Chat with PDF Agent Skill
Answer questions about PDF content, summarize, and extract information
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/claude-office-skills/skills --skill Chat with PDFThe instruction itself
25 sections, as written by the authorChat with PDF
Have intelligent conversations about PDF documents - ask questions, get summaries, and extract specific information.
Overview
This skill enables you to:
- Ask questions about PDF content
- Get summaries at various detail levels
- Extract specific data points
- Compare information across multiple PDFs
- Find relevant sections quickly
How to Use
Basic Interaction
- Share or upload the PDF document
- Ask your question or request
- Get contextual answers with citations
Question Types
Factual Questions
"What is the contract value mentioned in this document?"
"Who are the parties involved in this agreement?"
"What are the key dates mentioned?"
Summarization
"Summarize this document in 3 bullet points"
"Give me an executive summary"
"What are the main topics covered?"
Extraction
"Extract all names and titles mentioned"
"List all financial figures in the document"
"Find all action items or deliverables"
Analysis
"What are the risks mentioned in this contract?"
"Are there any ambiguous terms?"
"What obligations does Party A have?"
Output Formats
Q&A Format
**Question**: [Your question]
**Answer**: [Direct answer to your question]
**Source**: Page [X], Section [Y]
> "[Relevant quote from document]"
**Confidence**: [High/Medium/Low]
Summary Format
## Document Summary
**Type**: [Contract/Report/Manual/etc.]
**Pages**: [X]
**Date**: [If mentioned]
### Key Points
1. [Main point 1]
2. [Main point 2]
3. [Main point 3]
### Important Details
- [Detail 1]
- [Detail 2]
Extraction Format
## Extracted Information
### [Category 1]
| Item | Value | Location |
|------|-------|----------|
| [Item 1] | [Value] | Page X |
| [Item 2] | [Value] | Page Y |
### [Category 2]
...
Best Practices
For Better Answers
- Be specific: "What is the termination clause?" vs "Tell me about the contract"
- Reference sections: "What does Section 5.2 say about liability?"
- Ask follow-ups: Build on previous answers for deeper understanding
For Better Extraction
- Specify format: "Extract as a table" or "List as bullet points"
- Name the fields: "Extract: name, date, amount, description"
- Set criteria: "Only extract amounts over $10,000"
For Better Summaries
- Specify length: "Summarize in 100 words" or "3 bullet points"
- Focus area: "Summarize the financial terms only"
- Audience: "Summarize for a legal team" vs "for executives"
Example Workflows
Contract Review
1. "What type of contract is this?"
2. "Who are the parties and what are their roles?"
3. "What are the key obligations for each party?"
4. "What is the term and renewal process?"
5. "What are the termination conditions?"
6. "Are there any unusual or concerning clauses?"
Research Paper Analysis
1. "What is the main thesis or hypothesis?"
2. "What methodology was used?"
3. "What are the key findings?"
4. "What are the limitations mentioned?"
5. "What future research do they suggest?"
Financial Report
1. "What is the total revenue reported?"
2. "How does this compare to last year?"
3. "What are the main expense categories?"
4. "What guidance is given for next quarter?"
5. "Extract all financial metrics into a table"
Multi-Document Support
When working with multiple PDFs:
"Compare the terms in Contract A vs Contract B"
"Which document mentions [topic]?"
"Create a summary table comparing key points across all documents"
Comparison Output
## Document Comparison
| Aspect | Document A | Document B |
|--------|------------|------------|
| Term Length | 2 years | 3 years |
| Value | $50,000 | $75,000 |
| Termination | 30 days notice | 60 days notice |
### Key Differences
1. [Difference 1]
2. [Difference 2]
### Similarities
1. [Similarity 1]
2. [Similarity 2]
Handling Challenges
Scanned PDFs (Image-based)
- OCR will be applied automatically
- Quality depends on scan quality
- May have recognition errors
Complex Layouts
- Tables may need reformatting
- Multi-column text is processed left-to-right
- Footnotes processed separately
Long Documents
- Ask about specific sections for accuracy
- Request page-by-page summaries for overview
- Use targeted questions over broad ones
Limitations
- Cannot execute code embedded in PDFs
- Password-protected PDFs need password
- Very large PDFs (500+ pages) may need chunking
- Handwritten content recognition is limited
- Cannot guarantee 100% accuracy on scanned documents
- Charts and images are described, not analyzed numerically
Privacy Note
Document contents are processed according to the AI provider's privacy policy. For sensitive documents, consider:
- Using on-premise solutions
- Redacting sensitive information first
- Checking data retention policies
Other skills for the same job
different authors, same section of the catalogue
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
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.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
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.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
How to use it
Take claude-office-skills/chat with pdf from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.