diff --git a/AGENTS.md b/AGENTS.md
index a15b55d..5b2a7be 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -5,15 +5,9 @@ etc.) when working with code in this repository.
 
 ## Repository Overview
 
-A collection of Postgres best practices skills for AI coding agents,
-maintained by Supabase. Skills are packaged instructions that extend agent
-capabilities for database optimization.
-
-## Installation
-
-```bash
-npx skills add supabase/agent-skills
-```
+A collection of Postgres best practices skills for AI coding agents, maintained
+by Supabase. Skills are packaged instructions that extend agent capabilities for
+database optimization.
 
 ## Creating a New Rule
 
@@ -65,7 +59,6 @@ tags: relevant, keywords
 -- Comment explaining what's wrong
 [Bad SQL example]
 ```
-````
 
 **Correct (description):**
 
@@ -73,12 +66,8 @@ tags: relevant, keywords
 -- Comment explaining why this is better
 [Good SQL example]
 ```
-
-**Supabase Note:** [Optional platform-specific guidance]
-
-Reference: [Link](url)
-
 ````
+
 ### Best Practices for Context Efficiency
 
 Skills are loaded on-demand. To minimize context usage:
@@ -98,7 +87,7 @@ cd packages/postgres-best-practices-build
 npm install
 npm run validate  # Check rule format
 npm run build     # Generate AGENTS.md
-````
+```
 
 ### Impact Levels
 
@@ -123,4 +112,3 @@ npm run build     # Generate AGENTS.md
 | `data-`     | Data Access Patterns     | 6 (MEDIUM)      |
 | `monitor-`  | Monitoring & Diagnostics | 7 (LOW-MEDIUM)  |
 | `advanced-` | Advanced Features        | 8 (LOW)         |
-
diff --git a/packages/postgres-best-practices-build/src/build.ts b/packages/postgres-best-practices-build/src/build.ts
index d1a13fe..152c152 100644
--- a/packages/postgres-best-practices-build/src/build.ts
+++ b/packages/postgres-best-practices-build/src/build.ts
@@ -202,10 +202,6 @@ function buildAgents(): void {
         }
       }
 
-      if (rule.supabaseNotes) {
-        output.push(`**Supabase Note:** ${rule.supabaseNotes}\n`);
-      }
-
       if (rule.references && rule.references.length > 0) {
         if (rule.references.length === 1) {
           output.push(`Reference: ${rule.references[0]}\n`);
diff --git a/packages/postgres-best-practices-build/src/parser.ts b/packages/postgres-best-practices-build/src/parser.ts
index ddca1cc..5fbc9fb 100644
--- a/packages/postgres-best-practices-build/src/parser.ts
+++ b/packages/postgres-best-practices-build/src/parser.ts
@@ -194,14 +194,6 @@ function extractReferences(body: string): string[] {
   return references;
 }
 
-/**
- * Extract Supabase notes
- */
-function extractSupabaseNotes(body: string): string | undefined {
-  const match = body.match(/\*\*Supabase Note:\*\*\s*(.+?)(?=\n\n|\n\*\*|$)/s);
-  return match ? match[1].trim() : undefined;
-}
-
 /**
  * Parse a rule file and return structured data
  */
@@ -237,8 +229,7 @@ export function parseRuleFile(filePath: string): ParseResult {
     // Extract other fields
     const explanation = extractExplanation(body);
     const examples = extractExamples(body);
-    const references = extractReferences(body);
-    const supabaseNotes = extractSupabaseNotes(body);
+
     const tags = frontmatter.tags?.split(",").map((t) => t.trim()) || [];
 
     // Validation warnings
@@ -258,9 +249,8 @@ export function parseRuleFile(filePath: string): ParseResult {
       impactDescription: frontmatter.impactDescription,
       explanation,
       examples,
-      references: references.length > 0 ? references : undefined,
+      references: extractReferences(body),
       tags: tags.length > 0 ? tags : undefined,
-      supabaseNotes,
     };
 
     return { success: true, rule, errors, warnings };
diff --git a/skills/postgres-best-practices/rules/_contributing.md b/skills/postgres-best-practices/rules/_contributing.md
index 975364a..99686a9 100644
--- a/skills/postgres-best-practices/rules/_contributing.md
+++ b/skills/postgres-best-practices/rules/_contributing.md
@@ -27,12 +27,12 @@ to recognize anti-patterns.
 
 Include specific metrics. Helps agents prioritize fixes.
 
-**Good:** "10x faster queries", "50% smaller index", "Eliminates N+1" **Bad:**
-"Faster", "Better", "More efficient"
+**Good:** "10x faster queries", "50% smaller index", "Eliminates N+1" 
+**Bad:** "Faster", "Better", "More efficient"
 
 ### 4. Self-Contained Examples
 
-Examples should be complete and runnable (or close to it). Include CREATE TABLE
+Examples should be complete and runnable (or close to it). Include `CREATE TABLE`
 if context is needed.
 
 ```sql
@@ -51,8 +51,8 @@ CREATE INDEX users_active_email_idx ON users(email) WHERE deleted_at IS NULL;
 
 Use meaningful table/column names. Names carry intent for LLMs.
 
-**Good:** `users`, `email`, `created_at`, `is_active` **Bad:** `table1`, `col1`,
-`field`, `flag`
+**Good:** `users`, `email`, `created_at`, `is_active`
+**Bad:** `table1`, `col1`, `field`, `flag`
 
 ---
 
@@ -120,7 +120,6 @@ const posts = await db.query("SELECT * FROM posts WHERE user_id = ANY($1)", [
 ]);
 ```
 
-````
 ---
 
 ## Impact Level Guidelines
@@ -136,24 +135,6 @@ const posts = await db.query("SELECT * FROM posts WHERE user_id = ANY($1)", [
 
 ---
 
-## Supabase-Specific Notes
-
-**When to Add:**
-- Supavisor pooling configuration
-- Dashboard features (index monitoring, query stats)
-- RLS patterns specific to Supabase auth
-- PostgREST implications
-
-**Format:**
-```markdown
-**Supabase Note:** The Dashboard > Database > Indexes page shows index usage statistics.
-````
-
-**Balance:** ~10% of content should be Supabase-specific. Core rules should work
-on any Postgres.
-
----
-
 ## Reference Standards
 
 **Primary Sources:**