Karpathy Output Evolution logo

Karpathy Output Evolution

Community
LearnPrompt
karpathy-output-evolution

Upgrade LLM outputs from plain text to structured, rendered formats like HTML, Marp slides, or interactive dashboards. Use this skill when the user wants better-formatted output, needs to convert notes into a presentation, wants HTML output from an LLM, needs slides from a document, or says "make this prettier", "render this", "output as HTML", "make slides from this", "structured output", "Marp", "better format". Based on Karpathy 19k-like HTML output post.

Overview

PublisherLearnPrompt
Repositoryandrej-karpathy-skills
Skill namekarpathy-output-evolution
Stars
118
Forks
18
Bundled files
Instructions only
LicenseMIT
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 LearnPrompt on GitHub. Read the source before you install it.

Installation

Install the Karpathy Output Evolution 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/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-output-evolution
  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/LearnPrompt/andrej-karpathy-skills.git /tmp/andrej-karpathy-skills
mkdir -p .claude/skills
cp -r /tmp/andrej-karpathy-skills/karpathy-output-evolution .claude/skills/karpathy-output-evolution
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Karpathy Output Evolution 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 Karpathy Output Evolution 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 Karpathy Output Evolution 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.

Skill 7: Output Evolution(输出形式进化)

Source: https://x.com/karpathy/status/2053872850101285137 "HTML output + human-AI I/O evolution" — ~19k likes

Core Principle

Text is the lowest form of output. Demand structure.

Karpathy's progression: Text → Markdown → HTML → Interactive → (future) Neural

Every LLM output can be upgraded. A wall of text becomes a rendered document. A list becomes a sortable table. An explanation becomes a slide deck. The information is the same — but legibility and retention multiply.

The Output Evolution Ladder

Level 1: Plain text          ← most common, least useful for complex info
Level 2: Markdown            ← better, but not rendered in most contexts  
Level 3: Self-contained HTML ← renders anywhere, no dependencies
Level 4: Interactive HTML    ← sortable tables, collapsible sections, search
Level 5: Marp slides         ← presentations, teaching, sharing
Level 6: Data viz            ← charts, graphs, dashboards

Default rule: Always request at least Level 3 for any output you'll reuse or share.

Prompt Templates by Output Type

HTML Document (Level 3)

[YOUR CONTENT REQUEST]

Output format: A single self-contained HTML file.
Requirements:
- All CSS inline or in a <style> block (no external dependencies)
- Clean, readable typography (use system fonts: -apple-system, sans-serif)
- Proper heading hierarchy (h1 → h2 → h3)
- Key terms in <strong>, code in <code> blocks
- A table of contents at the top if > 3 sections
- Light/readable color scheme (#f8f9fa background, #212529 text)

Start with <!DOCTYPE html> and end with </html>. Nothing else.

Marp Slides (Level 5)

[YOUR CONTENT REQUEST]

Output format: Marp markdown slide deck.
Requirements:
- Start with: ---\nmarp: true\ntheme: default\npaginate: true\n---
- Separate each slide with ---
- Max 5 bullet points per slide
- One key concept per slide
- Speaker notes after each slide (<!-- note: ... -->)
- First slide: title + author + date
- Last slide: "Key Takeaways" + 3-5 bullets

Total slides: [N] (default: one per major concept)

Interactive HTML Table (Level 4)

Convert this data to an interactive HTML table:

[DATA]

Requirements:
- Self-contained HTML (CSS + JS inline)
- Sortable columns (click header to sort)
- Search/filter box at top
- Alternating row colors
- Responsive (works on mobile)
- Export to CSV button (optional)

Include only standard browser APIs, no jQuery or external libraries.

Research Summary as HTML Report (Level 3-4)

[YOUR RESEARCH TOPIC OR NOTES]

Output: A self-contained HTML research report.
Structure:
1. Executive Summary (3 sentences)
2. Key Findings (bulleted, with confidence levels: HIGH/MED/LOW)  
3. Evidence (expandable sections, one per finding)
4. Open Questions
5. Sources (linked, with one-sentence descriptions)

Style: Clean academic report. Background #fff, readable font-size 16px, max-width 800px centered.

Visual Comparison (Level 4)

Compare these [OPTIONS/APPROACHES/TOOLS]:

[LIST OF THINGS TO COMPARE]
[CRITERIA TO COMPARE ON]

Output: Self-contained HTML comparison page with:
- Side-by-side card layout (CSS grid)
- Color-coded ratings (green/yellow/red) for each criterion
- Summary recommendation at top
- No external CSS frameworks

The Universal Upgrade Prompt

Apply to ANY existing text output to instantly improve it:

Take this content and upgrade it to a self-contained HTML document.

Content:
[PASTE ANY TEXT OR MARKDOWN]

Upgrade rules:
1. Structure the content with proper heading hierarchy
2. Make lists visually distinct (styled bullets or numbered lists)
3. Put any code in syntax-highlighted <pre><code> blocks
4. Add a reading time estimate at the top
5. Make it look like a well-designed blog post
6. Keep the content identical — only change the format

Output: complete HTML file, nothing else.

Output Format Selection Guide

Use CaseBest FormatCommand
Quick notesMarkdownDefault
Sharing with non-technicalHTML"output as HTML"
PresentationMarp"make slides"
Data comparisonHTML table"as comparison table"
Research summaryHTML report"as research report"
DocumentationMarkdown + ToC"with table of contents"
Learning materialMarp + speaker notes"as teaching slides"

Always Add This to Important Prompts

Output as a self-contained HTML file. No external dependencies.
Clean design. Renders directly in a browser.

Workflow

属于工作流:研究到发布(第3步)

位置上游下游
第3步(包装)karpathy-llm-wiki(知识沉淀后)karpathy-education-first(教学化输出)

完整链路:autoresearch → llm-wiki → output-evolution → education-first

Prompt Contract

text
Take this content: <RAW_CONTENT>. Choose the best output format from: Markdown table / Marp slides / self-contained HTML / interactive dashboard / diagram. Justify your choice in one sentence. Then produce the complete rendered-ready artifact. Requirements: self-contained (no external deps), renders correctly, structured for scanning not linear reading.

Verification Checklist

  • 输出格式匹配使用场景(分享→HTML,演示→Marp,分析→Dashboard)
  • 文件完全自包含(无外部 CDN/依赖)
  • 可以直接在浏览器中打开并正确渲染
  • 结构支持扫读(有标题、表格、分区),不是一坨文字
  • 移动端也能基本可读

Frequently asked questions

What does the Karpathy Output Evolution AI skill do?

Upgrade LLM outputs from plain text to structured, rendered formats like HTML, Marp slides, or interactive dashboards. Use this skill when the user wants better-formatted output, needs to convert notes into a presentation, wants HTML output from an LLM, needs slides from a document, or says "make this prettier", "render this", "output as HTML", "make slides from this", "structured output", "Marp", "better format". Based on Karpathy 19k-like HTML output post.

Why use Karpathy Output Evolution on TypingMind?

Because you install it once and use it with any model. Karpathy Output Evolution 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 Karpathy Output Evolution in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-output-evolution. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Karpathy Output Evolution?

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 Karpathy Output Evolution?

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

Is the Karpathy Output Evolution AI skill free?

Yes. It is published on GitHub by LearnPrompt under the MIT license. 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 👇