Garden Skills is an open-source collection of reusable instructions for AI coding agents such as Claude Code, Cursor, and Codex, covering tasks including web design, image generation, and turning source material into articles or presentations. Developers use the skills to guide agents through these workflows.
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 ConardLi/garden-skills --skill beautiful-articlegit clone --depth 1 https://github.com/ConardLi/garden-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/conardli/garden-skills/beautiful-article)<a href="https://agentmods.dev/skills/conardli/garden-skills/beautiful-article"><img src="https://agentmods.dev/badge/skills/conardli/garden-skills/beautiful-article/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/conardli/garden-skills/beautiful-article"><img src="https://agentmods.dev/badge/skills/conardli/garden-skills/beautiful-article.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00226 | $0.09021 |
| Opus 5 | $0.00113 | $0.04510 |
| Sonnet 5 | $0.00045 | $0.01804 |
| Haiku 4.5 | $0.00023 | $0.00902 |
Grade A, and why
beautiful-article 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 12d 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 — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beautiful Article
背景原则
AI 生成内容越复杂,输出媒介越重要。HTML 的价值在于同时提升信息密度、视觉清晰度、分享便利性和交互能力:表格、SVG、CSS、代码片段、可调控件、复制与导出按钮,可以让读者不只是“看完”,而是能比较、定位、调整、复查和继续使用。Beautiful Article 的目的,是把原本枯燥、线性、难以消化的文字材料,转换成视觉体验更漂亮、阅读节奏更清晰、也更容易审阅和分享的单文件网页文章。
边界(先判断要不要进这个 Skill)
- 最终主产物是 single HTML 文章,不是网页应用。
- 文章可以有
Raw自由层(任意 HTML / CSS / JS / React:交互、布局排版、动效、小工具、 按需的 SVG / canvas 图解),但必须服务阅读、解释、论证、节奏或审美。 - 不生成:后台、表单、拖拽工作台、完整 dashboard、产品原型、通用 Web App。
- 信息密度由用户确认;默认保留 100% 信息,生成长文式网页文章。
如果用户要的是应用而不是文章,停下来澄清,不要进入本 Skill。
工作流总览
Phase 0 Intake 判断是否进入本 Skill + 初步文章类型
▼
Phase 1 Source → Markdown URL/PDF/DOCX/MD/文本 → source.md + extraction-notes.md
└ 主 Agent 内联 5 条 checklist 自查(仅复杂/低置信源升级 SubAgent)
▼
Phase 2 Editorial Planning 一份 plan.md(Brief / Outline / Theme / Assets 四段)
└ 主 Agent 内联自查(无 SubAgent、无 review 文件)
▼
Phase 3 Plan Checkpoint ★Checkpoint 1 必须停。逐项确认 5 件事:文章类型(含标配保留比例)/ 主题 / 版式 / 配图模式 / 封面
▼
Phase 4 First Spread 首屏 + 第一节 + 一个代表性视觉块(脚手架在此创建)
└ First Spread Reviewer SubAgent(写 review/first-spread-review.md)
└ ★Checkpoint 2 必须停。逐项确认 2 件事:验收结论 / 开发模式 A/B
▼
Phase 5 Full Article Build 生成完整网页文章(默认单 Agent,超长可按 Section 隔离)
└ Section Reviewer SubAgent(以消息返回 pass/fail,无须写 review 文件)
▼
Phase 6 Final Review Editorial / Visual / Technical 三视角终审(写 review/final-review.md)
▼
Phase 7 Repair 最小切片修复,有修复才写 repair-log.md
▼
Phase 8 Delivery ★Checkpoint 3 必须停。逐项确认交付决策 → 交付 article.html + 简短编辑说明
工作区结构(脚手架创建;这些文件是 Skill 的长期记忆,不要只依赖聊天上下文记决策):
<workspace>/
source/ original.* source.md source.<lang>.md(需翻译时) extraction-notes.md
plan/ plan.md # 单一规划文件:Brief / Outline / Theme / Assets 四段
article/ Cover.tsx(默认) Article.tsx sections/ raw-blocks/ assets/ article.html(产物)
review/ first-spread-review.md final-review.md # 仅这两份是常规产物
source-review.md(仅复杂源) repair-log.md(仅有修复时)
index.html package.json vite.config.ts tsconfig*.json (构建工装)
What ships with it
57 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.
