html-artifact
构建一个自包含的HTML文件——无需构建步骤、无依赖、无CDN——用于解释、规划、报告、评审、绘制图表、比较或制作供人阅读、分享或试用的原型。当交付物包含颜色、布局、图表、表格或交互,或用户要求提供制品、说明文档、计划文稿、图表或设计变体时使用。不适用于Markdown形式的笔记、仿照已知网站外观的品牌匹配,或生成式画布艺术。
机器翻译查看英文原文
Build one self-contained HTML file — no build step, no dependencies, no CDN — to explain, plan, report, review, diagram, compare, or prototype something a human should read, share, or poke at. Use when the deliverable has color, layout, diagrams, tables, or interaction, or when the user asks for an artifact, explainer, plan write-up, diagram, or design variants. Not for markdown-shaped notes, brand-matching a known site's look, or generative canvas art.
适用对象:设计与内容创作。自动收录 · 待核查。
原作者说明节选
从固定版本的 SKILL.md 提取,保留原文语言。以下内容属于作者说明,本站尚未验证安装、兼容或运行结果。
查看英文原文
原文涵盖的主题
- HTML Artifact Skill
- Scope — one mode-switched skill
- Reference files (load on demand)
- Templates
- Workflow
- Core principles
- Quick reference — mode → what to build
- Pitfalls
Produce a single self-contained .html file — no build step, no dependencies, no CDN — whenever the deliverable is something a human should read, share, or poke at: a concept explainer, an implementation plan, a status/incident report, a code-review walkthrough, a technical or educational diagram, a set of design variants, or a throwaway editor that exports its result back to you. HTML beats Markdown once a doc has color, layout, diagrams, tables, code, or interaction. It opens in any browser, shares as a link, stays readable past 100 lines, and can carry SVG diagrams and live controls Markdown can't. Default to an HTML artifact when the user says "make an HTML file/artifact", or asks you to explain how X works, write up a plan/PR/report, diagram something, compare options, or prototype an interaction — even when they don't say "HTML". Three overlapping diagram-ish skills were folded into this one for a concrete reason: they all emitted the same artifact — a single self-contained HTML file with inline CSS/SVG — and overlapped heavily (three "diagram" paths, two "compare variants" paths, no shared token system). One mode-switched skill removes the which-one-do-I-load ambiguity and gi
这里只展示节选,请以完整原文和当前要求为准。
- 来源仓库
- wxxb789/hoa
- 源文件
- skills/html-artifact/SKILL.md
- 固定版本
- beb1eca66d8fed7c3942dc3ef50990bf37837706
准备条件
- 本条仅收录原作者的技能元数据;请阅读完整说明,确认依赖、许可与使用条件。
第一件可以尝试的小事
先阅读原作者说明,再决定是否在自己的 AI 工具中使用。
对应 AI 工具说明
作者有说明不等于本站实机验证。没有证据时,不自动标为兼容、安全或免费。
来源与内容状态
本条为自动发现的元数据,尚未完成人工文档核查;适用性与运行结果待核查。
原作者:wxxb789/hoa · 原作者仓库元数据。文档核查:未核查。最近来源检查:2026-11-09T20:02:15.432Z。
分类由名称、说明与路径规则生成,分类不代表已核实适配。
许可与权利归属
MIT。第三方内容及版权归原作者,使用条件以原文为准。
许可原文 ↗本站没有因同步、复制或用户自报成功而将资源标为运行验证通过。
限制与注意事项
- 元数据收录不代表本站已经安装、适配、实测或进行安全审查。