Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。

★ 6,354⑂ 428👁 11⑃ 271● 138▤ 21
JavaScriptMITCreated 2026-10-02answer-me-with-html.com/
Download: v0.5.11v0.5.11 ↓0.5.112026-11-05
+22
Daily
+227
Weekly
+3,266
Monthly
6,354
stars
428
forks
11
watchers
271
prs
138
issues
21
releases

README

Answer me with HTML

 Sponsored by Zapply


    


Explore Zapply's Chrome extension for autofilling job applications, dedicated job board featuring the latest openings, multiple profiles for different resumes and roles, and application tracking with streaks and commitment awards.


 
     
    


Answer me with HTML

  
 --


  An agent skill. Ask a hard question, get a page you can actually read instead of a wall of text.The model writes about 1/8 of the tokens it would need to hand-write the HTML.



  
  
  
  
  
  



  Website · Install · Examples · Videos · Always-on mode · Reference · 简体中文 · 日本語


Once installed, ask questions the way you always do:


 Explain the TCP three-way handshake
 Map out how the modules in this repo fit together
 Redis or Memcached for our cache?


The agent writes a short Markdown draft and hands it to the CLI that ships with the skill. About 50 ms later you have a page:

https://github.com/user-attachments/assets/d3063a28-5dfd-4c44-a562-be901c49b249

24-second demo. Turn the sound on for the music.

 Why not just ask for HTML?

You can. Models write decent HTML now. But most of what they write is not content. We counted the tokens in 9 pages the model wrote by hand, 4,893 tokens on average:

| Part of the page | Share | With this skill |
| :--- | ---: | :--- |
| SVG diagrams: coordinates and paths | 47% | The CLI writes it |
| CSS | 15% | The CLI writes it |
| HTML tags | 17% | The CLI writes it |
| Text | 21% | The model writes it, as Markdown |

With this skill the model writes only a Markdown draft. For the same questions that was 612 tokens on average, about 1/8 of the hand-written HTML. Less to write means less to wait for (3 topics × 3 runs, medians, Claude Sonnet 5.5, a plain Claude Code setup):

| | Ask for HTML directly | Answer me with HTML | |
| :--- | ---: | ---: | :--- |
| Tokens the model writes | 4,893 | 612 | 8× fewer |
| Time | 31 s | 12 s | 2.6× faster |


  


The same question, the same model, answered both ways. Both pages are usable.

The token counts are saved in bench/corpus/tokens.json, so node bench/corpus.mjs gives the same numbers every time. The pages themselves are a download. The bill drops less than the writing, about 15% here, because every turn also reads the system prompt, your question and the conversation, with or without the skill. See where the cost goes.

Explainer videos save even more: about 18× fewer output tokens and 12× faster in a small test.

 Install

You need Node.js 20 or newer. There is no npm install step. The CLI is bundled inside the skill. No Node.js yet? With the recommended install below, your agent asks you and then installs it.

 Let your agent install it (recommended)

Paste this into Claude Code, Codex, Cursor, OpenCode or any other agent:

 Install Answer me with HTML: read https://raw.githubusercontent.com/QingYunA/answer-me-with-html/main/INSTALL.md and follow it.

INSTALL.md is written for agents. It installs the plugin in Claude Code and the ski

Top issues

Discussions

Latest release

v0.5.11 v0.5.11 2026-11-05
Send a page to a chat app: am export

Discord, Telegram, Slack and WeChat show an .html file as source. am export turns a rendered page into files they show (350, 354):

bash
am export page.html --pdf page.pdf      A4, the page's own print rules
am export page.html --png out/          out/page-1.png, out/page-2.png ...


- --png renders at 1200 CSS px wide and 2x, hides the toolbar, the reply and remark controls and the new-version notice, and cuts the page into slices no taller than 1800 CSS px. A cut falls in a gap between panels.
- Exporting into the same folder again removes the -.png slic

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON