split data in separate files

README.md

@@ -28,12 +28,15 @@ Use this prompt with Claude:
 **Prompt for Claude:**
 
 ```
-Process the pending scraped JSON files into docs.md.
+Process pending scraped JSON files into docs.md ONE FILE AT A TIME.
 
-1. Read `processed.md` to find pending JSON files (marked with `- [ ]`)
-2. For each pending file, read it from `scraped_data/`
-3. Extract game entities (buildings, goods, production chains, etc.)
-4. Translate German names to English:
+LOOP: Repeat these steps until all files are processed:
+
+1. Read `processed.md` to find the FIRST pending JSON file (marked with `- [ ]`)
+2. If no pending files remain, stop
+3. Read ONLY that one file from `scraped_data/`
+4. Extract game entities (buildings, goods, production chains, etc.)
+5. Translate German names to English:
    - Use the game's official English names where known
    - Common translations:
      - Latium = Latium (Roman region)
@@ -48,9 +51,10 @@ Process the pending scraped JSON files into docs.md.
      - Mercatoren = Mercators (Tier 4 Celtic)
      - Edelmänner = Nobles (Tier 5 Celtic)
      - Building/Good names: translate to English equivalents
-5. Format data according to the schemas defined in docs.md
-6. Add new entities or update existing ones in docs.md
-7. Mark the JSON file as processed in `processed.md` by changing `- [ ]` to `- [x]`
+6. Format data according to the schemas defined in docs.md
+7. Add new entities or update existing ones in docs.md
+8. Mark this JSON file as processed in `processed.md` (change `- [ ]` to `- [x]`)
+9. REPEAT from step 1
 
 Focus on extracting:
 - Buildings: name, category, region, build costs, maintenance, workforce, cycle time, inputs/outputs, area effects, requirements