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.
npx skills add phanghonghao/THU-Awesome-Skills --skill html2mdgit clone --depth 1 https://github.com/phanghonghao/THU-Awesome-SkillsWrote 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.
[](https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/html2md)<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.
<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>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 | $0.00059 | $0.00761 |
| Sonnet 5 | $0.00024 | $0.00304 |
| Haiku 4.5 | $0.00012 | $0.00152 |
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 9d ago.
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.
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 — Titleheaders. - Huge embedded HTML — decks saved as single
.htmlwith every image and video inlined as base64 (often 5–50 MB).markitdownand 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 —
markitdownhangs 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
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.
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.
- 9d ago First seen · 103 lines · 0 tokens per session scan A 68b0e6eab2be
html2md is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,522 once invoked, about $0.0006 per session on Opus 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.