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 paper-html-onepagegit 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/paper-html-onepage)<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/paper-html-onepage"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/paper-html-onepage/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/paper-html-onepage"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/paper-html-onepage.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 | $0.00088 | $0.01756 |
| Opus 5 | $0.00044 | $0.00878 |
| Sonnet 5 | $0.00018 | $0.00351 |
| Haiku 4.5 | $0.00009 | $0.00176 |
Grade A, and why
paper-html-onepage scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
网络层带 requests -> curl 自动降级，配合 /web-search-fallback，MCP 失效（429/限流/不可用）时仍可用。 How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper to One-page HTML Skill
功能
- 输入关键词 / arXiv / PDF URL / 本地 PDF，自动获取论文
- 下载对应 PDF
- 按
pdf-reader同款方式提取全文（PyMuPDF） - 先生成完整全文 HTML（逐页文本，默认作为中间产物生成后删除）
- 再基于全文做一轮总结，生成单页 A4 风格 HTML（和 DreamDojo summary 类似的卡片化布局）
- 无论输入是
--query、--url还是外部--pdf <path>，默认都会在最终输出目录保留一份本地源 PDF，并尽量与主输出同名
网络与降级（不依赖 MCP）
本 skill 的全部网络操作（arXiv 检索、按 ID 取元数据、下载 PDF）都带 requests -> curl 自动降级，对应 /web-search-fallback 的 Route 1（arXiv API）和 Route 4（直接 curl 抓取/下载）。降级链：
- 优先用 Python
requests requests不可用 / 抛异常（被限流、429、代理或 MCP web 工具失效）-> 自动改用系统curlcurl也不可用 -> 打印[WARN]并退出
因此即使 requests 没装好、或 MCP web_search / webReader 返回 429 / Limit Exhausted，本 skill 仍能独立完成检索 + 下载 + 渲染，不会被 MCP 失效卡住。
也可把 /web-search-fallback 当前置：先用它的 Route 1/4 拿到 arXiv ID 或把 PDF 下到本地，再用 --pdf <path> 或 --url <url> 喂给本 skill。
使用方式
在任意目录执行（建议在你的项目目录）：
python "<LOCAL_USER>\.codex\skills\paper-html-onepage\scripts\paper_to_onepage_html.py" --query "DreamDojo world model" --out "<OUTPUT_DIR>\dreamdojo_onepage.html"
直接传论文 URL（arXiv abs/pdf 或任意 PDF 直链，推荐用于已知论文）：
python "<LOCAL_USER>\.codex\skills\paper-html-onepage\scripts\paper_to_onepage_html.py" --url "https://arxiv.org/pdf/2602.23843" --out "<OUTPUT_DIR>\papers\20_locomotion\omni_xtreme\OmniXtreme.html"
也可以不传 --out，脚本会自动从论文标题/关键词命名，优先提取类似 DreamDojo、DreamZero、AMP 这类关键词；如果没有明显关键词，再退回到标题前几项内容生成文件名。若关键词重名，脚本会自动补一个标题后缀避免覆盖旧文件。
对比模式（默认彩色简约单页，Method/Data 导向）：
python "<SKILL_ROOT>\scripts\paper_to_onepage_html.py" --compare --items "<INPUT_DIR>\DreamDojo_summary.html" "<INPUT_DIR>\DreamZero_summary.html" --out "<OUTPUT_DIR>\DreamDojo_vs_DreamZero_compare_colorful.html"
如果不传 --items，脚本会交互式询问文件路径（用 | 分隔），不需要硬编码。
可选参数：
--query "..."：按关键词检索 arXiv--url <url>：直接传论文 URL（arXiv abs/pdf 或直链 PDF），自动下载并生成 HTML；网络层带 curl 降级--pdf <path>：跳过检索/下载，直接读取本地 PDF 生成 HTML--max-pages 60：最多读取多少页（默认 80）--pick 1：检索结果中选择第几个（默认第 1 个）--keep-pdf：显式保留下载的 PDF；现在是默认行为，主要用于兼容旧命令--no-keep-pdf：不保留--url/--query模式下载下来的本地 PDF，恢复旧的临时文件行为--keep-fulltext-html：保留中间生成的*_fulltext.html（默认生成后删除）--reflection <path>：把本地 Markdown/TXT 读后感整理成一页反思页 HTML，尽量保留原内容，并自动嵌入 Markdown 图片--out <path>：显式指定输出路径；不传时自动按检测到的关键词/短标题命名--compare：进入多论文对比模式（2 篇或多篇）--items ...：对比模式下输入文件路径列表（支持 pdf/html/txt）--compare-style colorful|minimal：对比页风格（默认colorful）
What ships with it
2 files 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.
- 11d ago First seen · 119 lines · 88 tokens per session scan A 25dfba43c1b8
paper-html-onepage is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,756 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.