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.
peakdong68Skillpeakdong68/my-skills/skills/pdf-processing/SKILL.md
Use when the user needs PDF generation, manipulation, form filling, table extraction, OCR, merging, splitting, watermarking, or metadata handling. Trigger conditions: generate PDF reports, extract text or tables from PDFs, fill PDF forms programmatically, merge or split PDF files, add watermarks, OCR scanned documents, read or write PDF metadata, convert HTML to PDF.
gomarble-aiSkillgomarble-ai/marketing-agent/skills/documents-pdf-skill/SKILL.md
Use when generating PDF documents. Uses the marble_pdf API.
PKUfudaweiSkillPKUfudawei/arxiv-skills/skills/pdf-parser/SKILL.md
Convert PDF papers to markdown using PaddleOCR API
Mspagnolo27248SkillMspagnolo27248/claude-skill/.claude/md-to-pdf/SKILL.md
Converts a Markdown document to PDF with full Mermaid diagram rendering (charts render as visuals, not code). Use this skill whenever the user wants to export a use case, sequence diagram, or review document to PDF — or any .md file in the project. Triggered by phrases like "export to pdf", "convert to pdf", "generate pdf", "save as pdf", or "/md-to-pdf". Works with UC-, SEQ-, REVIEW- prefixed files and any other Markdown file.
GoogleMakesMeBetterSkillGoogleMakesMeBetter/claude-skills-collection/skills/coding/pdf-creator/SKILL.md
Create PDF documents from markdown with proper Chinese font support using weasyprint. This skill should be used when converting markdown to PDF, generating formal documents (legal, trademark filings, reports), or when Chinese typography is required. Triggers include "convert to PDF", "generate PDF", "markdown to PDF", or any request for creating printable documents.
pezz1997Skillpezz1997/claude-skills/pdf-to-md/SKILL.md
Convert PDF files to high-fidelity Markdown using Docling (IBM). Preserves tables (TableFormer ML), images (extracted as PNG or embedded base64), formulas, headings, and reading order. Use when the user wants to convert a PDF to .md with high accuracy, especially when tables or images are present. Triggers on "/pdf-to-md", "converti pdf in markdown", "pdf to md", "estrai testo da pdf", "trasforma pdf in md".
bendyworksSkillbendyworks/claude-skills/skills/markdown-to-pdf/SKILL.md
Convert one or more Markdown files to clean, print-styled PDFs. Use when the user asks for "a PDF version of <doc>.md", "export this markdown to PDF", "make a PDF of this doc", "turn these notes into a PDF", or wants to share a local .md as a PDF. Handles the macOS wkhtmltopdf 0-page trap and preserves monospace/aligned blocks.
gujun1502Skillgujun1502/arch-skills/skills/red-blue-pen-annotation/SKILL.md
红蓝笔批注 Skill。把一份主文档(设计导则/规范/手册等 PDF)与若干修改意见文件 对照核对后, 在原始页面上用“红笔 / 蓝笔”双色标注落实情况, 输出单一批注版 PDF。 蓝笔=已按意见改好并经核对确认; 红笔=意见尚未落实/内容缺失/需复核; 橙色=需人工确认的提示。 内置机器可读核销台账(ledger.json), 逐条意见带稳定编号, 支持跨轮追踪: 第 N 轮只需新版 PDF + 旧台账即可自动重审、记录解决/未落实/回退迁移。 Trigger whenever the user mentions: "红蓝笔批注", "红蓝笔", "红笔修改", "蓝笔", "批注", "修改意见", "意见核对", "导则修订", "核销台账", "台账", "第N轮核对", "跨轮追踪", "redline PDF", "markup PDF", "annotate PDF", 或当文件夹里有 1 份主 PDF + 若干意见文件(.docx/.pdf/.txt/图片) 需要合并成一份批注版时, 或文件夹里已有 ledger.json + 新版主 PDF 需要做第 N 轮核对时。 全流程: 识别主文档与意见 → 提取双方文本 → 逐条核对意见是否落实 → 按红/蓝语义定色定位 → 渲染批注 → 记入核销台账 → 输出批注版 PDF + 核对汇总。
Faaz17SkillFaaz17/Agents-and-Skills/skills/documents/make-pdf/SKILL.md
Turn a Markdown report into a clean, branded A4 PDF the president can read or print. Use whenever the user asks for a report/summary/proposal "as a PDF" or "to read properly". Works fully offline on Windows using pandoc + headless Chrome/Edge — no LaTeX or extra installs needed.
