# document-chat-interface

document-chat-interface is a Claude Code skill for building conversational interfaces to query PDFs, GitHub repositories, email archives, and transcripts with source citations.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 148 installs · ★ 50 repo stars
- Author: qodex-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/qodex-ai/ai-agent-skills/tree/HEAD/skills/document-chat-interface/SKILL.md
- Updated: 2026-01-05
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/document-chat-interface

## What it 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.

## Requirements
- Works with: GitHub

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/document-chat-interface/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/document-chat-interface/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/document-chat-interface/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/document-chat-interface/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install qodex-ai/ai-agent-skills skills/document-chat-interface
```

2. **Manually: put the files in place**
- File: `.github/skills/document-chat-interface/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/qodex-ai/ai-agent-skills --path skills/document-chat-interface
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/document-chat-interface/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill document-chat-interface -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/qodex-ai/ai-agent-skills/tree/HEAD/skills/document-chat-interface/SKILL.md

## When to use it
- 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
- Build a LangChain conversational retrieval chain for `handbook.pdf` using 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

## Similar
- [exa-rag](https://affpapa.org/en/nevibecode/skills/exa-rag.md) — skill · 251 installs
- [llamaindex-development](https://affpapa.org/en/nevibecode/skills/llamaindex-development.md) — skill · 741 installs
- [liteparse](https://affpapa.org/en/nevibecode/skills/liteparse.md) — skill · 4200 installs
- [langchain-rag](https://affpapa.org/en/nevibecode/skills/langchain-rag.md) — skill · 18600 installs
- [audit-content](https://affpapa.org/en/nevibecode/skills/audit-content.md) — skill · ★ 30 repo stars
- [nutrient-document-processing](https://affpapa.org/en/nevibecode/skills/nutrient-document-processing.md) — skill · 6200 installs

From the same set: [qodex-ai/ai-agent-skills](https://affpapa.org/en/nevibecode/by/qodex-ai/ai-agent-skills.md) — 42 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
