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.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
hanlinlibhamSkillhanlinlibham/skills/pdf/SKILL.md
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Often used withgift-evaluatorVideo Generationstock_analysis
iadr-devSkilliadr-dev/colab/skills/pdf/SKILL.md
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Often used withgift-evaluatorVideo Generationstock_analysis
IGTA-TechSkillIGTA-Tech/claude-skills-research/skills/skills/pdf/SKILL.md
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Often used withgift-evaluatorVideo Generationstock_analysis
letsloose501Skillletsloose501/sqs-agent-memory/skills/pdf/SKILL.md
Reads ANY PDF into the knowledge vault - a book, a handbook, a paper, lecture slides, a manual, a scan, a printout. Detects scanned pages without a text layer, extracts structured markdown, reads the scans by eye through a render, and hands the text to `notes` (or stops after extraction if only reading is wanted). Use when a PDF file or its path arrives, with or without words: "take notes on this PDF", "add it to my notes", "what does this say", "extract the text", "convert to markdown", "read this file", "summarise this handbook". Covers the case where other tools fail silently: a scan with no text at all, where PyMuPDF and Read return nothing. Splitting, merging, rotating, filling forms, encrypting a PDF is a different job (those CHANGE the file; this one READS it).
Often used withgift-evaluatorVideo Generationstock_analysis
miptah21Skillmiptah21/skills/.agents/skills/pdf/SKILL.md
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Often used withgift-evaluatorVideo Generationstock_analysis
pepebot-spaceSkillpepebot-space/skills/pdf/SKILL.md
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Often used withgift-evaluatorVideo Generationstock_analysis
SaddssSkillSaddss/cursor-skills/skills/pdf/SKILL.md
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Often used withgift-evaluatorVideo Generationstock_analysis
szweibelSkillszweibel/claude-skills/pdf/SKILL.md
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Often used withgift-evaluatorVideo Generationstock_analysis
zhangjunwei0233Skillzhangjunwei0233/My-Claude-Skills/pdf/SKILL.md
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Often used withgift-evaluatorVideo Generationstock_analysis
aemerson-commitsSkillaemerson-commits/shareable-skills/skills/pdf/SKILL.md
Read, create, merge, split, OCR, watermark, encrypt, fill forms, or extract from PDF files. Trigger when user mentions .pdf or asks to produce one.
Often used withgift-evaluatorVideo Generationstock_analysis
AidenSbVevoSkillAidenSbVevo/claude-code-starter/skills/pdf/SKILL.md
Any task with PDF files: extract text/tables, merge or combine, split, rotate, watermark, create PDFs, fill PDF forms (bundled scripts), encrypt/decrypt, extract images, OCR scanned PDFs. Trigger whenever the user mentions a .pdf file or asks to produce one.
Often used withgift-evaluatorVideo Generationstock_analysis
ai-ecoverseSkillai-ecoverse/skills/skills/pdf/SKILL.md
Read, merge, split, rotate and rasterise PDF files with SLICC's built-in pdftk and pdftoppm, plus `pdf-text` for validated text extraction. Text extraction succeeds on simple fonts and on any PDF carrying a /ToUnicode CMap; for subset CID fonts without one it refuses to return glyph-index mojibake and escalates to poppler on an ssh follower, and it reports a scanned/image-only PDF as having no text layer instead of guessing. No Python required. Use when the user asks to work with PDFs or .pdf files, extract or read text from a PDF, merge, split, rotate or burst documents, check page count or metadata, or convert a PDF page to an image. Not OCR of scanned pages, not PDF form filling, and not PPTX conversion (use the pptx2pdf skill).
Often used withgift-evaluatorVideo Generationstock_analysis
anurag-mishra899Skillanurag-mishra899/Nano-ClaudeCode/skills/pdf/SKILL.md
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.
Often used withgift-evaluatorVideo Generationstock_analysis
ashleysbrainSkillashleysbrain/skills/pdf/SKILL.md
PDF files: create, read, merge, fill, OCR, edit text.
192 projects use a version of this
Often used withgift-evaluatorVideo Generationstock_analysis
AymanShamsSkillAymanShams/codex-coding-os/.agents/skills/pdf/SKILL.md
Use when the task involves local PDF reading, creation, extraction, review, page rendering, visual inspection, or layout-quality checks where pagination, tables, charts, typography, forms, images, or final rendered appearance matter. Use for creating PDFs, reviewing PDF output, extracting PDF text with layout caveats, checking generated pages, and validating visual defects with Poppler, `reportlab`, `pdfplumber`, or `pypdf`. Do not use for DOCX, PPTX, spreadsheets, plain text, web pages, Google Docs, generic fact checking, or non-layout prose review. If the primary task is source or citation verification inside a PDF, use evidence-checker alongside targeted PDF extraction. If the primary task is a formal artifact, use ssot-drafter for substance and this skill only for PDF rendering or file production.
Often used withgift-evaluatorVideo Generationstock_analysis
benjaleivasSkillbenjaleivas/Claude-Code-Workflow/skills/pdf/SKILL.md
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Often used withgift-evaluatorVideo Generationstock_analysis
BrightGold70SkillBrightGold70/skills/pdf/SKILL.md
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
Often used withgift-evaluatorVideo Generationstock_analysis
cadecodeSkillcadecode/agent-skills/skills/docs/pdf/SKILL.md
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Often used withgift-evaluatorVideo Generationstock_analysis
CastrozanSkillCastrozan/claude-code-flake/skills/pdf/SKILL.md
PDF processing and manipulation. Use when user asks to read PDFs, fill PDF forms, extract text/data from PDFs, merge/split PDFs, or convert to/from PDF format.
Often used withgift-evaluatorVideo Generationstock_analysis
dmitrykrivaltsevichSkilldmitrykrivaltsevich/claude-skills/skills/pdf/SKILL.md
Reads and writes PDF documents. Extracts text as markdown, searches content, extracts embedded images, and renders pages to high-DPI PNG for LLM vision OCR. Writes beautiful PDFs from Typst markup with proper typography, math, and New Computer Modern fonts. Use when the user asks to read, analyze, search, extract from, create PDF files, or reopen saved PDF extraction artifacts by selector, heading, chunk, or line range.
Often used withgift-evaluatorVideo Generationstock_analysis
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.
