One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
FkennedyFoxSkillFkennedyFox/claude-skills/skills/pdf-generator/SKILL.md
Generate pdf generator operations. Auto-activating skill for Business Automation. Triggers on: pdf generator, pdf generator Part of the Business Automation skill category. Use when working with pdf generator functionality. Trigger with phrases like "pdf generator", "pdf generator", "pdf".
NzettodessSkillNzettodess/Awesome-Agent-Skills/Skills/Reports/pdf-generator/SKILL.md
Generate pdf generator operations. Auto-activating skill for Business Automation. Triggers on: pdf generator, pdf generator Part of the Business Automation skill category. Use when working with pdf generator functionality. Trigger with phrases like "pdf generator", "pdf generator", "pdf".
ComPDFKitSkillComPDFKit/compdf-skills/skills/compdf-encryt-pdf-decrypt-pdf/SKILL.md
Encrypt PDFs with AES-128, AES-256, or RC4 options and decrypt authorized PDFs with ComPDF. Use for PDF passwords, permission controls, encryption, decryption, and document-access protection.
Tano73SkillTano73/agent-skills/skills/mineru-pdf-to-md/SKILL.md
Converte PDF e immagini in Markdown ad alta fedeltà usando MinerU con il modello VLM MinerU2.5-Pro (opendatalab/MinerU2.5-Pro-2604-1.2B), preservando layout, tabelle, formule ed estraendo le immagini. Usa SEMPRE questa skill quando l'utente vuole "convertire un PDF in Markdown", "estrarre il testo da un PDF", "parsare/leggere un PDF", "pdf to md", "OCR di un documento scansionato", "trasformare una scansione in testo", oppure quando nomina esplicitamente "MinerU", "MinerU2.5", "magic-pdf" o "mineru". Attiva anche quando l'utente chiede di rendere un PDF (paper, manuale, capitolato, bilancio, contratto) processabile da un LLM, indicizzabile per RAG o leggibile come testo, anche senza dire "Markdown". NON usare per: convertire DOCX/HTML/EPUB tra formati testuali (usa pandoc-convert), generare un PDF a partire da Markdown, compilare o unire PDF, o spezzare un Markdown già esistente in capitoli (usa markdown-chapter-splitter).
koreybaSkillkoreyba/Claude-Skill-pdf-to-epub/pdf_to_epub/SKILL.md
Convert PDF books to EPUB format for e-readers. Use when user asks to convert PDF to EPUB, create an e-book from PDF, make PDF readable on Kindle/phone/tablet, or extract book content from PDF. Handles: chapter detection, image extraction with optimization, footnotes/endnotes with hyperlinks, reading order for multi-column layouts. Validates conversion quality automatically.
digoalSkilldigoal/skills/paper-interpretation/SKILL.md
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF, arXiv PDF, conference paper PDF, journal paper PDF, or local/remote PDF URL.
delorenjSkilldelorenj/skills/nano-pdf/SKILL.md
Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).
kimmihyeon12Skillkimmihyeon12/skills/skills/pdf-parser/SKILL.md
PDF 파일에서 텍스트를 추출하여 처리 가능한 형식(.txt)으로 변환한다. Node.js와 pdf-parse 라이브러리를 사용하며, 출력 파일을 지정된 경로에 저장한다. 트리거: ".pdf 파일", "PDF 텍스트 추출", "PDF 파싱", "pdf-parser", "PDF를 읽어줘", "PDF 내용 추출"
TbusOSSkillTbusOS/sky-skills/skills/tech-pdf-reader/SKILL.md
Read technical PDFs — datasheets, schematics, hardware specs, protocol docs — where the answer is often inside a figure (timing diagram, pin table, waveform, block diagram) rather than in the text. Covers: locating the right page fast, rendering pages so diagrams are actually visible, extracting the text layer and embedded images, and — critically — diagnosing damaged/partial PDF copies so a missing section is never mistaken for a tool failure or, worse, filled in by guessing. Trigger on: "看下这个 datasheet", "读一下规格书", "PDF 里的时序图", "原理图 PDF", "查芯片手册", "这份 PDF 打不开/读不出来", "pdf 解析错误", "datasheet 上电时序", "read the datasheet", "extract timing diagram from PDF", or any request to confirm a hardware parameter from a vendor PDF. Not for converting whole documents to markdown (use doc-to-markdown) or generating PDFs (use md-to-pdf).
beveradbSkillbeveradb/claude-code-config/skills/md2pdf/SKILL.md
Render a Markdown file to a clean, watermark-free, professionally-styled PDF (headless Chrome via md-to-pdf). Use whenever the user asks for a PDF version of a Markdown document, or says "make a PDF", "export to PDF", "convert this markdown to PDF", "render as PDF", "md to pdf", or wants a nicely-formatted PDF of notes/docs/reports/READMEs.
