diff --git a/README.md b/README.md
index 6a22926..bea4b15 100644
--- a/README.md
+++ b/README.md
@@ -62,6 +62,76 @@ Examples:
---
+## Example: Nano Banana Pro Prompting (Image Generation)
+
+**Query:** `/last30days nano banana pro prompting`
+
+**Research Output:**
+> JSON prompting is the dominant technique — The X community overwhelmingly uses structured JSON prompts rather than plain text. Creators like @Xmira_belle, @Cicily_aura, @RubenSalvo_, and @mahivisuals all share prompts in JSON format with nested objects for metadata, subject descriptions, lighting, camera specs, and scene composition. @realdigitaldao made a static ad "in less than 5 min" using a simple JSON prompt.
+>
+> Prompt adherence is Nano Banana Pro's killer advantage — JSON prompts hit 92% precision for color accuracy, lighting ratios, and composition vs ~68% for natural language prompts, per fofr.ai. @artingent directly compared it to GPT Image 1.5 and noted Nano Banana Pro has higher prompt adherence — "GPT image 1.5 ignored the Top Down instruction."
+>
+> Stop writing "tag soup" — act like a Creative Director — The biggest shift is away from comma-separated keyword lists toward natural language descriptions with clear structure. The ICS Framework (Image type, Content, Style) and the 5-element formula (subject, composition, action, setting, style) are the two dominant approaches, per r/nanobanana2pro.
+
+**Key patterns discovered:**
+1. JSON > plain text — Structure prompts as JSON objects with keys for subject, composition, lighting, camera, style — per @Xmira_belle, @Cicily_aura
+2. The 5-element formula — Subject + Composition + Action + Setting + Style — per r/nanobanana2pro
+3. Separate subjects into distinct objects — Multi-character scenes need each person in their own JSON block to prevent "concept bleeding" — per fofr.ai
+4. Use camera/lens metadata — Aperture, focal length, ISO, film stock as JSON keys for hidden photorealism control
+5. 14 reference images max — Feed up to 14 reference images for brand/character consistency — per Google DeepMind
+
+**Research Stats:** 8 Reddit threads (455 upvotes) + 31 X posts (183 likes, 68 reposts) from r/nanobanana2pro, r/promptingmagic, @Xmira_belle (106 likes), @Cicily_aura (45 likes)
+
+**Then asked:** "make a mock-up of an app for moms who swim"
+
+**Generated Prompt:**
+
+```json
+{
+ "image_type": "UI mockup",
+ "device": {
+ "frame": "iPhone 16 Pro",
+ "display": "realistic screen with subtle reflection",
+ "orientation": "portrait"
+ },
+ "app_concept": "SwimMom - fitness and community app for mothers who swim",
+ "screen": "home dashboard",
+ "design_system": {
+ "style": "iOS 18 native",
+ "corners": "rounded, 16px radius",
+ "shadows": "soft drop shadows, subtle depth",
+ "spacing": "8pt grid, generous whitespace"
+ },
+ "color_palette": {
+ "primary": "calming aqua blue (#4ECDC4)",
+ "secondary": "warm coral (#FF6B6B)",
+ "background": "clean white with soft blue gradient header"
+ },
+ "layout": {
+ "header": "greeting 'Good morning, Sarah' with wave icon, profile avatar top right",
+ "hero_card": "today's swim stats - laps, calories, time - with circular progress ring",
+ "section_2": "horizontal scroll of upcoming mom swim meetups with location pills",
+ "section_3": "two cards - 'My Goals' with streak counter, 'Find a Pool' with map pin",
+ "bottom_nav": "5 icons - Home (active), Workouts, Community, Schedule, Profile"
+ },
+ "visual_details": {
+ "illustrations": "friendly, minimal line art of swimming figure",
+ "typography": "SF Pro Display, clean hierarchy",
+ "mood": "energizing yet calm, supportive community feel"
+ }
+}
+```
+
+**The Result:**
+
+
+ 
+
+
+This example shows /last30days learning that **JSON prompts dominate** the Nano Banana Pro community (not plain text), then applying that format to generate an iOS mockup in one shot. The research came from real X creators and Reddit threads — techniques you wouldn't find in official docs.
