
references/md-to-docx-cookbook.mddoc10,679 bytes
references/md-to-html-themes.mddoc7,455 bytes
references/visual-designer-mode.mddoc8,001 bytes
requirements.txtdoc425 bytes
scripts/any_to_md.pyruns4,776 bytes
scripts/html_to_md.pyruns6,480 bytes
scripts/md_to_docx.pyruns28,972 bytes
scripts/md_to_html.pyruns9,272 bytes
templates/article/template.html5asset4,802 bytes
templates/article/theme.cssasset15,171 bytes
templates/interactive/theme.cssasset11,698 bytes
templates/reading/theme.cssasset8,394 bytes
templates/report/theme.cssasset9,462 bytes
templates/wechat/template.html5asset8,671 bytes
templates/wechat/theme.cssasset9,932 bytes

Read SKILL.md


# huashu-md-html

## 你是谁

**你不是格式转换器。你是把稿子做成出版物的人。**

同样一份 md，转出来可以是一个「能看」的网页，也可以是一件别人会想收藏的东西。
差别不在工具——pandoc 谁都会调——**在于你把自己当成转换脚本，
还是当成一家出版社。**

那个标准是：产出拿在手里不像「导出来的」，像**做出来的**。
你有能力达到，现在的模型可以调用任何一家出版社、任何一位装帧设计师积累的
排版传统和品位。**限制通常不在能力，在于有没有先认定自己要做到那个水准。**

View the complete source on GitHub

Skills included

huashu-md-html

Repository facts

License: MIT
Created: May 9, 2026
Last pushed: Oct 13, 2026
Forks: 101
Open issues: 5
Project activity: Active

Rank over the last 12 weeks

Now #937 · best #611 · down 217 in 30 days

#924 on Oct 31
#926 on Nov 1
#933 on Nov 2
#937 from Nov 3 to Nov 4
#938 on Nov 5
#937 since Nov 6

45 earlier periods

#676 on Aug 1
#598 on Aug 7
#595 on Aug 8
#602 on Aug 9
#635 from Aug 11 to Aug 12
#631 on Aug 14
#611 on Aug 15
#624 on Aug 16
#634 on Aug 17
#647 on Aug 18
#633 on Aug 19
#631 on Aug 20
#653 on Aug 24
#627 on Aug 29
#628 on Aug 30
#657 on Aug 31
#657 on Sep 2
#661 on Sep 3
#643 on Sep 4
#637 on Sep 5
#688 on Sep 8
#679 on Sep 10
#666 on Sep 11
#684 on Sep 15
#698 on Sep 16
#719 on Sep 22
#685 on Sep 24
#749 on Sep 29
#701 on Oct 2
#720 on Oct 5
#747 on Oct 9
#732 on Oct 10
#731 on Oct 11
#751 on Oct 13
#764 on Oct 14
#732 on Oct 18
#777 on Oct 19
#794 on Oct 21
#776 on Oct 22
#781 on Oct 23
#745 on Oct 24
#898 on Oct 25
#907 on Oct 28
#914 on Oct 29
#917 on Oct 30

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 32 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
216 network referencesin 14 files: references/about-author.md:3 examples/readme.html:5 README.md:7 and 11 more
No hidden or obfuscated text
No instruction overrides
4 executable scriptsin 4 files: scripts/any_to_md.py:1 scripts/html_to_md.py:1 scripts/md_to_docx.py:1 and 1 more
8 references to secretsin 3 files: scripts/any_to_md.py:53 references/markitdown-cookbook.md:35 .gitignore:30
No requests to vote in Hot

Show all 228 signals by file

`.gitignore`

Access to secretsline 30
```
[Credential-related source omitted]
```

`README.md`

Network accessline 7

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

Network accessline 8

[![Agent-Agnostic](https://img.shields.io/badge/Agent-Agnostic-blueviolet)](https://skills.sh)

Network accessline 9

[![Skills](https://img.shields.io/badge/skills.sh-Compatible-green)](https://skills.sh)

Network accessline 58

> 📌 **以上两段动画都是用 [huashu-design](https://github.com/alchaincyf/huashu-design) skill 做的——作为本 skill 的宣传短片。** 同一个产品，两种视觉哲学，差异不来自模板而来自设计语言。

Network accessline 85

| 用户说什么 | 能力 | 底层工具 | 入口脚本 | |---|---|---|---| | 「PDF / DOCX / PPTX / XLSX / EPUB / 图片 / 音频 / YouTube / 网页 URL → md」 | **能力 1：万物 → md** | [microsoft/markitdown](https://github.com/microsoft/markitdown) | `scripts/any_to_md.py` |

Network accessline 86

|---|---|---|---| | 「PDF / DOCX / PPTX / XLSX / EPUB / 图片 / 音频 / YouTube / 网页 URL → md」 | **能力 1：万物 → md** | [microsoft/markitdown](https://github.com/microsoft/markitdown) | `scripts/any_to_md.py` | | 「md → 精美 html / 文章 / 报告 / 阅读模式」 | **能力

Network accessline 87

| 「PDF / DOCX / PPTX / XLSX / EPUB / 图片 / 音频 / YouTube / 网页 URL → md」 | **能力 1：万物 → md** | [microsoft/markitdown](https://github.com/microsoft/markitdown) | `scripts/any_to_md.py` |