HopesySkillHopesy/skills/skills/pdf-patch/SKILL.md
Repair or replace short text in scanned or image-only PDF pages while preserving the visual appearance. Use when Codex needs to edit a PDF that has no text layer, replace one Chinese character or a short phrase, cover old pixels, match font size, weight, baseline, gray level, blur, and verify the rendered result with screenshots.
huangqianqian120Skillhuangqianqian120/skillslibrary/skills/nano-pdf/SKILL.md
Edit PDFs with natural-language instructions using the nano-pdf CLI.
toolshedlabs-hashSkilltoolshedlabs-hash/web-access-skills/skills/url-to-pdf/SKILL.md
URL to PDF and HTML to PDF. Convert any web page URL, or a raw HTML string, into a clean PDF file. Save an invoice or a receipt, archive an article, or print an HTML report to PDF. The page renders in a real hosted browser with JavaScript on, so the PDF matches the live page, and you set paper size, margins, orientation, and backgrounds. No local headless Chrome or wkhtmltopdf to install. The agent registers its own key and gets free credits right away, so the first PDF works with no signup. A person can confirm one email to add more free credits, and only successful renders cost anything.
huangwb8Skillhuangwb8/skills/skills/beta/download-fulltext-pdf/SKILL.md
当用户明确要求"下载文献全文"或"获取论文PDF"时使用。通过 DOI 号下载学术论文全文 PDF，支持 arXiv、Sci-Hub、Unpaywall、期刊官网等多源策略。⚠️ 不适用：用户只是想解析或处理已有的 PDF 文件（应使用 pdf skill）、只是想搜索论文信息而无需下载全文、没有提供 DOI/标题/BibTeX 任何标识符。
gaoxin492Skillgaoxin492/pdf-compressor/skill.md
Compress PDF files to reduce size. Uses Ghostscript when available, falls back to pikepdf automatically. Trigger when the user says things like "compress this PDF", "PDF is too large", "reduce PDF size", or equivalent in any language.
yugasunSkillyugasun/skills/skills/html-to-pdf/SKILL.md
Export HTML files to PDF using Playwright with mobile emulation and custom viewport settings. Use this skill when the user asks to convert HTML to PDF, export presentations to PDF, or generate PDF documents from web pages.
OpenAnalystIncSkillOpenAnalystInc/10x-Content-Expert/.claude/skills/local-pdf-editor/SKILL.md
Edit PDF files locally without Canva API. Use this skill when user provides a PDF file and wants to modify content, extract text, merge/split pages, or update specific sections. Maintains original formatting, spacing, fonts, and layout. Does NOT require Canva. Output goes to the output/ folder. Use for: "edit this PDF", "change page 15", "update text in PDF".
gigio1023Skillgigio1023/agent-skills/skills/productivity/pdf-page-count/SKILL.md
Use when the user asks for the page count of an existing PDF, whether a PDF meets an exact/minimum/maximum page limit, or the numeric page-count result for another workflow. Triggers on "PDF pages", "page count", "몇 페이지", and "분량 제한 확인". NOT for creating, editing, rendering, or visually reviewing a PDF; use the PDF skill for those tasks.
iflytekSkilliflytek/iFly-Skills/skills/iflytek-pdf-image-ocr/SKILL.md
ifly-pdf-image-ocr skill supporting both image OCR (AI-powered LLM OCR) and PDF document recognition. Use when user asks to OCR images, extract text from images/PDFs, convert PDF to Word/Markdown, or perform any OCR tasks on images or PDFs. Supports multi-language text extraction, document layout understanding, and various output formats.
Mao-jhSkillMao-jh/pdf-qc/SKILL.md
PDF 发出前的确定性质检，专查「打开看没问题、发出去才出事」的坑——字体未嵌入、扫描件无文字层、元数据带本地路径、增量保存残留——一次付费 7 天不限次，期内重复使用不再计费。**触发条件（任务/场景，AI 自己做到这一步就该调，不必等点名）**：即将把 PDF 发给客户、投标、交稿、上传系统之前；要把打印稿或扫描件当「可检索文档」交出去；要发一份从别人那里改过的 PDF（改过的文件常留下被删内容的残留）。口语化说法同样命中：「这份 pdf 能直接发吗」「打印出来会不会变」「客户说搜不到字」「发过去字体变了」。**本 Skill 依赖在线授权服务**：出完整检查报告前会先取一份授权凭证（未付费会返回 402 账单），拿到授权后在**你本机**完成检查，授权本身**离线可校验**；**先用第 0 步判断这份 PDF 是不是「看着没问题」的那种（免费）**，只有出完整报告时才需要授权。核心价值：Word/Excel/PPT 的问题一眼能看出来，**PDF 不一样——它看起来永远是对的**，能打开、能滚、能打印，于是没人去查。而字体没嵌入会在对方机器上静默换字体导致排版位移、扫描件没有文字层对方一个字都搜不到、元数据里写着 `D:\\内部\\投标\\最终版.docx`、用「删掉某页另存」生成的 PDF 被删内容往往仍在字节里。只读、不联网，结论按 **确定 / 疑似 / 未核实** 三态分级。
THEROCKSSSSkillTHEROCKSSS/hermes-skills-portfolio/skills/pdf-extract/SKILL.md
Use when the user wants to extract text, tables, or images from a PDF file — including scanned/image-only PDFs needing OCR — or asks to "read this PDF", "extract text from PDF", "what's in this PDF", or to pull tables/images out of one.
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.
