html-artifact
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.
Target: Design & content creation. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- 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
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- wxxb789/hoa
- Source file
- skills/html-artifact/SKILL.md
- Fixed revision
- beb1eca66d8fed7c3942dc3ef50990bf37837706
Requirements
- Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.
A small first task
先阅读原作者说明,再决定是否在自己的 AI 工具中使用。
Instructions for your AI tool
- Claude Desktop: resource-specific guide not available yet
- Claude Code: resource-specific guide not available yet
- Cursor: resource-specific guide not available yet
- Codex: resource-specific guide not available yet
Author documentation is not live verification by this site. Without evidence, we do not mark a resource as compatible, safe or free.
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: wxxb789/hoa · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-09T20:02:15.432Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.