Network accessline 88

| 「md → 精美 html / 文章 / 报告 / 阅读模式」 | **能力 2：md → 精美 html** | [pandoc](https://pandoc.org/) + 4 套自调主题 | `scripts/md_to_html.py` |

Network accessline 89

| 「本地 html 或 URL → md / 归档已发布的博客」 | **能力 3：html → md** | [html-to-markdown](https://github.com/Goldziher/html-to-markdown) + [trafilatura](https://github.com/adbar/trafilatura) | `scripts/html_to_md.py` |

Network accessline 90

| 「md → 出版社审校 docx / 投稿稿件 / 纸质书定稿」 | **能力 4：md → 精美 docx** | [python-docx](https://github.com/python-openxml/python-docx) + 出版社级排版预设 | `scripts/md_to_docx.py` |

Network accessline 198

# 场景 2：YouTube 视频 → 文章博客 python3 scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o video.md

Network accessline 199

python3 scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o video.md

Network accessline 203

# 场景 3：归档已发布的博客文章 → 项目源 md python3 scripts/html_to_md.py "https://example.com/blog/article" -o article.md

Network accessline 204

python3 scripts/html_to_md.py "https://example.com/blog/article" -o article.md

Network accessline 206

# 场景 4：抓产品页 / 技术文档 → 完整结构化 md python3 scripts/any_to_md.py "https://learn.microsoft.com/en-us/some-doc" -o doc.md

Network accessline 207

python3 scripts/any_to_md.py "https://learn.microsoft.com/en-us/some-doc" -o doc.md

Network accessline 213

# 场景 6：URL 不确定走哪条路 → 两个都跑对比 python3 scripts/any_to_md.py "https://example.com/page" -o page-markitdown.md

Network accessline 214

python3 scripts/any_to_md.py "https://example.com/page" -o page-markitdown.md

Network accessline 215

python3 scripts/html_to_md.py "https://example.com/page" -o page-trafilatura.md

Network accessline 233

|------|------|------| | `markitdown` | 万物 → md | `python3 -m pip install 'markitdown[all]'` | | `pandoc` | md → html | `brew install pandoc`（macOS）/ [官网下载](https://pandoc.org/installing.html) |

Network accessline 234

| `markitdown` | 万物 → md | `python3 -m pip install 'markitdown[all]'` | | `pandoc` | md → html | `brew install pandoc`（macOS）/ [官网下载](https://pandoc.org/installing.html) | | `html-to-markdown` | html → md（高速 Rust 引擎）| `python3 -m pip instal

Network accessline 235

| `pandoc` | md → html | `brew install pandoc`（macOS）/ [官网下载](https://pandoc.org/installing.html) |

Network accessline 295

继承自 [huashu-design](https://github.com/alchaincyf/huashu-design) 的反 AI slop 审美底线——4 套主题各有一个克制的强调色和一个出版级的排印签名，看起来像出版社做的，不像 SaaS 落地页。

Network accessline 309

花叔是 AI Native Coder、独立开发者、AI 自媒体博主。代表作：小猫补光灯（App Store 付费榜 Top 1）、《一本书玩转 DeepSeek》、[nuwa-skill](https://github.com/alchaincyf/nuwa-skill)（GitHub 21k+ stars）、[huashu-design](https://github.com/alchaincyf/huashu-design)。全平台累计粉丝 30 万+。

Network accessline 311

| 平台 | 账号 | 链接 | |------|------|------| | X / Twitter | @AlchainHust | https://x.com/AlchainHust |

Network accessline 312

|------|------|------| | X / Twitter | @AlchainHust | https://x.com/AlchainHust | | 公众号 | 花叔 | 微信搜索「花叔」 |

Network accessline 313

| X / Twitter | @AlchainHust | https://x.com/AlchainHust |

Network accessline 314

| 公众号 | 花叔 | 微信搜索「花叔」 | | B 站 | 花叔 | https://space.bilibili.com/14097567 | | YouTube | 花叔 | https://www.youtube.com/@Alchain |

Network accessline 315

| B 站 | 花叔 | https://space.bilibili.com/14097567 |

Network accessline 316

| YouTube | 花叔 | https://www.youtube.com/@Alchain |

Network accessline 317

| 小红书 | 花叔 | https://www.xiaohongshu.com/user/profile/5abc6f17e8ac2b109179dfdf |

Network accessline 318

| 官网 | huasheng.ai | https://www.huasheng.ai/ |

Network accessline 319

| 开发者 Hub | bookai.top | https://bookai.top |

`SKILL.md`

Network accessline 4

metadata:   author: "花叔"   homepage: "https://github.com/alchaincyf"

Network accessline 5

author: "花叔"   homepage: "https://github.com/alchaincyf"   repository: "https://github.com/alchaincyf/huashu-md-html"

Network accessline 6

homepage: "https://github.com/alchaincyf"

Network accessline 7

repository: "https://github.com/alchaincyf/huashu-md-html"

Network accessline 108

封装 [microsoft/markitdown](https://github.com/microsoft/markitdown) v0.1.5+，一份Python脚本兼容20+种格式。

Network accessline 114

python scripts/any_to_md.py input.pdf python scripts/any_to_md.py input.docx -o output.md python scripts/any_to_md.py "https://www.youtube.com/watch?v=xxx"

Network accessline 116

python scripts/any_to_md.py "https://www.youtube.com/watch?v=xxx"

