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 agentmods add skills/laborany/laborany/paper-explainernpx skills add laborany/laborany --skill paper-explainergit clone --depth 1 https://github.com/laborany/laboranyWrote 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/laborany/laborany/paper-explainer)<a href="https://agentmods.dev/skills/laborany/laborany/paper-explainer"><img src="https://agentmods.dev/badge/skills/laborany/laborany/paper-explainer.svg" alt="Measured on agentmods" 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 | $0.00116 | $0.01492 |
| Opus 5 | $0.00058 | $0.00746 |
| Sonnet 5 | $0.00023 | $0.00298 |
| Haiku 4.5 | $0.00012 | $0.00149 |
Grade A, and why
论文讲解助手 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 4d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
论文讲解助手
将复杂学术论文转化为结构化、易理解的知识文档。
工作流程
PDF输入 → 解析提取 → 深度分析 → HTML输出
Step 1: PDF解析
运行 scripts/parse_pdf.py 提取原始内容:
python scripts/parse_pdf.py <论文.pdf> -o parsed.json --image-dir ./images
输出结构:
{
"pages": [{"page_num": 1, "text": "...", "tables": [...]}],
"images": [{"page_num": 1, "image_index": 1, "path": "..."}]
}
Step 2: 内容分析
阅读解析结果，提取以下信息:
| 字段 | 来源 | 说明 |
|---|---|---|
| title | 首页顶部 | 论文标题 |
| authors | 标题下方 | 作者列表 |
| affiliations | 脚注/作者下 | 机构信息 |
| motivation | Abstract + Intro | 研究动机与问题 |
| method | Method章节 | 核心方法详解 |
| experiments | Experiments章节 | 实验设置与结果 |
分析要点 (详见 references/analysis_guide.md):
- 动机: 回答What/Why/Gap三问
- 方法: 分层讲解(直觉→架构→细节→数学)
- 公式: 提供符号表+直觉解释
- 实验: 批判性分析基线公平性
Step 2.5: 图片智能分类与嵌入
对提取的图片进行分类，识别其用途:
| 类型 | 特征 | 嵌入位置 |
|---|---|---|
| 框架图 | 展示整体架构/流程，通常较大，含模块和箭头 | method 开头 |
| 模块细节图 | 展示单个组件内部结构 | method 对应段落 |
| 实验曲线 | 折线图/柱状图，含坐标轴和图例 | experiments 对应分析处 |
| 可视化结果 | 热力图/注意力图/生成样本 | experiments 定性分析处 |
| 示意图 | 概念解释/对比图 | motivation 或 method |
| 其他 | Logo/装饰/无关图片 | 仅放附录或忽略 |
分类方法:
- 查看图片尺寸: 框架图通常宽度 > 高度，且尺寸较大
- 查看所在页码: 第1-2页多为示意图，Method章节多为架构图
- 结合论文正文中的 "Figure X" 引用，匹配图片与描述
- 分析图片内容: 含箭头/模块框的是架构图，含坐标轴的是实验图
嵌入策略:
- 框架图: 在 method 开头用
<figure>标签嵌入，配详细说明 - 实验图: 在 experiments 对应结论处嵌入，解释图中趋势
- 其他关键图: 根据论文引用位置，嵌入对应段落
Step 3: 生成HTML
构造分析结果JSON:
{
"title": "论文标题",
"authors": "作者1, 作者2",
"affiliations": "机构1; 机构2",
"motivation": "<p>HTML格式的动机分析</p>",
"method": "<p>HTML格式的方法讲解，支持$LaTeX$公式</p>",
"experiments": "<p>HTML格式的实验分析</p>",
"images": [...],
"embedded_images": {
"motivation": [{"index": 0, "caption": "图1说明", "position": "after_intro"}],
"method": [{"index": 1, "caption": "框架图说明", "position": "start"}],
"experiments": [{"index": 2, "caption": "实验结果图", "position": "inline"}]
}
}
embedded_images 字段说明:
index: 对应 images 数组中的索引caption: 图片说明文字position: 嵌入位置 (start/inline/end)
What ships with it
3 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.
- 4d ago First seen · 168 lines · 116 tokens per session scan A 6e7d44d85713
论文讲解助手 is a skill published in the GitHub repository laborany/laborany (80 stars, last pushed 3mo ago), licensed MIT. It adds 116 tokens to every session and 1,492 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
baoyu-comic
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
claude-coach
Personal coach that teaches users to become Claude power users. Use this skill the FIRST time a user asks to "learn Claude", "be a power user", "coach me", "teach me Claude tricks", "what can Claude do", "make me better at prompting", or any variation. After activation, also use it on EVERY subsequent turn to detect…
code-tour
Use when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Trigger for: create a tour, onboarding tour, architecture tour, PR review tour, explain how X works, vibe check, RCA tour, contributor guide, or any structured code walkthrough…
prototype-pattern
讲解通过 prototype 实现属性共享的原型模式。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…