PDF skills
PDF skills are SKILL.md folders Claude Code or Codex follow to read a PDF and pull out text and tables, convert a document to Markdown, fill in forms, merge and split files, run OCR on scans and lay out new PDFs. These are the top 30 by installs. They go in .claude/skills for Claude Code and .agents/skills for Codex.
Ordered by install count from the source, then by repository stars on GitHub. A language model writes each description from the source file; only descriptions that passed the automatic check are listed.
-
1
121,543installs
canvas-design official
canvas-design — a skill for Claude Code and Claude.ai that produces static visual art as .png or .pdf files. It kicks in when you ask for a poster, a graphic piece, or a design that has no existing layout.
skill · anthropics · Apache-2.0
-
2
51,700installs
firecrawl-parse
firecrawl-parse turns a local PDF, DOCX or XLSX into markdown, writes a summary, or answers a question about the document. Built for file paths rather than URLs.
skill · firecrawl
-
3
32,100installs
baoyu-slide-deck
baoyu-slide-deck is a Claude Code skill that builds presentations as rendered slide images, drafting an outline before generating slides. Trigger it with "create slides", "make a presentation", or "slide deck".
skill · JimLiu · MIT
-
4
27,000installs
summarize
Runs a CLI tool to summarize or transcribe web articles, YouTube videos, podcasts, and local PDF documents directly within your AI assistant.
skill · openclaw · MIT
-
5
16,600installs
nature-reader
nature-reader creates source-grounded Chinese-English paper readers with aligned text, tables, and equations. Handles full translations, excerpt parsing, and targeted questions.
skill · Community contribution, refactored into static/dynamic layers · Apache-2.0
-
6
14,600installs
read
read fetches a URL or PDF and returns a summary or clean Markdown, with a DeepSeek search fallback when built-in search comes up thin.
skill · tw93 · MIT
-
7
14,000installs
pdf official
A skill for reading, creating and reviewing PDFs where layout matters. Useful when the agent builds a document and needs to see how it renders.
skill · openai · Apache-2.0
-
8
14,000installs
kami
Lays out resumes, one-pagers, white papers, letters, portfolios, slide decks and social cards from Kami's templates. Triggers on requests to build a PDF, typeset a resume, or draft slides.
skill · tw93 · MIT
-
9
13,700installs
convert-documents-to-markdown
convert-documents-to-markdown converts office documents, spreadsheets, and PDFs into GitHub-Flavored Markdown via anydoc. Useful when an agent must read DOCX or XLSX files without manual copy-pasting.
skill · firecrawl · MIT
-
10
12,000installs
nature-paper-card
nature-paper-card turns one scientific paper into a structured deep-reading card: methods, experiment-to-claim evidence, limitations. Useful when you need the paper taken apart, not summarised.
skill · Yuan1z0825 · Apache-2.0
-
11
10,500installs
deep-research
deep-research — a skill for Claude Code, Codex, Cursor and other agents that runs a multi-phase research pipeline and produces a fully cited report with per-claim verification.
skill · 199-biotechnologies
-
12
9,978installs
pdftk-server official
This GitHub Copilot skill guides PDF work through the pdftk CLI, from merging files to filling forms and applying stamps. Use it when PDF changes belong in a terminal workflow.
skill · github · MIT
-
13
9,700installs
book-to-skill
book-to-skill turns books and documents into structured agent skills with frameworks, principles, and techniques. Useful when an agent should apply an author's methods while working.
skill · virgiliojr94 · MIT
-
14
9,600installs
pdf-extraction
pdf-extraction extracts tables and text from PDF files using pdfplumber. It helps when you need to pull tabular data into DataFrames or parse invoices.
skill · claude-office-skills · MIT
-
15
7,500installs
k2f
k2f — an agent skill that authors documents as semantic JSON and exports them to docx, PDF, fillable AcroForm and IDML. Handy for menus, certificates, planners and invitations.
skill · suzheng · Apache-2.0
-
16
7,400installs
remove-pdf-watermark
remove-pdf-watermark removes watermarks from PDF files via the official Pilio CLI and API. Useful when cleaning up editable documents or reconstructing pages with AI.
skill · pilioai · MIT
-
17
7,200installs
nano-pdf
A skill for editing PDF pages using natural-language instructions through the nano-pdf CLI. Runs in Claude Code, Codex, Cursor, and other AI editors — change headings, fix typos, or rebuild layouts from code without opening manual tools.
skill · openclaw · MIT
-
18
7,200installs
k2f-flyer
k2f-flyer drafts single-page promotional flyer blueprints with clear visual intent, tight word budgets, and a single call to action for the K2F engine.
skill · suzheng · Apache-2.0
-
19
7,100installs
office-mcp
An MCP server with 39 tools for Word, Excel, PowerPoint, PDF and OCR work. Useful when your agent has to read and build office files inside a project.
skill · claude-office-skills · MIT
-
20
6,200installs
nutrient-document-processing
nutrient-document-processing is a Claude Code skill that processes files through the Nutrient DWS API. It handles conversions, OCR, data extraction, redaction, signatures, and PDF forms.