KinomotoMioSkillKinomotoMio/resumaker/.claude/skills/resume-pdf/SKILL.md
简历 PDF 生成器。将 HTML 简历转换为高质量矢量 PDF（文字可选中）。当用户想要导出简历、生成 PDF、或说"把简历转成 PDF"时触发此 skill。
tanis90Skilltanis90/pdf-converter-mineru/SKILL.md
PDF converter powered by MinerU — convert PDF to Word, Markdown, HTML, LaTeX, or plain text. Also handles image-to-text OCR, scanned document recognition, and Office formats (DOCX, PPTX, Excel). Supports 80+ languages. Use this skill when the user wants to convert, extract, read, parse, or summarize any PDF or document. Also applies when the user shares a PDF file or link and asks about its content, needs tables or formulas extracted, wants PDF OCR, or says things like 'turn this into a doc' or 'what does this paper say'.
Abdox-menaraSkillAbdox-menara/guard-skills/skills/workflow/pdf-ocr/SKILL.md
ULTRA-ADVANCED PDF OCR Skill — Content stream scaling approach that produces the smallest possible searchable PDFs with perfect text selectability. Uses Tesseract's native PDF output and scales it to match original page dimensions via PDF content stream transforms.
lsongdevSkilllsongdev/skills/pdf-converter/SKILL.md
Convert Markdown, HTML, plain text, images, and pandoc-supported formats to PDF with CJK font rendering, half-width numbers, and emoji support. Use this skill whenever the user asks to convert a file to PDF, generate a PDF from Markdown or HTML, export a PDF, or run "Convert to PDF" / "Generate PDF" / "Export PDF".
flonatSkillflonat/flonat-research/skills/split-pdf/SKILL.md
Download, split, and deeply read an academic PDF that is not available through Paperpile. Use when a long external PDF needs page-wise ingestion. For Paperpile items, use the Paperpile text-extraction route instead.
keirsalteregoSkillkeirsalterego/jailbreak-fable/skills/public/pdf-reading/SKILL.md
this skill when you need to read, inspect, or extract content from PDF files — especially when file content is NOT in your context and you need to read it from
claesbackmanSkillclaesbackman/AI-research-feedback/Skills/pdf-to-markdown/SKILL.md
Split a PDF into chunks and convert it to readable markdown text. Use when the user wants to read, extract, or convert a PDF document.
yamadashySkillyamadashy/pdfvision/skills/pdfvision/SKILL.md
Extract text, metadata, per-page density signals, layout, image boxes, OCR, and page PNGs from a PDF via the pdfvision CLI. Use when the input is a `.pdf` URL, a local PDF path, or a PDF another agent skill produced. Triggers on: 'read this pdf', 'extract from <file>.pdf', '.pdf', 'scan / slide / paper / form contents'.
MicrosoftSkillmicrosoft/power-platform-skills/plugins/mobile-apps/skills/add-native/add-pdf-viewer/SKILL.md
Internal implementation skill invoked by /add-native for native PDF control workflows. Handles HTTPS and file URI PDF viewing with @microsoft/power-apps-native-pdf-viewer 0.2.9+.
TbusOSSkillTbusOS/astock-lab/skills/finance-pdf-report/SKILL.md
出金融 / 投资分析类 PDF 报告的固定版式与工具链。核心=**HTML + playwright 打印, 不用 md2pdf**(md2pdf 不支持行内粗体和颜色,出来纯黑白)。版式规范:结论前置、 四个 KPI 封面、语义色(涨绿 788c5d / 跌橙 d97757 / 中性灰 6b6a5f)、 数据用内联 SVG 画图不用截图、每张表配来源、**末尾必须有逐条数据来源表**。 含可直接复制的 CSS 模板、html2pdf.mjs 脚本、页码页眉配置、A4 分页控制、 交付前的逐页渲染自检(不能只看"生成成功")。 **本 skill 带 `deep_report.py`** —— 把 preport 的快照 + journal 的判断 渲染成给人看的深度分析报告(结论前置 / 正反证据 / 价格坐标图 / 三情景赔率图 / 回撤容忍线 / 数据来源表),不联网、不发明判断。 触发词:金融 PDF / 投资报告 PDF / 分析报告 PDF / 出 PDF / 报告版式 / 持仓报告 / 研报格式 / html 转 pdf / playwright pdf / md2pdf 黑白 / 报告要好看 / 带图表的 PDF / 深度报告 / deep_report / dreport / 给人看的报告 / 结论前置 / 赔率图 / 价格坐标图。 **边界**:只管「金融分析报告怎么排版成 PDF」;不管分析方法(那是 stock-analysis-workflow)、不管取数(astock-quote)、不管通用网页设计(anthropic-design)。
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
