#141141st of 149 in Skills, plugins and rules
answer-me-with-html
Agent skill that renders answers as one offline HTML page from Markdown
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- JavaScript
Missed the latest GitHub check; these facts may be older.
Overview
An agent skill with a bundled Node CLI (`am`). The model writes a short Markdown draft, and the CLI lays out panels, flow, sequence, ER and tree diagrams, tables and themes into a single HTML file. It can also build narrated explainer videos. It works with Claude Code, Codex, Cursor, OpenCode and others.
Who it is for: Coding-agent users who want readable pages with diagrams instead of long text
Strengths
- Model writes about 612 tokens vs 4,893 for hand-written HTML, per the README benchmark
- Each page is one HTML file with no CDN links or web fonts, so it opens offline
- On draft errors the CLI returns line number and a correct example for the agent to fix
- Installs as a Claude Code plugin or via `npx skills add`; no npm install step
Weaknesses
- Always-on mode is off by default and needs a rule added to your rules file
- MP4 video export needs ffmpeg
- Pages accumulate in ~/.answer-me-with-html/ until you run `am clean`
- Benchmark covers 3 topics on one model (Claude Sonnet 5.5); other setups unknown
What it needs
- no GPU
- Needs Node.js 20+, ffmpeg (optional, for MP4)
- Models: Claude Code, Codex, Cursor, OpenCode, Pi
Also in Skills, plugins and rules
See all 149| Rank | Project | Score |
|---|---|---|
| 1 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #4 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 94 out of 100 |
| #5 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |