structurecc 1.0.0 → 1.0.2

package/README.md

@@ -1,75 +1,183 @@
-<h1 align="center">STRUCTUREIT</h1>
+<h1 align="center">STRUCTURE</h1>
 
 <p align="center">
-<strong>Agentic Document Extraction for Claude Code</strong><br>
-<em>One command. Every figure. Every table.</em>
+<strong>Landing AI charges $500/month for agentic document extraction.<br>This is free.</strong>
 </p>
 
 <p align="center">
 <a href="https://www.npmjs.com/package/structurecc"><img src="https://img.shields.io/npm/v/structurecc.svg" alt="npm version"></a>
-<a href="https://github.com/JamesWeatherhead/structurecc/stargazers"><img src="https://img.shields.io/github/stars/JamesWeatherhead/structurecc" alt="GitHub stars"></a>
 <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
 </p>
 
 <p align="center">
-<em>Unstructured in. Structured out.</em>
+<img src="assets/terminal.png" alt="structurecc" width="550">
+</p>
+
+<p align="center">
+<em>Works on Mac, Windows, and Linux</em>
 </p>
 
 ---
 
 ## The Problem
 
-You have a PDF with figures, tables, and charts. You need that data.
+You have a 50-page PDF with figures, tables, and charts. You need that data.
 
-**Manual approach:** Screenshot each figure. Copy tables cell by cell. Spend hours on one document.
+**Manual approach:** Screenshot each figure. Transcribe tables cell by cell. Spend hours on one document.
+
+**With structurecc:** One command. Walk away. Come back to perfectly structured markdown.
 
-**structurecc:**
 ```
 /structure paper.pdf
 ```
 
-Done.
+Spawns parallel AI agents. Each agent analyzes one visual element. All run simultaneously. Done in minutes, not hours.
+
+---
+
+## What is this?
+
+Give it a document. It extracts every image. Spawns one AI agent per image. Each agent exhaustively analyzes its element—tables become markdown tables, figures get descriptions, charts get data points extracted.
+
+Runs inside **[Claude Code](https://docs.anthropic.com/en/docs/claude-code)** (Anthropic's terminal assistant). One command. ~$0.50-$5 per document.
+
+Like [Landing AI's Agentic Document Extraction](https://landing.ai/agentic-document-extraction), but running locally via Claude Code.
 
 ---
 
-## What It Does
+## Before You Start
 
+You need two things:
+
+### 1. Node.js
+
+Check if you have it:
+
+```bash
+node --version
 ```
-PDF  ───▶  [Agent 1]  ───┐
-           [Agent 2]  ───┤
-           [Agent 3]  ───┼───▶  STRUCTURED.md
-           [Agent N]  ───┘
+
+If you see a version number, you're good. If you see "command not found", download Node.js from **[nodejs.org](https://nodejs.org/)** and install it.
+
+### 2. Anthropic API Key or Pro/Max Plan
+
+You need one of these to use Claude Code:
+
+- **API key:** Get one at **[console.anthropic.com](https://console.anthropic.com/)**. Requires a payment method.
+- **Pro or Max plan:** If you subscribe to Claude Pro ($20/mo) or Max ($100/mo), you can use Claude Code without a separate API key.
+
+---
+
+## Setup (5 minutes)
+
+### Step 1: Open your terminal
+
+**Mac:** Press `Cmd + Space`, type `Terminal`, press Enter
+
+**Windows:** Press `Win + X`, click "Terminal" or "PowerShell"
+
+**Linux:** Press `Ctrl + Alt + T`
+
+---
+
+### Step 2: Install Claude Code
+
+Copy this command and paste it into your terminal:
+
+```bash
+npm install -g @anthropic-ai/claude-code
 ```
 
-1. **Extracts** every image from your document
-2. **Spawns** one AI agent per image (running in parallel)
-3. **Analyzes** each element exhaustively
-4. **Outputs** clean, structured markdown
+<p align="center">
+<img src="assets/screenshots/step0.png" alt="Install Claude Code" width="550">
+</p>
 
-Like [Landing AI's Agentic Document Extraction](https://landing.ai/agentic-document-extraction), but running locally via Claude Code.
+Wait for it to finish.
 
 ---
 
-## Install
+### Step 3: Install structurecc
+
+Copy and run this:
 
 ```bash
 npx structurecc
 ```
 
-## Use
+<p align="center">
+<img src="assets/screenshots/step1.png" alt="Install structurecc" width="420">
+</p>
+
+You will see a STRUCTURE banner. That means it worked. You only do this once.
+
+---
+
+### Step 4: Set up your document folder
+
+Create a folder with your document:
+
+<p align="center">
+<img src="assets/screenshots/step2.png" alt="Folder structure" width="380">
+</p>
+
+```
+documents/
+├── document.pdf          ← your PDF, DOCX, or image
+└── images/               ← extracted images go here (created automatically)
+    ├── figure_1.png
+    ├── table_2.png
+    └── chart_3.png
+```
+
+**Put your document in a folder. That's it.**
+
+---
+
+### Step 5: Open Claude Code
+
+Navigate to your document folder and start Claude Code:
+
+```bash
+cd ~/Desktop/documents
+claude
+```
+
+<p align="center">
+<img src="assets/screenshots/step3a.png" alt="Start Claude Code" width="460">
+</p>
+
+**Windows users:** Replace `~/Desktop/documents` with your actual path, like `C:\Users\YourName\Desktop\documents`
+
+The first time you run `claude`, it will ask for your API key. Paste it in.
+
+---
+
+### Step 6: Run structure
 
-In Claude Code:
+Now you are inside Claude Code. Type this command:
 
 ```
-/structure path/to/document.pdf
+/structure document.pdf
 ```
 