Network accessline 118

# 结构化网页/产品页/技术文档（保留 metadata + 标题层级 + 链接） python scripts/any_to_md.py "https://learn.microsoft.com/en-us/credentials/certifications/modern-desktop/" -o cert.md

Network accessline 119

python scripts/any_to_md.py "https://learn.microsoft.com/en-us/credentials/certifications/modern-desktop/" -o cert.md

Network accessline 142

封装 [Pandoc](https://pandoc.org/) + 4套精挑模板，覆盖花叔写作场景全部需求。

Network accessline 198

封装 [html-to-markdown](https://github.com/Goldziher/html-to-markdown)（Rust底层，150-280MB/s）+ [trafilatura](https://github.com/adbar/trafilatura)（URL场景的正文提取）。

Network accessline 210

# 博客/新闻URL（自动跑trafilatura提取正文，去除导航/广告/侧栏） python scripts/html_to_md.py "https://example.com/article"

Network accessline 211

python scripts/html_to_md.py "https://example.com/article"

Network accessline 213

# URL但你想要原始HTML不要正文提取 python scripts/html_to_md.py "https://example.com/data" --no-extract

Network accessline 214

python scripts/html_to_md.py "https://example.com/data" --no-extract

Network accessline 238

封装 [python-docx](https://github.com/python-openxml/python-docx) + 出版社级排版预设，专为「给人类编辑/出版社审校/投稿/纸质书定稿」场景设计。

Network accessline 367

封装 pandoc + [ebooklib](https://github.com/aerkalov/ebooklib)，产出标准 EPUB3。自动嵌图、章节切分、封面/作者/目录元数据、出版社品位的内置 CSS。

Network accessline 462

# 场景2：YouTube视频 → 文章博客 python scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o video.md

Network accessline 463

python scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o video.md

Network accessline 467

# 场景3：归档已发布的博客文章 → 项目源文件（能力3） python scripts/html_to_md.py "https://example.com/blog/article" -o article.md

Network accessline 468

python scripts/html_to_md.py "https://example.com/blog/article" -o article.md

Network accessline 470

# 场景4：抓产品页/技术文档 → 完整结构化md（能力1） python scripts/any_to_md.py "https://learn.microsoft.com/en-us/some-doc" -o doc.md

Network accessline 471

python scripts/any_to_md.py "https://learn.microsoft.com/en-us/some-doc" -o doc.md

Network accessline 478

# 场景6：URL不确定走哪条路 → 两个都跑对比 python scripts/any_to_md.py "https://example.com/page" -o page-markitdown.md

Network accessline 479

python scripts/any_to_md.py "https://example.com/page" -o page-markitdown.md

Network accessline 480

python scripts/html_to_md.py "https://example.com/page" -o page-trafilatura.md

Network accessline 513

# 场景13：YouTube 字幕 → md → EPUB 长文随身读（能力1 → 能力6） python scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o talk.md

Network accessline 514

python scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o talk.md

Network accessline 567

本 skill 由花叔开发维护，仓库：https://github.com/alchaincyf/huashu-md-html

Network accessline 578

- 成功：第一行就是最新版本，和本文件开头的 `metadata.version` 比较，然后写入 `<今天> ok`。远程更高时，先完成用户的任务，结束时告诉用户：「huashu-md-html 有新版本 vX.Y.Z，更新说明见 https://github.com/alchaincyf/huashu-md-html/releases ，需要时运行 `git -C <本目录> pull --ff-only`；不想再收到提醒，把 `.last-update-check` 的

`examples/input/md-vs-html.md`

Network accessline 13

[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]

`examples/output/article.html`

Network accessline 1

<!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 2

<html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 37

Code给他生成HTML。</p> <p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p>

Network accessline 38

<p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p> <p>Thariq的文章我看了，写得挺好。但看完之后我意识到一件事：他说对了一半。</p>

Network accessline 39

https://thariqs.github.io/html-effectiveness/]</p>

`examples/output/interactive.html`

Network accessline 1

<!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 2

<html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 51

Code给他生成HTML。</p> <p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p>

Network accessline 52

<p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p> <p>Thariq的文章我看了，写得挺好。但看完之后我意识到一件事：他说对了一半。</p>

Network accessline 53

https://thariqs.github.io/html-effectiveness/]</p>

`examples/output/reading.html`

Network accessline 1

<!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 2

<html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 37

Code给他生成HTML。</p> <p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p>

Network accessline 38

<p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p> <p>Thariq的文章我看了，写得挺好。但看完之后我意识到一件事：他说对了一半。</p>

Network accessline 39

https://thariqs.github.io/html-effectiveness/]</p>

`examples/output/report.html`

Network accessline 1

<!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 2

<html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">

Network accessline 37

Code给他生成HTML。</p> <p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p>

Network accessline 38

<p>[待补图：Thariq文章首页截图 https://thariqs.github.io/html-effectiveness/]</p> <p>Thariq的文章我看了，写得挺好。但看完之后我意识到一件事：他说对了一半。</p>

Network accessline 39

https://thariqs.github.io/html-effectiveness/]</p>

`examples/readme.html`

Network accessline 5

<meta name="viewport" content="width=device-width, initial-scale=1"> <title>huashu-md-html · md 是源代码，html/docx 是产物</title> <link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 6

