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 Ethan2409/PaperFlow --skill paper-readergit clone --depth 1 https://github.com/Ethan2409/PaperFlowWrote 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/ethan2409/paperflow/paper-reader)<a href="https://agentmods.dev/skills/ethan2409/paperflow/paper-reader"><img src="https://agentmods.dev/badge/skills/ethan2409/paperflow/paper-reader/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/ethan2409/paperflow/paper-reader"><img src="https://agentmods.dev/badge/skills/ethan2409/paperflow/paper-reader.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 | $0.00069 | $0.03637 |
| Opus 5.5 | $0.00028 | $0.01455 |
| Sonnet 5.5 | $0.00014 | $0.00727 |
| Haiku 4.5 | $0.00007 | $0.00364 |
Grade A, and why
paper-reader 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 1mo 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Reader: 文献精读与认知重构
读论文不是做摘要，是猎取思想。本Skill把PDF论文拆解成「不懂这个领域的聪明人也能看懂并复述」的认知框架，最终输出带图片的结构化HTML精读笔记。
前置步骤：读取配置
开始前先读取项目根目录下的 config.yaml（如不存在则读取 config.example.yaml 并提示用户复制修改）。从配置中获取：
paths.python_exe— Python 解释器路径literature.pdf_dir— PDF 论文存放目录（按 W{周号}/ 子目录组织）literature.html_output_dir— 精读 HTML 输出目录（按 W{周号}/ 子目录组织）
路径约定
| 用途 | 路径 | 说明 |
|---|---|---|
| PDF输入 | {literature.pdf_dir}/W{周号}/ |
按ISO周号组织，如 W24。从 config.yaml 读取 pdf_dir |
| HTML输出 | {literature.html_output_dir}/W{周号}/ |
自动创建对应周目录。从 config.yaml 读取 |
| 图片资源 | {输出目录}/{论文名}_assets/ |
与HTML同目录下的assets子目录 |
| 提取工具 | <SKILL_DIR>/assets/extract_figures.py |
PDF文字+图片提取脚本 |
周号规则：默认使用当前ISO周号（python -c "import datetime; print(datetime.date.today().isocalendar()[1])"）。用户可指定周号，如"处理W19的所有论文"。
路径说明：所有路径通过项目根目录的
config.yaml集中配置。安装后请复制config.example.yaml为config.yaml并修改其中的路径为你本机的实际路径。详见项目 README.md 的"安装与配置"章节。
触发条件
用户消息包含以下任一关键词时触发：
- "精读论文" / "文献精读" / "paper reader" / "paper reading"
- "读这篇论文" / "解析文献" / "拆解这篇文献"
- "处理本周文献" / "处理W{数字}的论文"
工作流（严格按此顺序执行）
Phase 1: 确定范围并扫描
-
确定周号：
- 若用户未指定，用
python -c "import datetime; print(datetime.date.today().isocalendar()[1])"获取当前周 - 格式化为
W{周号}（如W24）
- 若用户未指定，用
-
扫描PDF：
- 用
ls或Get-ChildItem列出{literature.pdf_dir}/W{周号}/*.pdf - 若无PDF文件，告知用户并结束
- 向用户展示待处理清单，请求确认后再继续
- 用
-
创建输出目录：
mkdir -p "{literature.html_output_dir}/W{周号}"
Phase 2: 逐篇处理循环
对每个PDF文件，按以下子步骤执行：
2a. 提取文字 + 图片
运行提取脚本：
"{python_exe}" \
"<SKILL_DIR>/assets/extract_figures.py" \
--pdf "{literature.pdf_dir}/W{周号}/{论文文件名}.pdf" \
--output-dir "{literature.html_output_dir}/W{周号}/{论文名}_assets"
脚本输出：
{论文名}_meta.json— 元数据（full_text, figures列表）- 提取的图片文件（
fig_1.png,fig_2_rendered.png等）
读取 _meta.json 获取 full_text 和 figures 信息。
扫描版PDF检测（必须执行）：读取 _meta.json 后，检查 text_length。如果 text_length < 500（意味着几乎所有页面都无文字层，是扫描图片版PDF），立即停止处理该篇，告知用户：
"这篇「{论文名}」是扫描图片版PDF，fitz 无法提取文字（仅 {text_length} 字符）。请替换为文字版PDF后重试。"
- 跳过该篇，继续处理列表中下一篇
- 严禁尝试OCR、渲染页面截图等任何降级方案——这些不可靠且浪费时间
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.
- 1mo ago First seen · 326 lines · 69 tokens per session scan A d477c8567eea
paper-reader is a skill published in the GitHub repository Ethan2409/PaperFlow (12 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 3,637 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
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.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…