-Works with: **PDF, DOCX, PNG, JPG**
+<p align="center">
+<img src="assets/screenshots/step3.png" alt="Run /structure" width="500">
+</p>
+
+**Important:** The `/structure` command only works inside Claude Code. If you type it in your regular terminal, it will not work.
+
+structurecc will:
+1. Extract every image from your document
+2. Spawn one agent per image (all running in parallel)
+3. Each agent exhaustively analyzes its visual element
+4. Combine everything into `STRUCTURED.md`
 
 ---
 
 ## What You Get
 
+A comprehensive markdown file with every visual element extracted:
+
 ```
 document_extracted/
 ├── images/           # All extracted visuals
@@ -97,66 +205,72 @@ document_extracted/
 | p-value | - | 0.67 | 0.73 |
 
 ## Notes
-- * Missing data excluded
+- Confidence level: High
+- * Missing data excluded from analysis
 ```
 
-### Example: Figure Analysis
+### Example: Chart Analysis
 
 ```markdown
 # Kaplan-Meier Survival Curves
 
-**Type:** Figure
+**Type:** Chart (Line/Survival)
 **Source:** Page 7, clinical_trial.pdf
 
 ## Content
 
 Survival curves comparing treatment (blue) vs placebo (red) over 24 months.
 
+Key data points:
 - 12-month survival: Treatment 0.89, Placebo 0.78
 - 24-month survival: Treatment 0.76, Placebo 0.61
 - Log-rank p = 0.003
 
-## Labels & Text
-- "Survival Probability"
-- "Time (months)"
-- "Treatment (n=245)"
-- "Placebo (n=248)"
+## Labels & Annotations
+- Y-axis: "Survival Probability"
+- X-axis: "Time (months)"
+- Legend: "Treatment (n=245)", "Placebo (n=248)"
 ```
 
 ---
 
-## How It Works
-
-1. **Extract** - PyMuPDF pulls all images from PDF (or unzip DOCX media folder)
-2. **Swarm** - Launch N parallel agents, one per image
-3. **Analyze** - Each agent reads its image, extracts everything, writes markdown
-4. **Combine** - Merge all element files into STRUCTURED.md
-
-Agents run simultaneously. 10 images = 10 agents = fast.
-
----
-
 ## Cost
 
-Depends on document complexity:
-
 | Document | Elements | ~Cost |
 |----------|----------|-------|
 | Simple paper | 5-10 | $0.50-$1 |
 | Full paper | 15-25 | $2-$4 |
 | Dense report | 40+ | $5-$10 |
 
-Uses Claude's multimodal vision. Works best with **Opus 4.5**.
+Uses Claude's multimodal vision. Works best with **Opus 4.5** for complex tables and charts.
 
 ---
 
-## Requirements
+## Supported Formats
+
+- **PDF** - Extracts embedded images via PyMuPDF
+- **DOCX** - Extracts images from Word's media folder
+- **PNG/JPG/TIFF** - Analyzes images directly
+
+---
+
+## Troubleshooting
+
+**"npm: command not found"**
+
+You need Node.js. Download it from [nodejs.org](https://nodejs.org/).
+
+**"bash: /structure: No such file or directory"**
+
+You typed `/structure` in your regular terminal. You need to type it inside Claude Code. First run `claude` to start Claude Code, then type `/structure`.
+
+**"No images found"**
+
+Make sure your PDF contains actual images, not just text. Some PDFs render everything as text.
 
-- Node.js
-- Claude Code (`npm install -g @anthropic-ai/claude-code`)
-- Anthropic API key or Claude Pro/Max
+**Claude Code asks for an API key**
 
-PyMuPDF installed automatically if needed.
+Either get an API key at [console.anthropic.com](https://console.anthropic.com/), or subscribe to Claude Pro/Max at [claude.ai](https://claude.ai/).
 
 ---
 
@@ -175,5 +289,5 @@ MIT
 ---
 
 <p align="center">
-<strong>Stop copying tables by hand.</strong>
+<strong>Unstructured in. Structured out.</strong>
 </p>

package/agents/{structureit-extractor.md → structurecc-extractor.md}

@@ -1,5 +1,5 @@
 ---
-name: structureit-extractor
+name: structurecc-extractor
 description: Extract and analyze any visual element from documents
 ---
 

package/bin/install.js

@@ -4,7 +4,7 @@ const fs = require('fs');
 const path = require('path');
 const os = require('os');
 
-const VERSION = '1.0.0';
+const VERSION = '1.0.2';
 const PACKAGE_NAME = 'structurecc';
 
 // Colors
@@ -103,7 +103,7 @@ function install() {
     const agentFiles = fs.readdirSync(srcAgentsDir);
     ensureDir(agentsDir);
     for (const file of agentFiles) {
-      if (file.startsWith('structureit-')) {
+      if (file.startsWith('structurecc-')) {
         fs.copyFileSync(
           path.join(srcAgentsDir, file),
           path.join(agentsDir, file)
@@ -138,7 +138,7 @@ function uninstall() {
   if (fs.existsSync(agentsDir)) {
     const agentFiles = fs.readdirSync(agentsDir);
     for (const file of agentFiles) {
-      if (file.startsWith('structureit-')) {
+      if (file.startsWith('structurecc-')) {
         fs.unlinkSync(path.join(agentsDir, file));
         log(`  ✓ Removed ${file}`, colors.green);
       }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "structurecc",
-  "version": "1.0.0",
+  "version": "1.0.2",
   "description": "Agentic document extraction for Claude Code. One command. Every figure. Every table.",
   "keywords": [
     "document-extraction",