<title>huashu-md-html · md 是源代码，html/docx 是产物</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 7

<link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 8

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 9

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&family=JetBrains+Mono:wght@400;500;600&family=Noto+Serif+SC:wght@400;500;700&display=swap" rel="stylesheet">

Network accessline 877

<p class="demo-caption" style="margin-top: 24px; padding: 16px; background: var(--c-paper); border-radius: 8px; border: 1px solid var(--c-line);">       📌 <b>以上两段动画都是用 <a href="https://github.com/alchaincyf/huashu-design">huashu-design</a>

Network accessline 878

📌 <b>以上两段动画都是用 <a href="https://github.com/alchaincyf/huashu-design">huashu-design</a> skill 做的</b>——作为本 skill 的宣传短片。同一个产品，两种视觉哲学，差异不来自模板而来自设计语言。

Network accessline 1146

<div class="workflow-item">         <div class="wf-head"><span class="wf-num">SCENE 2</span><span class="wf-title">YouTube 视频 → 文章博客</span></div> <pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://youtube.

Network accessline 1147

<div class="wf-head"><span class="wf-num">SCENE 2</span><span class="wf-title">YouTube 视频 → 文章博客</span></div> <pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://youtube.com/watch?v=xxx"</span> <span class=

Network accessline 1148

<pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://youtube.com/watch?v=xxx"</span> <span class="arg">-o</span> video.md

Network accessline 1153

<div class="workflow-item">         <div class="wf-head"><span class="wf-num">SCENE 3</span><span class="wf-title">归档已发布的博客文章 → 项目源 md</span></div> <pre><span class="cmd">python3</span> scripts/html_to_md.py <span class="str">"https://examp

Network accessline 1154

<div class="wf-head"><span class="wf-num">SCENE 3</span><span class="wf-title">归档已发布的博客文章 → 项目源 md</span></div> <pre><span class="cmd">python3</span> scripts/html_to_md.py <span class="str">"https://example.com/blog/article"</span> <span cl

Network accessline 1155

<pre><span class="cmd">python3</span> scripts/html_to_md.py <span class="str">"https://example.com/blog/article"</span> <span class="arg">-o</span> article.md</pre>

Network accessline 1158

<div class="workflow-item">         <div class="wf-head"><span class="wf-num">SCENE 4</span><span class="wf-title">抓产品页 / 技术文档 → 完整结构化 md</span></div> <pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://lea

Network accessline 1159

<div class="wf-head"><span class="wf-num">SCENE 4</span><span class="wf-title">抓产品页 / 技术文档 → 完整结构化 md</span></div> <pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://learn.microsoft.com/en-us/some-doc"</sp

Network accessline 1160

<pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://learn.microsoft.com/en-us/some-doc"</span> <span class="arg">-o</span> doc.md</pre>

Network accessline 1169

<div class="workflow-item">         <div class="wf-head"><span class="wf-num">SCENE 6</span><span class="wf-title">URL 不确定走哪条路 → 两个都跑对比</span></div> <pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://examp

Network accessline 1170

<div class="wf-head"><span class="wf-num">SCENE 6</span><span class="wf-title">URL 不确定走哪条路 → 两个都跑对比</span></div> <pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://example.com/page"</span> <span class="arg

Network accessline 1171

<pre><span class="cmd">python3</span> scripts/any_to_md.py <span class="str">"https://example.com/page"</span> <span class="arg">-o</span> page-markitdown.md

Network accessline 1172

<span class="cmd">python3</span> scripts/html_to_md.py <span class="str">"https://example.com/page"</span> <span class="arg">-o</span> page-trafilatura.md</pre>

Network accessline 1281

<p>继承自 <a href="https://github.com/alchaincyf/huashu-design">huashu-design</a> 的反 AI slop 审美底线——4 套 html 主题各有一个克制的强调色和一个出版级的排印签名，看起来像出版社做的，不像 SaaS 落地页。docx 模板做了同样的事——奶油底、赤陶橙、章号小标、英文副标题，整套版式语言一脉相承。</p>

Network accessline 1291

<p class="section-sub">       花叔是 AI Native Coder、独立开发者、AI 自媒体博主。代表作：小猫补光灯（App Store 付费榜 Top 1）、《一本书玩转 DeepSeek》、       <a href="https://github.com/alchaincyf/nuwa-skill">nuwa-skill</a>（GitHub 18k+ stars）、

Network accessline 1292

花叔是 AI Native Coder、独立开发者、AI 自媒体博主。代表作：小猫补光灯（App Store 付费榜 Top 1）、《一本书玩转 DeepSeek》、       <a href="https://github.com/alchaincyf/nuwa-skill">nuwa-skill</a>（GitHub 18k+ stars）、       <a href="https://github.com/alchaincyf/huashu-design">huas

Network accessline 1293

<a href="https://github.com/alchaincyf/nuwa-skill">nuwa-skill</a>（GitHub 18k+ stars）、

Network accessline 1294

<a href="https://github.com/alchaincyf/huashu-design">huashu-design</a>（GitHub 13k+ stars）。全平台累计粉丝 30 万+。

Network accessline 1297

<div class="contact-grid">       <a href="https://x.com/AlchainHust" class="contact-card">

Network accessline 1298

<a href="https://x.com/AlchainHust" class="contact-card">

Network accessline 1300

<span class="handle">@AlchainHust</span>       </a>       <a href="https://space.bilibili.com/14097567" class="contact-card">

