By hirokita117
Generate self-contained HTML explainer bundles from documents, PRs, READMEs, or specs. The plugin analyzes content to produce structured YAML (core.yaml, view.yaml, quiz.yaml) and builds an offline HTML bundle with light/dark theme, view switcher, and interactive quiz.
turn core.yaml + view.yaml (the explainer's meaning + presentation strategy) — plus quiz.yaml when present — into a self-contained html bundle that helps users understand documents, repositories, pull requests, design notes, or specifications. the bundle has a light/dark shell whose right pane switches between multiple iframe view documents, and copyable prompt templates that ask a local-file-reading ai to add another switchable view. an interactive quiz tab (comprehension check with instant grading) is added by default unless the user explicitly declines. use when the user has (or wants) a core.yaml/view.yaml pair and wants a visual html explainer, or wants to add a new representation (table, worktree, cards, faq, beginner, engineer, pdm view, quiz, …) to an existing bundle. produce the yaml first with the generate-explainer-yaml skill.
analyze a document, repository summary, pull request, README, design note, or specification and produce (or refine) the intermediate yaml files that drive the explainer pipeline — core.yaml (the semantic structure / meaning), view.yaml (the presentation strategy for a particular reader), and, by default, quiz.yaml (comprehension-check questions derived from core.yaml; skipped only when the user explicitly declines a quiz). use when the user wants to capture what a target means and how to show it before generating an html explainer, or wants to edit/reshape an existing core.yaml / view.yaml / quiz.yaml. the generate-explainer-html skill then turns these yaml files into a switchable, light/dark html bundle.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin with two skills that turn an understanding target — a document, repository summary, pull request / diff, README, design note, or specification — into an offline HTML explainer bundle tailored to how a particular reader understands things.
The two skills split the work cleanly:
| skill | role | output |
|---|---|---|
generate-explainer-yaml | Gen YAML | core.yaml (meaning) + view.yaml (presentation strategy) + quiz.yaml (comprehension quiz, default) |
generate-explainer-html | Gen HTML | a bundle: a light/dark shell + switchable iframe views (incl. a quiz tab) |
Input (doc / repo / PR / README / design note / spec)
↓ generate-explainer-yaml
core.yaml (what it MEANS — concepts, relations, importance, difficulty, sources)
view.yaml (how to SHOW it to this reader — audience, forms, emphasis)
quiz.yaml (how to CHECK understanding — questions, answers, explanations)
↓ generate-explainer-html
HTML bundle: index.html (light/dark shell + view switcher + add-a-view prompts)
+ views/NN-<id>.html (one switchable iframe view each, incl. a quiz tab)
Quizzes are generated by default. Both the quiz.yaml and the interactive quiz tab
(answer → instant grading → explanation, adapted to the reader and per-item difficulty)
are produced unless you explicitly say you don't want a quiz in your prompt. The score
lives only in the page — reloading resets it (the bundle stores nothing by design).
1. Install the plugin (run these inside Claude Code):
/plugin marketplace add hirokita117/yaml-to-html-skill
/plugin install yaml-to-html@yaml-to-html-skill
2. Ask for an explainer. A single prompt runs both skills in the right order —
generate-explainer-yaml first (writes core.yaml + view.yaml), then
generate-explainer-html (reads that YAML by absolute path and builds the HTML bundle).
Paste a document / repo summary / PR diff / README / design note, or point at a path.
English
Build me an offline HTML explainer bundle for this PR, aimed at an engineer reviewing it.
First use generate-explainer-yaml to produce core.yaml + view.yaml, then use
generate-explainer-html to turn that YAML (by absolute path) into a light/dark switchable
view bundle in ./explainer-bundle.
--- target ---
<paste the PR / document / repo summary / README / design note here, or give a path>
Japanese
この PR を、レビューするエンジニア向けに分かりやすく説明する HTML バンドルを作ってください。
まず generate-explainer-yaml で core.yaml と view.yaml を生成し、
続けて generate-explainer-html でその YAML(絶対パス)から
ライト/ダーク切り替え付きのビュー HTML バンドルを ./explainer-bundle に組み立ててください。
--- 対象 ---
<ここに PR / ドキュメント / リポジトリ概要 / README / 設計メモを貼る、またはパスを指定>
3. Open it. Open ./explainer-bundle/index.html in Firefox over file://, or serve
the folder for Chrome/Edge (cd explainer-bundle && python3 -m http.server). See
Opening the bundle for why.
Prefer to drive it step by step? Generate just the YAML first ("
generate-explainer-yaml で core.yaml と view.yaml を作って"), review the two files, then hand their absolute paths togenerate-explainer-html.
The HTML output is a bundle (a directory), not a single file:
index.html) with a theme toggle (light by default).views/. Views are additive — ask for a "table"
view next to your "beginner" view and you get a second tab, not a replacement.sandbox="allow-scripts", no allow-same-origin)
and cannot reach the parent page.The shell loads each view via a local relative src (e.g. views/01-engineer.html) —
a local file read, not a network read. (A remote src stays forbidden.)
Two intermediate representations sit between the input and the HTML, produced by
generate-explainer-yaml:
npx claudepluginhub hirokita117/yaml-to-html-skill --plugin yaml-to-htmlリポジトリやドキュメントを、固定ルールの DSL(repo-map v1 / document-map v1)を正本として地図化する Agent Skills 集。DSL 生成(repo-map-notation / document-map-notation)と決定的レンダリング(notation-render)を分離し、共通土台(notation-core)で支える。生成済み HTML をローカル Claude Code とつなぐ対話ビューア(repo-map-interactive-viewer)も同梱。
Prompt-native interactive HTML docs — open-source community implementation of Jesse Pollak's bdocs idea. Generate self-contained HTML from a prompt, comment on text + artifacts, publish to your own Cloudflare Worker for free always-on sharing.
Generate beautiful HTML pages for diagrams, diff reviews, plan reviews, slides, and data tables
Generate reviewable HTML documents, serve previews, collect comments, and feed review outcomes back into agent workflows.
Create beautiful HTML presentations from markdown specs using a Poimandres-themed template
Hamsurang brand HTML presentation generator. Soft Modern design with light/dark themes, 14 slide types, 4-color code highlighting.
Turn any GitHub repo into a beautiful, art-directed explainer site that takes a stranger from "I've never seen this" to "oh, I get why this matters — and I'm ready to use it." One Claude Code skill (the brain) reads the repo, builds a real RVF vector knowledge base, conceives a bespoke visual metaphor, authors the comprehension arc, generates raster + SVG visuals, assembles a responsive page on a shared design system, grades it on real pixels against a dual quality gate (>=95 on mobile and desktop), deploys it to its own URL, and ships a downloadable AI knowledge pack so the reader's AI gets it too. Pure, independently-testable tools do the mechanics; one BuildContext carries the work.