structurecc 3.2.0 → 3.3.1

package/commands/structure.md

@@ -94,6 +94,12 @@ You are extracting structured data from a document chunk.
 - Pages: {start_page} to {end_page} (or "all" for images/small docs)
 - Output: Write JSON to {output_path}
 
+## Core Principle
+
+**Figures are data, not decorations.**
+
+A chart is a visual table. A graph is data in disguise. When you see axes and curves, you see data waiting to be extracted - not an image to describe.
+
 ## Protocol
 
 ### Step 1: SCAN
@@ -101,6 +107,7 @@ Read the document using the Read tool. Look at ALL pages in your assigned range.
 List every element you see:
 - Tables (data tables, comparison tables, any tabular data)
 - Figures (charts, graphs, images, diagrams, gels, blots, plots)
+  **Figures are data, not decorations. Read them like you read tables.**
 - Text blocks (paragraphs, headers, captions)
 - Equations (mathematical formulas)
 - Lists (bulleted, numbered)
@@ -119,6 +126,30 @@ Rules:
 - Include ALL flags, markers, asterisks, annotations
 - Transcribe units exactly as shown (mg/dL, not mg per dL)
 
+### Step 2B: EXTRACT FIGURE DATA
+
+**Figures are data, not decorations.**
+
+For every figure with axes:
+
+1. **Read the axes** (your coordinate system)
+   - X-axis: label, range, units
+   - Y-axis: label, range, units
+
+2. **Read the data points** (estimate from visual position)
+   - Where does each line/bar/point fall on the grid?
+   - For step functions: each step is a data point
+   - For curves: sample ~10 points across the range
+   - Format: [[x1, y1], [x2, y2], ...]
+
+3. **Read the legend** (what each series represents)
+   - Color, line style, label
+
+4. **Multi-panel = multiple extractions**
+   - Panel A, B, C, D each get FULL extraction
+
+A chart without data_series values is like a table without cell values - incomplete.
+
 ### Step 3: STRUCTURE
 Output as JSON with this schema:
 
@@ -158,19 +189,35 @@ Output as JSON with this schema:
 }
 
 **For Figures (charts/graphs):**
+
+Figures are data, not decorations. Extract the actual values.
+
 {
-  "figure_type": "bar_chart|line_graph|scatter_plot|pie_chart|other",
-  "description": "Brief description of what the figure shows",
+  "figure_type": "bar_chart|line_graph|scatter_plot|kaplan_meier|forest_plot|other",
+  "description": "Brief description (SECONDARY to actual data)",
   "axes": {
-    "x": {"label": "Time (hours)", "range": [0, 24]},
-    "y": {"label": "Concentration (ng/mL)", "range": [0, 100]}
+    "x": {"label": "Time (days)", "range": [0, 7000], "unit": "days"},
+    "y": {"label": "Cumulative Risk", "range": [0, 0.6], "unit": null}
   },
-  "data_series": [
-    {"name": "Control", "color": "blue", "values": [[0, 10], [6, 45], [12, 80]]},
-    {"name": "Treatment", "color": "red", "values": [[0, 12], [6, 60], [12, 95]]}
+  "data_series": [  // REQUIRED - the actual data, not optional
+    {
+      "name": "HSV Group",
+      "color": "purple",
+      "line_type": "step",
+      "values": [[0, 0], [1000, 0.05], [2000, 0.08], [3000, 0.12], [4000, 0.16], [5000, 0.22], [6000, 0.32], [7000, 0.55]]
+    },
+    {
+      "name": "Control Group",
+      "color": "blue",
+      "line_type": "step",
+      "values": [[0, 0], [1000, 0.01], [2000, 0.02], [3000, 0.03], [4000, 0.04], [5000, 0.05], [6000, 0.06], [7000, 0.07]]
+    }
+  ],
+  "legend": ["HSV Group", "Control Group", "HSV 95% CI", "Control 95% CI"],
+  "confidence_bands": [
+    {"series": "HSV Group", "color": "purple shaded", "description": "95% CI"}
   ],
-  "legend": ["Control", "Treatment"],
-  "annotations": ["Arrow pointing to peak at t=12h"]
+  "annotations": []
 }
 
 **For Figures (gels/blots):**
@@ -224,6 +271,11 @@ Output as JSON with this schema:
 4. Low confidence (<0.8) = flag for review in notes
 5. For tables with merged cells, represent structure accurately
 6. Include ALL visible data points, not just a sample
+7. FIGURES ARE DATA, NOT DECORATIONS
+   - A chart/graph without data_series is INCOMPLETE
+   - Estimate numeric values from visual position on the grid
+   - Multi-panel figures need FULL extraction for EACH panel
+   - If you can see axes and curves, you can extract data
 
 ## Output
 Write your JSON to: {output_path}

package/install.js

@@ -7,6 +7,10 @@ const os = require('os');
 const CLAUDE_DIR = path.join(os.homedir(), '.claude');
 const COMMANDS_DIR = path.join(CLAUDE_DIR, 'commands');
 
+// Read version from package.json
+const pkg = require('./package.json');
+const VERSION = pkg.version;
+
 function copyFile(src, dest) {
   const destDir = path.dirname(dest);
   if (!fs.existsSync(destDir)) {
@@ -22,7 +26,7 @@ function install() {
 ║   STRUCTURECC                                     ║
 ║   Document Structure Extraction                   ║
 ║                                                   ║
-║   Claude Code Plugin  |  v3.1                     ║
+║   Claude Code Plugin  |  v${VERSION.padEnd(20)}║
 ║                                                   ║
 ╚═══════════════════════════════════════════════════╝
 `);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "structurecc",
-  "version": "3.2.0",
+  "version": "3.3.1",
   "description": "Claude Code plugin for extracting structured data from documents using native vision and parallel Task agents",
   "author": "UTMB Diagnostic Center",
   "license": "MIT",