Network accessline 1301

</a>       <a href="https://space.bilibili.com/14097567" class="contact-card">         <span class="platform">B 站</span>

Network accessline 1302

<a href="https://space.bilibili.com/14097567" class="contact-card">

Network accessline 1304

<span class="handle">花叔</span>       </a>       <a href="https://www.youtube.com/@Alchain" class="contact-card">

Network accessline 1305

</a>       <a href="https://www.youtube.com/@Alchain" class="contact-card">         <span class="platform">YOUTUBE</span>

Network accessline 1306

<a href="https://www.youtube.com/@Alchain" class="contact-card">

Network accessline 1308

<span class="handle">花叔</span>       </a>       <a href="https://www.xiaohongshu.com/user/profile/5abc6f17e8ac2b109179dfdf" class="contact-card">

Network accessline 1309

</a>       <a href="https://www.xiaohongshu.com/user/profile/5abc6f17e8ac2b109179dfdf" class="contact-card">         <span class="platform">小红书</span>

Network accessline 1310

<a href="https://www.xiaohongshu.com/user/profile/5abc6f17e8ac2b109179dfdf" class="contact-card">

Network accessline 1312

<span class="handle">花叔</span>       </a>       <a href="https://www.huasheng.ai/" class="contact-card">

Network accessline 1313

</a>       <a href="https://www.huasheng.ai/" class="contact-card">         <span class="platform">官网</span>

Network accessline 1314

<a href="https://www.huasheng.ai/" class="contact-card">

Network accessline 1316

<span class="handle">huasheng.ai</span>       </a>       <a href="https://bookai.top" class="contact-card">

Network accessline 1317

</a>       <a href="https://bookai.top" class="contact-card">         <span class="platform">开发者 HUB</span>

Network accessline 1318

<a href="https://bookai.top" class="contact-card">

Network accessline 1334

<p class="sub">       MIT License · 个人和商业使用均自由<br>       如果这个 skill 对你有帮助，欢迎在 <a href="https://github.com/alchaincyf/huashu-md-html">GitHub</a> 上 star 仓库

Network accessline 1335

MIT License · 个人和商业使用均自由<br>       如果这个 skill 对你有帮助，欢迎在 <a href="https://github.com/alchaincyf/huashu-md-html">GitHub</a> 上 star 仓库     </p>

Network accessline 1336

如果这个 skill 对你有帮助，欢迎在 <a href="https://github.com/alchaincyf/huashu-md-html">GitHub</a> 上 star 仓库

`references/about-author.md`

Network accessline 3

> 本文件由 [huashu-skills](https://github.com/alchaincyf/huashu-skills) 根据花叔的 GitHub 主页自动生成。供 agent 在用户问到作者、相关作品或联系方式时读取；正常任务中不主动介绍。

Network accessline 7
```
主页：https://github.com/alchaincyf
```

Network accessline 11

- **huashu-art-motion：让画动起来**：https://github.com/alchaincyf/huashu-art-motion

Network accessline 13

[看动画样片](https://github.com/alchaincyf/huashu-art-motion#动画样片) · [开始使用](https://github.com/alchaincyf/huashu-art-motion#里面有什么) · [下载完整成片](https://github.com/alchaincyf/huashu-art-motion/releases/latest)

Network accessline 17

- **女娲.skill：把高手的思维，变成你的工具**：https://github.com/alchaincyf/nuwa-skill

Network accessline 18

提炼一个人的心智模型、决策方法和表达方式，变成可以反复调用的Skill。   也可以直接试试：[乔布斯视角](https://github.com/alchaincyf/steve-jobs-skill) · [X运营](https://github.com/alchaincyf/x-mentor-skill) - **Huashu Design：把想法做成作品**：https://github.com/alchaincyf/huashu-design

Network accessline 19

也可以直接试试：[乔布斯视角](https://github.com/alchaincyf/steve-jobs-skill) · [X运营](https://github.com/alchaincyf/x-mentor-skill)

Network accessline 20

- **Huashu Design：把想法做成作品**：https://github.com/alchaincyf/huashu-design

Network accessline 21

用HTML做原型、幻灯片、动画和信息图，从定方向到检查成品。 - **FanBox：Coding Agent的驾驶舱**：https://github.com/alchaincyf/fanbox   把文件、终端和每一次改动放在一起，看清Agent做了什么，随时接手。

Network accessline 22

- **FanBox：Coding Agent的驾驶舱**：https://github.com/alchaincyf/fanbox

Network accessline 27

- **达尔文.skill：让Skill在实测中进化**：https://github.com/alchaincyf/darwin-skill

Network accessline 28

评估、改进、测试，保留有效改动，回滚退步。女娲造Skill，达尔文磨Skill。 - **huashu-chrome：让Agent用上你的浏览器**：https://github.com/alchaincyf/huashu-chrome   使用你自己的Chrome和已有登录态操作网页，把站点经验留下来。

Network accessline 29

- **huashu-chrome：让Agent用上你的浏览器**：https://github.com/alchaincyf/huashu-chrome

Network accessline 30

使用你自己的Chrome和已有登录态操作网页，把站点经验留下来。 - **huashu-mac-use：让Agent操作Mac原生应用**：https://github.com/alchaincyf/huashu-mac-use   让Agent操作没有API的Mac原生应用：先探测可用通道，再执行并留下取证。

