markdown-html-orchestrator

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: markdown-html-orchestrator
description: Use when a user wants to convert any markdown file in their Claude project into a single-file, lightly-interactive HTML — long-form documents (specs, plans, RFCs, reports, explainers), code reviews with diffs and severity-tagged annotations, or slide decks. Triggers on "convert this markdown to HTML", "make this an HTML file", "turn this into an interactive document", "render this report as HTML", "PR writeup as HTML", "slides from this markdown". Forks context to route to one of three converter sub-skills (md-document, md-review, md-slides) based on a deterministic doctype classifier, after the user has run the design-system onboarding once. Refuses if input is under 100 lines (per Shihipar — markdown still wins below the threshold) or design-system isn't onboarded. Distinct from Anthropic's official Playground plugin (which is interactive prompt-tuning controls with sliders/knobs/prompt-copy-back) and from marketing/landing/ (which is a landing-page generator).
context: fork
version: 2.10.3
author: Alireza Rezvani
license: MIT
tags: [markdown, html, converter, orchestrator, documentation, code-review, slides, design-system]
compatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]
---

# Markdown → HTML — Domain Orchestrator

Thariq Shihipar's argument (Claude Code HTML output essay, Medium 2026): **markdown collapses past 100 lines for agent-generated artifacts.** Long specs, code reviews, and architecture explainers lose density, hierarchy, and lightweight interaction the moment they exceed a screen of text. HTML restores all three — single-file, browser-native, shareable.

This orchestrator forks context, classifies the input markdown deterministically, routes to the right converter sub-skill, and returns a digest with the output path. Heavy intake (full markdown bodies, diffs, slide decks) stays in the forked context.

**Domain status (complete):** all five skills are live — orchestrator + `design-system` (onboarding + shared brand tokens) + the three converter sub-skills (`md-document`, `md-review`, `md-slides`). Always route conversions to the shipped converter's scripts; never hand-render HTML inline.

## When to invoke

| Symptom | Sub-skill |
|---|---|
| "Convert this RFC / spec / report / explainer to HTML" — long-form doc | `md-document` |
| "Turn this PR writeup / code review into HTML" — markdown with diff blocks | `md-review` |
| "Make a slide deck from this markdown" — `---` boundaries or H1 cadence | `md-slides` |

## Pre-flight gates (hard refusals)

1. **Below the 100-line threshold.** Markdown wins below 100 lines (Shihipar). The classifier prints `below_min_lines: true` and `route_explainer.py` refuses. Tell the user to keep their input as markdown.
2. **Design-system not onboarded.** If `~/.config/markdown-html/design-system.json` doesn't exist (or its `setup_completed_at` is null), refuse. Point the user at `python3 markdown-html/skills/design-system/scripts/onboard.py` (or `--defaults` for a zero-touch run).
3. **Unwritable save location.** `output_path_resolver.py` refuses if the configured `default_output_dir` (or `--out` override) isn't writable.

## Routing logic (deterministic)

Two-signal threshold pattern lifted from `research-ops/skills/research-ops-skills/SKILL.md`. Filename hint = 2 points; each content signal = 1 point. Silent-route allowed when winner ≥ 3 AND (runner-up = 0 OR winner ≥ 2× runner-up). Below threshold → one clarifying question with a recommended answer.

### Signal table

| Signal class | Filename hints | Content signals | Sub-skill |
|---|---|---|---|
| DOCUMENT | `report.md`, `*-doc.md`, `spec.md`, `rfc-*.md`, `*-analysis.md`, `*-explainer.md` | `## Table of Contents` (2), `^# `, `^## `, markdown table rows, `> [!NOTE]/[!TIP]/[!IMPORTANT]` callouts | `md-document` |
| REVIEW | `review.md`, `*-pr-*.md`, `*.diff.md`, `code-review*.md` | ` ```diff ` (2), `^[-+]{3} ` (2), `^@@` (2), `> [!BLOCKER]/[!MA