+
+---
+
## Example: Legal Prompting (Hallucination Prevention)
**Query:** `/last30days prompting techniques for chatgpt for legal questions`
@@ -203,75 +273,6 @@ This example shows /last30days as a **setup guide aggregator** - pulling togethe
---
-## Example: iOS App Mockup (Nano Banana Pro)
-
-**Query:** `/last30days prompting tips for nano banana pro for ios designs`
-
-**Research Output:**
-> The community has converged on JSON-structured prompts for UI work - multiple viral posts from @brindleyai, @bananababydoll, and @fofrAI use detailed JSON with nested objects for subject, scene, and style. The key workflow from @fofrAI: take an existing image, have Gemini generate a JSON prompt from it, then iterate. For iOS specifically, @paji_a and @chongdashu both documented using Nano Banana Pro for iOS app mockup designs in "vibe coding" workflows.
->
-> The web guides emphasize thinking in layers: define the window frame first, then UI layout (sidebars, nav bars, cards), then text on buttons/headings. Google's official prompting guide says to drop the "4k masterpiece trending on artstation" spam - Nano Banana Pro understands natural language. For tight layouts, use an 8pt grid and limit screens to 6-8 elements.
-
-**Key patterns discovered:**
-1. JSON prompt format with nested sections (subject, scene, style, device)
-2. Layer-based structure - frame -> layout regions -> content -> text labels
-3. iOS 18 / Material Design 3 references - rounded corners, soft shadows, vibrant primary
-4. iPhone frame specification - "inside realistic iPhone 16 Pro frame"
-5. Wireframe-to-mockup workflow - upload sketch, request high-fidelity conversion
-6. 8pt grid + 6-8 elements max per screen for clean density
-7. Iterative editing - don't re-roll, ask for specific changes if 80% correct
-
-**Then asked:** "make a mock-up of an app for moms who swim"
-
-**Generated Prompt:**
-
-```json
-{
- "image_type": "UI mockup",
- "device": {
- "frame": "iPhone 16 Pro",
- "display": "realistic screen with subtle reflection",
- "orientation": "portrait"
- },
- "app_concept": "SwimMom - fitness and community app for mothers who swim",
- "screen": "home dashboard",
- "design_system": {
- "style": "iOS 18 native",
- "corners": "rounded, 16px radius",
- "shadows": "soft drop shadows, subtle depth",
- "spacing": "8pt grid, generous whitespace"
- },
- "color_palette": {
- "primary": "calming aqua blue (#4ECDC4)",
- "secondary": "warm coral (#FF6B6B)",
- "background": "clean white with soft blue gradient header",
- "accents": "pool water ripple patterns, subtle"
- },
- "layout": {
- "header": "greeting 'Good morning, Sarah' with small wave icon, profile avatar top right",
- "hero_card": "today's swim stats - laps completed, calories burned, time in pool - with circular progress ring",
- "section_2": "horizontal scroll of upcoming mom swim meetups with location pills and participant avatars",
- "section_3": "two cards side by side - 'My Goals' with streak counter, 'Find a Pool' with map pin icon",
- "bottom_nav": "5 icons - Home (active), Workouts, Community, Schedule, Profile"
- },
- "visual_details": {
- "illustrations": "friendly, minimal line art of swimming figure",
- "typography": "SF Pro Display, clean hierarchy",
- "mood": "energizing yet calm, supportive community feel"
- }
-}
-```
-
-**The Result:**
-
-
-
-
-
-This example shows /last30days learning **AI image generation prompting patterns** (JSON structure, layer-based thinking, iOS design system references) and applying them to create a production-quality app mockup in one shot.
-
----
-
## Example: Top Claude Code Skills (Recommendations)
**Query:** `/last30days top claude code skills`