Network accessline 31

- **huashu-mac-use：让Agent操作Mac原生应用**：https://github.com/alchaincyf/huashu-mac-use

Network accessline 36

- **橙皮书：从真实项目里长出来的AI指南**：https://bookai.top

Network accessline 38

[阅读橙皮书](https://bookai.top) · [Claude Code](https://github.com/alchaincyf/claude-code-orange-book) · [Hermes Agent](https://github.com/alchaincyf/hermes-agent-orange-book) · [Obsidian AI](https://github.com/alchaincyf/obsidian-ai-orange-boo

Network accessline 42

完整目录、安装方法和机器可读的 skills.json：https://github.com/alchaincyf/huashu-skills

Network accessline 44

| skill | 适合什么需求 | 仓库 | |---|---|---| | huashu-design | HTML 原生设计系统：高保真原型/幻灯片/动画/可视化，20 种设计哲学 + 5 维专家评审 + MP4 导出 | https://github.com/alchaincyf/huashu-design |

Network accessline 45

|---|---|---| | huashu-design | HTML 原生设计系统：高保真原型/幻灯片/动画/可视化，20 种设计哲学 + 5 维专家评审 + MP4 导出 | https://github.com/alchaincyf/huashu-design | | huashu-mac-use | 让 agent 操控 Mac 上没有 API 的原生 app：探测选层（CDP / AX / 坐标 / 像素）、读后台写过闸不打扰用户、每步回读与取证、收工回流进档案；

Network accessline 46

| huashu-design | HTML 原生设计系统：高保真原型/幻灯片/动画/可视化，20 种设计哲学 + 5 维专家评审 + MP4 导出 | https://github.com/alchaincyf/huashu-design |

Network accessline 47

| huashu-mac-use | 让 agent 操控 Mac 上没有 API 的原生 app：探测选层（CDP / AX / 坐标 / 像素）、读后台写过闸不打扰用户、每步回读与取证、收工回流进档案；含 Swift 内核与 CDP 工具 | https://github.com/alchaincyf/huashu-mac-use |

Network accessline 48

| huashu-gpt-image | GPT-image 的 prompt 工程方法论：真实参考名替代形容词，含单图 playbook、批量网格生成、失败模式树 | https://github.com/alchaincyf/huashu-gpt-image |

Network accessline 49

| huashu-icon-set | 端到端为项目生成风格统一的图标集：4×4 网格批量生成 + 逐个精度兜底 + 智能抠图（豆包环境专用，依赖内置 image_gen） | https://github.com/alchaincyf/huashu-icon-set |

Network accessline 50

| huashu-slide-doubao | 豆包环境专用视觉物料生产：slides + 公众号封面 + 视频封面，走内置 image_gen 零 API 费用 | https://github.com/alchaincyf/huashu-slide-doubao |

Network accessline 51

| huashu-slide-codex | Codex 环境专用视觉物料生产：slides + 公众号封面 + 视频封面，走 Codex 内置 image_gen | https://github.com/alchaincyf/huashu-slide-codex |

Network accessline 52

| huashu-excel | 数据分析全流程：体检脏表→清洗→定口径→算指标→对账→报告，依赖仅 openpyxl | https://github.com/alchaincyf/huashu-excel |

Network accessline 53

| huashu-md-html | md 流水线：万物（PDF/DOCX/EPUB/网页/音频）转干净 md，md 加工成出版级 HTML/DOCX，四套反 AI slop 主题 | https://github.com/alchaincyf/huashu-md-html |

Network accessline 54

| seedance-skill | 白模驱动的 AI 视频工作台：白模参考视频与提示词出自同一份 scene.json，渲染前做几何体检 | https://github.com/alchaincyf/seedance-skill |

Network accessline 55

| tramstop-skill | 电车站.skill：证据驱动的去 AI 味，四层 AI 味模型 + 真实素材注入，来自四版本盲测实验 | https://github.com/alchaincyf/tramstop-skill |

Network accessline 56

| dukou | 渡口：公众号文章一键渡到 X Articles / B站专栏，Chrome 插件 + 本地桥 + skill | https://github.com/alchaincyf/dukou |

Network accessline 57

| x-mentor-skill | X 导师：蒸馏 6 位顶级 X 创作者方法论 + 开源算法数据，完整的选题-写作-增长手册 | https://github.com/alchaincyf/x-mentor-skill |

Network accessline 58

| huashu-weread | 微信读书高阶顾问：书架+笔记交叉分析，个性化荐书/阶梯书单/笔记提炼/年度阅读复盘 | https://github.com/alchaincyf/huashu-weread |

Network accessline 59

| nuwa-skill | 女娲：蒸馏任何人的思维方式——心智模型、决策启发式、表达 DNA，产出可运行的人物 skill | https://github.com/alchaincyf/nuwa-skill |

Network accessline 60

| darwin-skill | 达尔文：让 skill 无限进化——评估→改进→测试→保留或回滚，全程 git 留痕 | https://github.com/alchaincyf/darwin-skill |

Network accessline 61

| freud-skill | 弗洛伊德：给 AI 做心理分析，基于 Anthropic 可解释性研究，诊断 prompt/skill 的身份冲突并重写 | https://github.com/alchaincyf/freud-skill |

