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 5.5 | $0.00048 | $0.04726 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (26 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 11,814 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 2026-08-30.
yanxi compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| yanxihk011/yanxi-paper-note | Skill | 26 | 3mo ago | MIT | A | 119 | Claude Code, Codex |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| foundry-hosted-agent-validationmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 82 | Claude Code, Codex |
| skill-doc-deliverynyldn/claude-octopus | Skill | 4.4k | yesterday | MIT | A | 29 | Claude Code |
| meta-web-to-pdf-briefingopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 45 | Claude Code, Codex |
| paper-readerhuangkiki/dailypaper-skills | Skill | 1.3k | 4d ago | Apache-2.0 | A | 135 | Claude Code, Codex |
| chat-complex-documentsvellum-ai/vellum-assistant | Skill | 1.5k | 2d ago | MIT | A | 90 | Claude Code, Codex |