- assets/scaffold-template/.npmrc 37 B
- assets/scaffold-template/article/Article.tsx 2.7 KB
- assets/scaffold-template/article/Cover.tsx 7.5 KB
- assets/scaffold-template/article/main.tsx 1.1 KB
- assets/scaffold-template/article/sections/01-opening.tsx 1.3 KB
- assets/scaffold-template/index.html 755 B
- assets/scaffold-template/package.json 783 B
- assets/scaffold-template/tsconfig.json 512 B
- assets/scaffold-template/tsconfig.node.json 230 B
- assets/scaffold-template/vite.config.ts 614 B runs code
- manifest.json 733 B
- README.md 24 KB
- README.zh-CN.md 23 KB
- references/article-types.md 3.7 KB
- references/article-types/briefing.md 2.1 KB
- references/article-types/dialogue.md 2.1 KB
- references/article-types/essay.md 2.1 KB
- references/article-types/explainer.md 2.3 KB
- references/article-types/full-report.md 2.4 KB
- references/article-types/interactive-explainer.md 4.9 KB
- references/article-types/longform.md 2.3 KB
- references/article-types/review.md 2.3 KB
- references/article-types/tutorial.md 2.2 KB
- references/article-types/visual-essay.md 2.4 KB
- references/asset-policy.md 3.7 KB
- references/component-policy.md 5.4 KB
- references/cover.md 12 KB
- references/harness.md 2.1 KB
- references/html-output.md 1.9 KB
- references/information-density.md 3.2 KB
- references/layout.md 2.0 KB
- references/pdf-output.md 9.8 KB
- references/plan-template.md 5.7 KB
- references/raw-policy.md 4.4 KB
- references/repair-policy.md 1.2 KB
- references/review-checklist.md 7.1 KB
- references/scaffold.md 3.5 KB
- references/section-build.md 5.3 KB
- references/source-to-markdown.md 6.3 KB
- references/theme-selection.md 2.2 KB
- scripts/html-to-pdf.sh 6.2 KB runs code
- scripts/pdf-print-overrides.css 6.3 KB
- scripts/scaffold.sh 7.3 KB runs code
- scripts/source-to-markdown-markitdown.py 3.2 KB runs code
- scripts/source-to-markdown.py 5.9 KB runs code
- theme-profiles/andy.md 3.3 KB
- theme-profiles/bayer.md 3.1 KB
- theme-profiles/bodoni.md 3.2 KB
- theme-profiles/freddie.md 3.3 KB
- theme-profiles/fuller.md 3.2 KB
- theme-profiles/index.json 5.8 KB
- theme-profiles/knuth.md 3.5 KB
- theme-profiles/press.md 3.5 KB
- theme-profiles/shannon.md 3.7 KB
- theme-profiles/sottsass.md 3.3 KB
- theme-profiles/tufte.md 3.5 KB
- theme-profiles/vignelli.md 3.6 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.
- 12d ago First seen · 467 lines · 226 tokens per session scan A 0ca56194c1c7
beautiful-article is a skill published in the GitHub repository ConardLi/garden-skills (12,353 stars, last pushed 2mo ago), licensed MIT. It adds 226 tokens to every session and 9,021 once invoked, about $0.0011 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
personal-website
Generate a beautiful personal homepage (linktree-style) and publish it online for the user. Reads user info from /.clacky/agents/USER.md and AI info from /.clacky/agents/SOUL.md. Returns a public URL the user can share. Trigger on: "profile card", "homepage", "personal page", "generate my card", "make my card"…
winui-design
Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…
winui-wpf-migration
Migrate WPF applications to WinUI 3 — namespace replacement (System.Windows → Microsoft.UI.Xaml), control mapping (DataGrid→ListView, WrapPanel→ItemsRepeater, TabControl→TabView), threading (Dispatcher→DispatcherQueue), imaging (System.Drawing→BitmapImage), MVVM conversion to CommunityToolkit.Mvvm, and…
yida-canvas-custom-page
A development guide for creating custom pages in Yida, a business application platform, using React 18. It covers pages such as websites, dashboards, workspaces, lists, details, and portals inside YidaCodeCanvas.
yida-create-form-page
A procedure for creating or updating standard Yida forms, including their fields, layout, rules, and data connections. A form is a page where people enter or submit structured information.
yida-custom-page
A set of rules for building custom React-style pages on the Yida platform, a business application platform. It covers page structure, event handling, state, and Yida's JavaScript interface.