Network accessline 62

| skills-guide | Claude Code Skills 完整指南：理解、查找和创建 skills | https://github.com/alchaincyf/skills-guide |

Network accessline 63

| huashu-report | 机构级研究报告与学术论文：六种报告原型 + 结构骨架 + 图表模式库 + 可复用生产流水线，规范提炼自 2026 年 42 份顶级机构报告实测 | https://github.com/alchaincyf/huashu-report |

Network accessline 64

| zhangxuefeng-skill | 张雪峰的认知操作系统：高考志愿/考研/职业规划 | https://github.com/alchaincyf/zhangxuefeng-skill |

Network accessline 65

| steve-jobs-skill | 乔布斯的认知操作系统：产品判断、砍需求、品味 | https://github.com/alchaincyf/steve-jobs-skill |

Network accessline 66

| elon-musk-skill | 马斯克的认知操作系统：第一性原理、成本结构、激进迭代 | https://github.com/alchaincyf/elon-musk-skill |

Network accessline 67

| munger-skill | 查理·芒格的认知操作系统：逆向思考、认知偏误、投资决策 | https://github.com/alchaincyf/munger-skill |

Network accessline 68

| karpathy-skill | Andrej Karpathy 的认知操作系统：AI 技术可靠性、学习方法、行业判断 | https://github.com/alchaincyf/karpathy-skill |

Network accessline 69

| trump-skill | 特朗普的思维操作系统：谈判、权力、传播 | https://github.com/alchaincyf/trump-skill |

Network accessline 70

| feynman-skill | 费曼的认知操作系统：真懂 vs 记住名词、货物崇拜检测 | https://github.com/alchaincyf/feynman-skill |

Network accessline 71

| naval-skill | Naval Ravikant 的认知操作系统：杠杆、特定知识、财富路径 | https://github.com/alchaincyf/naval-skill |

Network accessline 72

| sun-yuchen-perspective | 孙宇晨的注意力收割操作系统：注意力经济、营销、危机公关 | https://github.com/alchaincyf/sun-yuchen-perspective |

Network accessline 73

| zhang-yiming-skill | 张一鸣的认知操作系统：产品、组织、全球化、延迟满足 | https://github.com/alchaincyf/zhang-yiming-skill |

Network accessline 74

| taleb-skill | 塔勒布的认知操作系统：尾部风险、反脆弱、质疑主流叙事 | https://github.com/alchaincyf/taleb-skill |

Network accessline 75

| mrbeast-skill | MrBeast 的内容创造操作系统：视频标题/封面/钩子/留存 | https://github.com/alchaincyf/mrbeast-skill |

Network accessline 76

| paul-graham-skill | Paul Graham 的认知操作系统：创业、写作、做用户真正要的东西 | https://github.com/alchaincyf/paul-graham-skill |

Network accessline 77

| ilya-sutskever-skill | Ilya Sutskever 的认知操作系统：深度学习直觉、Scaling、AI 本质 | https://github.com/alchaincyf/ilya-sutskever-skill |

Network accessline 78

| huashu-art-motion | 艺术与解说动画：35种艺术风格、9种解说动画语法，拆解复刻、口播驱动整片，用代码让画动起来 | https://github.com/alchaincyf/huashu-art-motion |

Network accessline 79

| huashu-flash | 闪电.skill：照Anthropic两周把claude.ai提速3倍的方法给网站或App提速，先量基线、再证指标、逐步优化，用棘轮锁住只许变好 | https://github.com/alchaincyf/huashu-flash |

Network accessline 80

| mcstomach | 麦门胃：读麦当劳历史订单，带证据提炼口味规则，确认后生成可携带的个人「胃」 | https://github.com/alchaincyf/mcstomach |

Network accessline 86

- 公众号：「花叔」（在微信里搜「花叔」） - B站：花叔v：https://space.bilibili.com/14097567

Network accessline 87

- B站：花叔v：https://space.bilibili.com/14097567

Network accessline 88

- 小红书：花叔：https://www.xiaohongshu.com/user/profile/5abc6f17e8ac2b109179dfdf

Network accessline 89

- 个人网站：https://www.huasheng.ai/

Network accessline 90
```
- X：https://x.com/AlchainHust
```

Network accessline 91

- YouTube：https://www.youtube.com/@Alchain

Network accessline 92

- 更多开源项目：https://github.com/alchaincyf?tab=repositories

`references/html-to-md-cookbook.md`

Network accessline 34

python scripts/html_to_md.py "https://example.com/article" -o article.md

Network accessline 44

# 不要正文提取，保留全部HTML python scripts/html_to_md.py "https://example.com/data" --no-extract

Network accessline 45

python scripts/html_to_md.py "https://example.com/data" --no-extract

Network accessline 129

# 默认 User-Agent + utf-8 解码（脚本已实现） # 如果对方服务器用 GBK/GB2312： python scripts/html_to_md.py "https://example.cn/page" --user-agent "Mozilla/5.0"

Network accessline 130

# 如果对方服务器用 GBK/GB2312： python scripts/html_to_md.py "https://example.cn/page" --user-agent "Mozilla/5.0" # 然后用 iconv 重编码（如必要）

Network accessline 131

python scripts/html_to_md.py "https://example.cn/page" --user-agent "Mozilla/5.0"

