A converter that turns HTML into clean Markdown, with special handling for slide decks and very large files containing embedded images or videos.

Use it to convert slide-based HTML into one Markdown section per slide, extract deck text for review, or process oversized base64-heavy HTML files.

It preserves the structure of slide presentations and avoids wasting time processing large embedded data that is not useful as text.

html2md — Skill for Claude Code and Codex by phanghonghao

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add phanghonghao/THU-Awesome-Skills --skill html2md

Clone the repo

git clone --depth 1 https://github.com/phanghonghao/THU-Awesome-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/html2md/github.svg)](https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/html2md)

Your own site

<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/html2md"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/html2md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/html2md"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/html2md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,522 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00118	$0.01522
Opus 5.5	$0.00047	$0.00609
Sonnet 5.5	$0.00024	$0.00304
Haiku 4.5	$0.00012	$0.00152

Measured 2mo ago against content hash 68b0e6eab2be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

html2md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (html2md.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/html2md/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

html2md — HTML → Markdown (deck-aware, base64-safe)

A stdlib-only converter (html2md.py) tuned for two cases generic converters choke on:

Slide decks — a .slide-per-page HTML presentation. A normal converter flattens it into one wall of text; this one keeps the slide structure and emits ## Slide NN — Title headers.
Huge embedded HTML — decks saved as single .html with every image and video inlined as base64 (often 5–50 MB). markitdown and friends spend minutes decoding megabytes of base64 into useless inline blobs; this strips the data URIs first, then parses.

When to Use

User mentions: html2md, /html2md, "html to md", "html→md", "把 deck 转成 markdown", "deck 转 md"
You have a slide-style HTML deck (each slide is a <div class="slide"> / <section class="slide">) and want structured per-slide Markdown
You have a bloated HTML file (multi-MB) that is mostly base64 — markitdown hangs or produces garbage
You want to extract the text content of a deck so an LLM can critique / revise it

When NOT to Use (use a different skill instead)

Need	Better skill
Generic non-deck HTML page	`markitdown` (`/markitdown`) — broad format support
DOCX with math	`/word2md` (correct OMML→LaTeX)
PDF → Markdown	`/any2md --pdf-backend pymupdf` or `/pdf-reader`
Want to render a deck to PDF (md/html → pdf)	`/html2pdf`
A whole web page from a URL	the `web_reader` MCP tool

How to Use

# Convert, write to a sibling .md file
PYTHONIOENCODING=utf-8 python ~/.claude/skills/html2md/html2md.py "deck.html" "deck.md"

# Convert, print to stdout
PYTHONIOENCODING=utf-8 python ~/.claude/skills/html2md/html2md.py "deck.html"

# Extract the base64 images/videos to disk and rewrite refs (instead of [IMAGE] placeholders)
PYTHONIOENCODING=utf-8 python ~/.claude/skills/html2md/html2md.py "deck.html" "deck.md" --extract-assets

# Drop [IMAGE]/[VIDEO] placeholders entirely (pure text)
PYTHONIOENCODING=utf-8 python ~/.claude/skills/html2md/html2md.py "deck.html" "deck.md" --no-assets

# Flat document — don't try to split slides
PYTHONIOENCODING=utf-8 python ~/.claude/skills/html2md/html2md.py "page.html" "page.md" --no-slides

Read the full file on GitHub · 103 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

html2md.py 21 KB runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 103 lines · 0 tokens per session scan A 68b0e6eab2be

Subscribe to this mod's changes

html2md is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 1,522 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents

html2md next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
html2mdphanghonghao/THU-Awesome-Skills	Skill	8	3mo ago	MIT	A	118	Claude Code, Codex
orbit-notionnexu-io/open-design	Skill	107k	today	Apache-2.0	A	117	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	yesterday	Apache-2.0	A	123	Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	48	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	68	Claude Code
report-to-pdfasgeirtj/system_prompts_leaks	Skill	71k	yesterday	CC0-1.0	A	17	Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks	Skill	71k	yesterday	CC0-1.0	A	54	Claude Code, Codex