skill · affaan-m · MIT
-
21
5,869installs
pdf-processing-pro
pdf-processing-pro is a Claude Code skill for filling PDF forms, extracting tables, and processing PDFs with Python scripts. It supports automated document workflows.
skill · davila7
-
22
4,800installs
ocr-document-processor
ocr-document-processor pulls text and structure out of scans, photos and scanned PDFs. Useful when the only copy of a document is an image.
skill · dkyazzentwatwa
-
23
4,200installs
liteparse
liteparse extracts text, tables, and values from PDFs, Office files, and images with the local lit CLI. Use it when an agent needs facts from a document.
skill · LlamaIndex · MIT
-
24
4,100installs
slide-creator
slide-creator builds 16:9 presentation slide decks using HTML and CSS, then renders them to PDF via headless Chromium.
skill · Starchild-ai-agent
-
25
4,000installs
paddleocr-text-recognition
paddleocr-text-recognition extracts machine-readable text line by line from screenshots, scans, and PDFs via PaddleOCR. Useful when dealing with handwritten notes, small print, or CJK characters.
skill · Aidenwu0209 · Apache-2.0
-
26
3,900installs
minimax-pdf
minimax-pdf generates professional PDFs with visual identity: reports, resumes, portfolios. Design is derived from document type, with consistent color and typography throughout.
skill · MiniMax-AI · MIT
-
27
3,700installs
literature-search-arxiv
literature-search-arxiv searches arXiv for papers and preprints, returns metadata and abstracts, and downloads full text as PDF, HTML or LaTeX source.
skill · google-deepmind · Apache-2.0
-
28
3,600installs
paper-audit
paper-audit — a reviewer-style skill for checking academic papers before submission, with blocker triage and revision plans for .tex, .typ, and .pdf.
skill · bahayonghang
-
29
3,500installs
engineering-drawing
engineering-drawing is a Claude Code skill that creates dimensioned PDF drawings from part geometry. It activates for requests for manufacturing sheets, prints, or 2D views of a part.
skill · earthtojake · MIT
-
30
3,400installs
literature-search-openalex
literature-search-openalex queries the OpenAlex database to find research papers, download open-access PDFs, and collect citation metrics via a local CLI. Handy for resolving DOIs and tracking author publications.
skill · google-deepmind · Apache-2.0
How to choose a PDF skill
The catalog has 316 skills that work with PDF. The jobs differ: some read a document (text, tables, conversion to Markdown), some edit an existing file (pages, forms, watermarks), and some create a PDF from scratch: a report, a resume, a deck. Scans need a skill with OCR, since plain extraction returns nothing on them.
Check where processing happens. Skills built on local tools such as pdfplumber and pdftk keep the file on your machine. Skills that call an outside API send the document to that service, which may not suit contracts or personal data. Nearby: slides, Word and Excel skills, presentation skills.
FAQ
Which skill reads PDFs in Claude Code or Codex?
By installs, the list is led by canvas-design, firecrawl-parse and baoyu-slide-deck. For text and tables take an extraction skill, for scans one with OCR.
Can a skill edit a PDF?
Yes: the list has skills that merge and split files, rotate pages, fill in forms and edit a page from a text instruction.
Does my PDF leave my machine?
It depends on the skill. Those built on local tools keep the file with you, and skills on an outside API send the document to that service. SKILL.md says which service is called.
Other collections
- Best Claude Code skills
- Best Claude Code plugins
- Best Claude Code subagents
- Best Codex skills
- Best Cursor rules
- Best MCP servers
- MCP servers for Cursor
- Frontend skills
- Testing skills
- Security skills and rules
- SEO and marketing skills
- Design skills
- DevOps skills
- MCP servers for databases
- Browser and scraping MCP servers
- Code review and refactoring skills
- Skills and MCP for game development and 3D
- Video generation and editing skills
- Mobile development skills
- Backend and API skills
- Marketing skills and agents
- Scientific skills for AI agents
- UI/UX design skills
- Writing skills
- Claude Code hooks examples
- Claude Code slash commands
- Best Codex plugins
- GitHub Copilot agent skills
- Gemini CLI extensions and skills
- GitHub Copilot instructions
- MCP servers for Claude Code
- MCP servers for Codex
- MCP servers for VS Code
- Remote MCP servers
- Security MCP servers
- Office skills: slides, PDF, Word, Excel
- Data analysis skills
- Research skills
- Telegram AI agent tools
- 1C AI agent tools
- Codex subagents
- Cursor skills
- OpenCode skills
- Animation skills
- Presentation skills
- Software architecture skills
- Planning and spec skills
- Debugging skills
- Audio, voice and music skills
- Branding and logo skills
- Humanizer and AI-text detector skills
- Game design skills
- Product management skills
- SwiftUI and iOS design skills
- HyperFrames skills
- Figma skills
- Blender skills
- Unity skills
- Godot skills