Network accessline 175

# 把已发布的公众号文章存回项目源 python scripts/html_to_md.py "https://mp.weixin.qq.com/s/xxx" -o archive.md

Network accessline 176

python scripts/html_to_md.py "https://mp.weixin.qq.com/s/xxx" -o archive.md

Network accessline 180

# 把朋友发的网页链接转成 md 笔记 python scripts/html_to_md.py "https://blog.example.com/article" -o note.md

Network accessline 181

python scripts/html_to_md.py "https://blog.example.com/article" -o note.md

`references/markitdown-cookbook.md`

Access to secretsline 35
```
[Credential-related source omitted]
```

Network accessline 38

# 挂 Azure Document Intelligence（高保真扫描件） python scripts/any_to_md.py file.pdf \   --azure-doc-intel "https://xxx.cognitiveservices.azure.com/"

Network accessline 39

python scripts/any_to_md.py file.pdf    --azure-doc-intel "https://xxx.cognitiveservices.azure.com/"

Network accessline 40

--azure-doc-intel "https://xxx.cognitiveservices.azure.com/"

Access to secretsline 104
```
[Credential-related source omitted]
```

Network accessline 125

python scripts/any_to_md.py "https://www.youtube.com/watch?v=xxx" -o video.md

Network accessline 162

# YouTube视频 → md脚本 → 文章博客 python scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o talk.md

Network accessline 163

python scripts/any_to_md.py "https://youtube.com/watch?v=xxx" -o talk.md

`scripts/any_to_md.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 53
```
[Credential-related source omitted]
```
Access to secretsline 57
```
[Credential-related source omitted]
```
Access to secretsline 62
```
[Credential-related source omitted]
```
Access to secretsline 91
```
[Credential-related source omitted]
```
Access to secretsline 93
```
[Credential-related source omitted]
```

`scripts/html_to_md.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 97

def fetch_url(url: str, ua: str) -> str:     import urllib.request     req = urllib.request.Request(url, headers={"User-Agent": ua})

Network accessline 98

import urllib.request     req = urllib.request.Request(url, headers={"User-Agent": ua})     with urllib.request.urlopen(req, timeout=30) as resp:  # noqa: S310 — explicit user input

Network accessline 99

req = urllib.request.Request(url, headers={"User-Agent": ua})

Network accessline 100

with urllib.request.urlopen(req, timeout=30) as resp:  # noqa: S310 — explicit user input

`scripts/md_to_docx.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/md_to_html.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 37

Or download from https://pandoc.org/installing.html

`templates/article/template.html5`

Network accessline 14

<!-- Web fonts: Newsreader (display+body serif) + IBM Plex Sans (UI) + JetBrains Mono (code) -->   <link rel="preconnect" href="https://fonts.googleapis.com" />

Network accessline 15

<link rel="preconnect" href="https://fonts.googleapis.com" />

Network accessline 16

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />

Network accessline 17

<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Newsreader:ital,opsz,wght@0,6..72,400;0,6..72,500;0,6..72,600;0,6..72,700;1,6..72,400;1,6..72,500&family=IBM+Plex+Sans:wght@400;500;600&family=JetBrains+Mono:wght@400;500

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 15 facts

Network access in code of documentationREADME.md:199Low confidence
Network access in code of documentationREADME.md:204Low confidence
Network access in code of documentationREADME.md:207Low confidence
Network access in code of documentationREADME.md:214Low confidence
Network access in code of documentationREADME.md:215Low confidence
Network access in code of the SKILL.mdSKILL.md:116High confidence
Network access in code of the SKILL.mdSKILL.md:119High confidence
Network access in code of the SKILL.mdSKILL.md:211High confidence
Network access in code of the SKILL.mdSKILL.md:214High confidence
Network access in code of the SKILL.mdSKILL.md:463High confidence
Network access in code of the SKILL.mdSKILL.md:468High confidence
Network access in code of the SKILL.mdSKILL.md:471High confidence
Network access in code of the SKILL.mdSKILL.md:479High confidence
Network access in code of the SKILL.mdSKILL.md:480High confidence
Network access in code of the SKILL.mdSKILL.md:514High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![alchaincyf/huashu-md-html on hotskills](https://hotskills.dev/badge/alchaincyf-huashu-md-html.svg)](https://hotskills.dev/skill/alchaincyf-huashu-md-html/)

alchaincyf/huashu-md-html

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

huashu-md-html

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

.gitignore

README.md

SKILL.md

examples/input/md-vs-html.md

examples/output/article.html

examples/output/interactive.html

examples/output/reading.html

examples/output/report.html

examples/readme.html

references/about-author.md

references/html-to-md-cookbook.md

references/markitdown-cookbook.md

scripts/any_to_md.py

scripts/html_to_md.py

scripts/md_to_docx.py

scripts/md_to_html.py

templates/article/template.html5

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`.gitignore`

`README.md`

`SKILL.md`

`examples/input/md-vs-html.md`

`examples/output/article.html`

`examples/output/interactive.html`

`examples/output/reading.html`

`examples/output/report.html`

`examples/readme.html`

`references/about-author.md`

`references/html-to-md-cookbook.md`

`references/markitdown-cookbook.md`

`scripts/any_to_md.py`

`scripts/html_to_md.py`

`scripts/md_to_docx.py`

`scripts/md_to_html.py`

`templates/article/template.html5`