Paper To Html logo

Paper To Html

Community
ysyecust
paper-to-html

Generate a self-contained, beautifully styled HTML analysis of an academic paper. Use when the user provides an arXiv link, paper URL, PDF, or asks to analyze a research paper. Produces a standalone HTML file with structured sections (Problem, Translation/Analogy, Architecture, Key Results, Verdict), embedded figures, and responsive design. Trigger words include 读论文, 分析论文, paper analysis, paper review.

Overview

Publisherysyecust
Repositorylecture-to-notes
Skill namepaper-to-html
Stars
292
Forks
29
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ysyecust on GitHub. Read the source before you install it.

Installation

Install the Paper To Html AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ysyecust/lecture-to-notes/tree/main/skills/paper-to-html
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ysyecust/lecture-to-notes.git /tmp/lecture-to-notes
mkdir -p .claude/skills
cp -r /tmp/lecture-to-notes/skills/paper-to-html .claude/skills/paper-to-html
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paper To Html in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Paper To Html on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Paper To Html is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Paper to HTML

Generate a self-contained HTML analysis of an academic paper. The output is a single .html file with embedded CSS — no external dependencies, ready to deploy or share.

Output Structure

The HTML analysis must follow this structure:

Header

  • Paper title (original)
  • Authors and affiliations
  • Source (arXiv ID, venue)
  • Tags (topic tags as colored badges)

Sections

  1. 问题 (Problem)

    • What problem does this paper solve?
    • Why is it hard? What existing approaches fall short?
    • Use plain language, no jargon in the first paragraph
  2. 翻译 (Translation / Analogy)

    • Explain the core idea using a real-world analogy
    • Make it accessible to a non-specialist
    • This is the most important section for readability
  3. 架构 (Architecture / Method)

    • Technical details of the proposed approach
    • Use .architecture code blocks for diagrams (ASCII art)
    • Use .concept cards for key definitions
    • Include paper figures when available
  4. 关键结果 (Key Results)

    • Performance numbers, benchmarks, comparisons
    • Use tables for quantitative results
    • Highlight surprising or noteworthy findings
  5. 评价 (Verdict)

    • Use .verdict box: one-sentence assessment
    • Strengths and limitations
    • Who should read this paper?
  6. 博导审稿 (PhD Supervisor Review)

    • Identity: Switch to a PhD supervisor who has mentored graduate students for 20 years in this exact research direction
    • Scene: A student brings you this paper in your office. You judge whether it's worth taking seriously
    • Tone: Plain language, like chatting with a student — not formal review language
    • Five evaluation axes (each gets a one-sentence assessment):
      • 选题眼光 (Topic Selection): Is this a real problem or a manufactured one?
      • 方法成熟度 (Method Maturity): Is this engineering polish or genuine methodological innovation?
      • 实验诚意 (Experimental Sincerity): Did they test on hard cases or cherry-pick easy ones?
      • 写作功力 (Writing Craft): Clear thinking or jargon smokescreen?
      • 影响力预判 (Impact Forecast): Will anyone cite this in 3 years?
    • Verdict: strong accept / weak accept / borderline / weak reject / strong reject + one-sentence justification
    • Use .supervisor CSS class (dark green left border, light green background)
  7. 一句话总结 (One-line Summary)

    • The elevator pitch version

Footer

  • Generation metadata
  • Link to original paper

Math Rendering

All HTML output MUST include KaTeX for LaTeX math rendering. Add these lines in <head>:

html
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.11/dist/katex.min.css">
<script defer src="https://cdn.jsdelivr.net/npm/katex@0.16.11/dist/katex.min.js"></script>
<script defer src="https://cdn.jsdelivr.net/npm/katex@0.16.11/dist/contrib/auto-render.min.js"
  onload="renderMathInElement(document.body,{delimiters:[{left:'$$',right:'$$',display:true},{left:'$',right:'$',display:false}]})"></script>

Use standard LaTeX delimiters in text:

  • $$...$$ for display math (centered, own line)
  • $...$ for inline math

Example: The complexity is $O(N_c^2)$ renders as proper math.

HTML Template

Use this CSS design system (warm stone palette, purple accent):

css
:root {
  --bg: #fafaf9;
  --fg: #1c1917;
  --muted: #78716c;
  --accent: #7c3aed;
  --accent-light: #ede9fe;
  --border: #e7e5e4;
  --code-bg: #f5f5f4;
  --verdict-bg: #fef3c7;
  --verdict-border: #f59e0b;
}

Key CSS classes:

  • .architecture — monospace code/diagram blocks
  • .concept — definition cards with labeled fields
  • .insight — purple left-border highlight blocks
  • .verdict — amber warning-style assessment box
  • .supervisor — dark green left-border review box (for 博导审稿)
  • .score-grid — 2-column grid for evaluation axes
  • .paper-figure — centered image with caption
  • .tag — purple badge for topic tags

Figure Handling

When paper figures are available (from PDF extraction or provided by user):

  1. Save figures to assets/<paper_id>/ directory
  2. Reference with relative paths: assets/<paper_id>/fig1.png
  3. Add descriptive figcaptions

File Naming Convention

<timestamp>--paper-<short-name>__paper.html

Example: 20260326T133200--paper-nonlinearsolve-jl__paper.html

Quality Requirements

  • Self-contained: Single HTML file with embedded CSS, no external dependencies
  • Responsive: Readable on mobile (max-width: 760px centered layout)
  • Chinese by default: All analysis text in Chinese, technical terms in original language
  • Accessible: Non-specialists should understand sections 1-2; specialists get value from 3-4
  • Honest: Don't oversell the paper. Use the verdict box for balanced assessment

Frequently asked questions

What does the Paper To Html AI skill do?

Generate a self-contained, beautifully styled HTML analysis of an academic paper. Use when the user provides an arXiv link, paper URL, PDF, or asks to analyze a research paper. Produces a standalone HTML file with structured sections (Problem, Translation/Analogy, Architecture, Key Results, Verdict), embedded figures, and responsive design. Trigger words include 读论文, 分析论文, paper analysis, paper review.

Why use Paper To Html on TypingMind?

Because you install it once and use it with any model. Paper To Html is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Paper To Html in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ysyecust/lecture-to-notes/tree/main/skills/paper-to-html. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Paper To Html?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Paper To Html?

As many as you like. As long as a model supports skills, you can use Paper To Html with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Paper To Html AI skill free?

It is published on GitHub by ysyecust. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