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 hk011/yanxi-paper-note --skill qwenpaw-skillgit clone --depth 1 https://github.com/hk011/yanxi-paper-noteWrote 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/hk011/yanxi-paper-note/qwenpaw-skill)<a href="https://agentmods.dev/skills/hk011/yanxi-paper-note/qwenpaw-skill"><img src="https://agentmods.dev/badge/skills/hk011/yanxi-paper-note/qwenpaw-skill/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/hk011/yanxi-paper-note/qwenpaw-skill"><img src="https://agentmods.dev/badge/skills/hk011/yanxi-paper-note/qwenpaw-skill.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 | $0.00119 | $0.11814 |
| Opus 5 | $0.00060 | $0.05907 |
| Sonnet 5 | $0.00024 | $0.02363 |
| Haiku 4.5 | $0.00012 | $0.01181 |
Grade A, and why
yanxi 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 12d 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 — 741 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研析（Yanxi）论文解读 Skill
AI 驱动的英文学术论文中文解读流水线：PDF 解析 → 结构化 → 三阶段笔记（联网 + 配图）→ PDF 交付。
Core Pipeline: PDF（PaddleOCR → 备选 Kreuzberg）→ 三阶段笔记 → note.md → note.pdf → **交付前自检 PASS** → send_file_to_user
[!CAUTION]
🚨 全局执行纪律（MANDATORY）
- 三阶段笔记是质量核心 — 必须执行：阶段一大纲 → 阶段二六章 → 阶段三综合终稿；禁止跳过阶段一直接写终稿，禁止用单段摘要代替完整流水线
- 只裁 Figure、禁止整页当图 —
images/每张须为单个 Figure/Table 图表区域（仅图表本身，不含整页）；禁止整页 PDF 截图充当原图；裁剪边界须含图内全部文字标签与矢量元素（见 §1.3.4）；插图自检对照原论文source.pdf（见「术语」）- 图片必须对齐 Figure — 禁止匿名批量抽图（如
extracted image 1）；每张图须绑定正文Figure N图题；catalog 格式与 Web 端一致；校验通过后再写笔记- PDF 提取：PaddleOCR 首选 — 论文内容首选 PaddleOCR 解析；安装失败或运行超时时改 Kreuzberg；无论哪条路径都须 §1.3.4 裁剪规范；勿因装包调试而省略三阶段
- NO YANXI BACKEND — 不要求
YANXI_API_KEY；笔记结构与 Prompt 与研析 Web 端note_pipeline一致- UTF-8 ONLY — 所有
.md/.txt必须用 UTF-8 读写；Windows 禁止Out-File（默认 UTF-16/GBK）、禁止pandoc无 CJK 引擎直接转 PDF（中文会乱码）- PDF DELIVERY ONLY — 用户最终 MUST 收到
{论文简称}_yanxi_note.pdf- SELF-CHECK BEFORE DELIVERY — PDF 生成后、
send_file_to_user前 MUST 自检；必查两项图片问题：① 是否把整页当 Figure 图；② Figure 是否裁切不全（边缘信息丢失）；存在则按 Step 7 自行修复后再交付，禁止带病交付- NO FABRICATION — 禁止编造图片路径、URL、引用来源
- MODEL LOCK — 三阶段笔记全程同一 LLM：优先豆包 Seed（若已接入），否则当前会话模型；禁止切换到 Agent 上其他模型
[!IMPORTANT]
定位
本 Skill 提供研析笔记生成方法论（流程 + Prompt 规范）。PDF 内容首选 PaddleOCR，失败或超时改 Kreuzberg；可选 Agent Reach 增强联网。
术语（Agent 必读）
| 名称 | 含义 | 如何确定 |
|---|---|---|
source.pdf |
用户提供的待解读原论文 PDF（英文论文；Skill 的唯一输入 PDF） | 用户消息中的路径/附件；或 Agent 复制到工作目录后命名为 paper_work/source.pdf |
parsed.md |
从原论文提取的结构化 Markdown（中间产物） | Step 1 产出 |
note.md |
三阶段生成的中文解读笔记（中间产物） | Step 5 产出 |
note.pdf / {简称}_yanxi_note.pdf |
交付给用户的中文解读笔记 PDF（输出，不是 source.pdf） |
Step 6 产出 |
source.pdf不是笔记 PDF。全文凡写「对照source.pdf」「从source.pdf提取 Figure」，均指用户给的那篇原论文，不是note.pdf、不是 Web 端笔记、不是 Agent 生成的任何文件。
本 Skill 使用的组件
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.
- 12d ago First seen · 741 lines · 119 tokens per session scan A f5a7dac8bbb3
yanxi is a skill published in the GitHub repository hk011/yanxi-paper-note (25 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 11,814 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 2026-08-30.
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.