Download PDFs for papers listed in a markdown roadmap file. Parses tables with columns 제목 / 저자 / 저널/학회 / 비고, then for each row uses Crossref to find a DOI, tries arXiv first, then resolves https://doi.org/{DOI} and parses the publisher landing page for the citation_pdf_url meta tag. Saves into a 'pdf/' folder next to the markdown file. Filenames follow {firstauthorlastname}_{firsttitleword}_{year}.pdf (e.g. kim_characterization_2026.pdf). Trigger when the user asks to download PDFs from a literature roadmap, fetch papers listed in a markdown file, or batch-download papers from a research-list .md. Also trigger on '/pdf_crawl <path>' or 'crawl PDFs from <path>'.
Translate a PDF document while preserving layout. Extracts text spans, applies rule-based medical dictionaries (lab results, ultrasound reports, PET-CT scans, immunohistochemistry reports), and rebuilds the PDF with translated text at original positions. Asks for clarification on unknown terms with surrounding context.
Markdown 转 PDF 工具，支持 Mermaid 和 PlantUML 图表自动渲染。触发场景：(1)用户需要将 Markdown 转换为 PDF，(2)用户提到 "md2pdf"、"markdown to pdf"，(3)用户需要生成包含图表的 PDF 文档，(4)用户需要导出文档为 PDF 格式。
深度分析 arXiv 论文、公开 PDF URL、本地 PDF、研究项目页、技术博客或普通网页，自动识别来源类型并生成带证据与图片的 Obsidian 笔记。Use when the user provides an arXiv ID/link、public PDF URL、company research page、blog URL、local PDF or existing note and asks for analysis, summary, evaluation, or knowledge-base capture.
Adds a searchable text layer to a scanned PDF with ocrmypdf. Installs the toolchain at runtime in ~18s. Use when a PDF's pages are images and the deliverable is a file to keep, grep, or hand to another tool: 'make this PDF searchable', 'OCR this scan', 'I can't select the text in this PDF', 'search across these scanned pages', 'the pdf skill returned nothing'. Handles non-English scans via tesseract language packs. NOT for charts, diagrams, handwriting, or slide layouts. Route those to transcribing-images.
Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing Data Analytics report, dashboard, or inline chart export into a PDF artifact.
Convert a PDF book into a reflowable EPUB (strip running headers/footers/watermarks, rebuild paragraphs, split chapters). Use when the user asks to 转 EPUB / PDF 转电子书 / convert PDF to EPUB / Calibre 效果不好 / 扫描件转 EPUB, or runs /pdf-to-epub.
Read, extract, create, merge, split, and manipulate PDF files. Use when the user asks to generate handout packs, extract tables from reports, create PDF exports, merge BookSummary chapters, fill forms, or work with any PDF content.
Interactive PDF viewer skill. Use when user wants to open, view, annotate, highlight, stamp, fill form fields, or sign a PDF with live visual feedback. Trigger phrases: "open this PDF", "show me this contract", "highlight the key terms", "help me fill out this form", "sign this", "stamp it APPROVED", "mark this CONFIDENTIAL", "add initials to each page", "walk me through this document". Also trigger when user provides a PDF path or arXiv URL alongside any visual/interactive intent. Do NOT trigger for pure summarization or text extraction (use native Read tool instead).
Audit a UBC (University of British Columbia) master's thesis or doctoral dissertation PDF for final post-defence submission to cIRcle. Use whenever a user asks to check or review a UBC thesis/dissertation, UBC Graduate and Postdoctoral Studies (G+PS) formatting, PDF margins, page numbering, front matter, committee pages, figures or tables, final filename and PDF preflight, cIRcle readiness, citation or bibliography metadata, or a revised-PDF regression review. Read-only by default; not for generic manuscript peer review or another university's formatting rules.
Professional PDF generation from markdown using Pandoc with Eisvogel template and EB Garamond fonts. Use when converting markdown to PDF, creating white papers, research documents, marketing materials, or technical documentation. Supports both English and Russian documents with professional typography and color-coded themes. Mobile-optimized layout (6x9) by default for Telegram bot context, desktop/print layout (A4) for other contexts.
Navigating delivery status read-only: reconciles planned scope (specs/roadmap/PRD) against implemented code for what's built vs left. Not for priority scoring (Rank) or AC conformance (Attest).
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
hhyy0401Skill
