document-chat-interface — Claude Code skill: setup and guide
document-chat-interface is a Claude Code skill for building conversational interfaces to query PDFs, GitHub repositories, email archives, and transcripts with source citations.
no license 148 installs ★ 50 updated 2026-01-05
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a claude-codeWhat document-chat-interface does
This skill provides reference patterns and blueprints for document Q&A pipelines. It covers the full flow from file ingestion and sentence-aware chunking to vector search and conversational memory.
The processing workflow details how to extract tables via pdfplumber and run OCR on scanned pages with pytesseract. On the conversational side, it explains question rewriting, conversation history pruning, and generating reference citations with page numbers.
OCR extraction will fail without pytesseract and system-level OCR tools configured. For implementation, the skill includes working setups using LangChain with Chroma as well as LlamaIndex with a chat memory buffer.
What it helps with
- create an interactive Q&A assistant for PDF reports
- extract text and tables from scanned documents via OCR
- index a GitHub repository for natural language querying
- format assistant answers with source citations and page numbers
Example prompts for the agent
- Build a LangChain conversational retrieval chain for
handbook.pdfusing Chroma - Set up a document ingestion script that handles scanned PDFs with pytesseract
- Implement a LlamaIndex chat engine with memory for querying our technical docs
How to install document-chat-interface
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a claude-code2Manually: put the files in place
~/.claude/skills/document-chat-interface/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/document-chat-interface/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a codex2Manually: put the files in place
.agents/skills/document-chat-interface/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a cursor2Manually: put the files in place
.cursor/skills/document-chat-interface/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install qodex-ai/ai-agent-skills skills/document-chat-interface2Manually: put the files in place
.github/skills/document-chat-interface/SKILL.md1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a gemini-cli2Platform CLI
gemini skills install https://github.com/qodex-ai/ai-agent-skills --path skills/document-chat-interfaceManually: put the files in place
.devin/skills/document-chat-interface/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about document-chat-interface
How to install document-chat-interface in Claude Code?
Run npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a claude-code in your terminal.
What file formats and sources does document-chat-interface handle?
The skill outlines pipelines for PDF documents, GitHub repositories, email archives, web pages, and YouTube video transcripts.
Which Python packages are required for OCR and table extraction?
The implementations rely on pdfplumber to pull tabular data and pytesseract to extract text from scanned images.