anything-to-html
PassAudited by ClawScan on May 10, 2026.
Overview
This instruction-only skill appears focused on creating polished single-file HTML deliverables, with minor notes about broad auto-use and optional CDN-loaded resources.
This looks safe to install if you want AI deliverables to default to polished HTML. Be aware it may choose HTML even for broad report/summary requests, and generated files may include external CDN resources for charts or fonts unless you ask for a fully offline, no-CDN version.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The user may receive an HTML file or HTML-formatted final answer when they expected Markdown or a normal text response.
The skill tells the agent to prefer this HTML-output workflow for a broad class of deliverable requests even when HTML was not explicitly requested.
都应该优先触发这个技能——即使用户没有明确说"HTML"，只要任务产物复杂到...
Use the skill when HTML is wanted; if the user asks for a specific format such as Markdown, PDF-ready text, or plain notes, honor that explicit format.
Opening a generated HTML file may contact external CDN/font providers and execute third-party chart or styling scripts if the generated document uses them.
The skill permits generated HTML to load external libraries and fonts from CDNs, which is disclosed and useful for charts/layout but introduces network and third-party dependency behavior.
以下库可以通过 `<script src="...">` 或 `<link href="...">` 引用... Tailwind... ECharts... Chart.js... D3... Google Fonts
Prefer inline CSS/SVG when possible, review generated HTML for external `<script>` or `<link>` tags before sharing, and avoid CDN use for offline or highly sensitive deliverables.