answer-me-with-html
Skill1 starsChanged 38 days agoMITView on GitHub
把一个知识点做成一页单文件 HTML 图解(抽象概念给类比、流程给步骤、算法给具体例子)。 只在用户明确要求「用图文讲一下 / 画个图 / 出一页 / 可视化讲解」时使用,不要主动附页。 本仓库里它有两个执行入口:命令行 `npx eyedot explain` 与网页端「一页图解」。
8 other projects use a version of this.
Adopted by
Most recently taken up by
- taixuann/development-spacetheir own version, first seen Nov 8, 2026
- Hoerire/Azurtheir own version, first seen Nov 8, 2026
- iasiv5/skillstheir own version, first seen Nov 1, 2026
- DawnMoon1542/agents-skillstheir own version, first seen Nov 1, 2026
- Simon-zj1/jev-examword for word, first seen Oct 15, 2026
- minuque/skillstheir own version, first seen Oct 15, 2026
Used with
Projects with it also use writing-for-agents, grill-with-docs and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillwriting-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
Also in 3 projects that use this
MicrosoftSkillgrill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Also in 3 projects that use this
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 3 projects that use this
- +1 more from microsoft
Other versions8 projects use a version of this.
Word for word · 1
- Simon-zj1/jev-exam★ 1100% same
Edited · 0
None found.
Wrote their own version · 7
- QingYunA/answer-me-with-html★ 6ksame name
- niki914/zafiro★ 346same name
- DawnMoon1542/agents-skills★ 8same name
- iasiv5/skills★ 3same name
- Hoerire/Azur★ 2same name
- taixuann/development-space★ 1same name
- minuque/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/eyedot.mdcCursor rule
- llms.txtllms.txt
- eyedotSkill
The file
Files
一页图解(answer-me-with-html)
这个 skill 在本仓库里的形态是能力,不是另一个 CLI:
生成逻辑写在 src/lib/explain/prompt.ts,
内容契约在 src/lib/explain/schema.ts,
渲染器在 src/lib/explain/render.ts,
清洗与沙箱写在 src/lib/security/html-sandbox.ts,
命令行入口是 eyedot explain,网页入口是材料页的「一页图解」。
原始形态是 Codex/Claude Code 里的 answer-me-with-html skill(自带 am 渲染器,带主题、面板与自动校验)。
这里保留它的内容规则,因为它要解决的是同一个问题:一页纸讲清一个概念,而不是把答案摊成流量。
什么时候产出一页
满足任意一条就值得出页:≥3 个相互关联的概念、有流程/协议/状态流转、有跨 ≥3 个维度的比较、有层级或时间演进。 否则用普通文字回答就够了——不要为了出页而出页。
只在用户要求时使用("用 HTML 讲一下"、"画个图"、"可视化讲解"、"没看懂,给我看一页"); 用户要纯文本时不要附页。
内容规则(提示词里已经写死,这里说明为什么)
- 模型只输出内容 JSON,HTML 由我们的渲染器生成(
kind取 prose / steps / flow / compare / code / callout)。 这样单文件自包含、离线可读、移动端不横向滚动都是代码保证的,不靠模型自觉。 - 先给结论:第一屏就说清「这是什么、为什么重要」,后面才是证据。
- 一个面板回答一个问题;超过 8 个面板就拆页或砍掉。
- 按信息的形状选讲法:抽象概念 → 类比 + 边界;流程 → 步骤或思维导图;代码 → 逐行注释;算法 → 先说要解决哪类问题,再用一个例子走一遍。
- 每个取自材料的说法标出处(引出原句的前 12 个字),模型补充的内容必须标「补充」—— 这和报告里「材料原文 / 模型补充」是同一套规矩,不能只在报告里守。
- 不编数据:没有真实数字就不要画刻度;示意数据要写明是示意。
- 一屏能读:正文不小于 16px,不固定宽度、不横向滚动,手机上也能看。
执行
# 命令行:材料和知识点进去,单文件 HTML 出来
npx eyedot explain --material notes.md --topic "注意力机制为什么需要缩放" --out explain.html网页端在材料页的「一页图解」:选知识点 → 生成 → 内嵌在 sandbox iframe 里看,也可以在新标签页打开保存。 两种入口共用同一套提示词与清洗,所以结果不会分叉。
安全前提(改这个 skill 时不要绕过)
- 材料是不可信输入:拼提示词前必须走
scanMaterial()的promptText。 - 模型产出是不可信输出:落库或写文件前必须走
sanitizeExplainerHtml(),页面再用EXPLAINER_CSP关进唯一源。 正则清洗做不到完备,所以真正的防线是 CSP 的sandbox——两层都要留。 - 平台额度调用要扣积分并记用量:走
assertPlatformCallAllowed()与recordChatUsage(),不要自己直连模型。
想要完整的 am 体验
原始 skill 自带排版引擎(主题、面板、视频、STE 校验)。需要那种效果时单独安装它:
npx skills add answer-me-with-html它负责「排版与呈现」,本仓库负责「内容从材料里来、出处可核对、消耗算得清」。两者不冲突。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

