@salesforce/afv-skills 1.27.0 → 1.28.0

package/skills/platform-custom-field-generate/SKILL.md

@@ -135,7 +135,7 @@ The `<restricted>` boolean inside `<valueSet>` controls whether only admin-defin
 
 ---
 
-## 5. Master-Detail Relationship Rules ⭐ CRITICAL
+## 5. Master-Detail Relationship Rules CRITICAL
 
 Master-Detail fields have **strict attribute restrictions** that differ from Lookup fields. Violating these rules causes deployment failures.
 
@@ -160,7 +160,7 @@ Master-Detail fields have **strict attribute restrictions** that differ from Loo
 | `<reparentableMasterDetail>` | ✅ Optional | ❌ Not applicable |
 | `<writeRequiresMasterRead>` | ✅ Optional | ❌ Not applicable |
 
-### ❌ INCORRECT — Master-Detail with forbidden attributes:
+### INCORRECT — Master-Detail with forbidden attributes:
 
 ```xml
 <CustomField xmlns="http://soap.sforce.com/2006/04/metadata">
@@ -188,7 +188,7 @@ Master-Detail fields have **strict attribute restrictions** that differ from Loo
 - `Can not specify 'deleteConstraint' for a CustomField of type MasterDetail`
 - `Lookup filters are only supported on Lookup Relationship Fields`
 
-### ✅ CORRECT — Master-Detail field:
+### CORRECT — Master-Detail field:
 
 ```xml
 <CustomField xmlns="http://soap.sforce.com/2006/04/metadata">
@@ -206,7 +206,7 @@ Master-Detail fields have **strict attribute restrictions** that differ from Loo
 </CustomField>
 ```
 
-### ✅ CORRECT — Lookup field (with optional attributes):
+### CORRECT — Lookup field (with optional attributes):
 
 ```xml
 <CustomField xmlns="http://soap.sforce.com/2006/04/metadata">
@@ -240,7 +240,7 @@ Master-Detail fields have **strict attribute restrictions** that differ from Loo
 
 ---
 
-## 6. Roll-Up Summary Field Rules ⭐ CRITICAL
+## 6. Roll-Up Summary Field Rules CRITICAL
 
 Roll-up Summary fields have the **highest deployment failure rate**. Follow these rules exactly.
 
@@ -276,7 +276,7 @@ ChildObjectAPIName__c.FieldAPIName__c
 - `summaryForeignKey` = `ChildObject__c.MasterDetailFieldOnChild__c`
 - `summarizedField` = `ChildObject__c.FieldToSummarize__c`
 
-### ❌ INCORRECT — Roll-Up Summary with common errors:
+### INCORRECT — Roll-Up Summary with common errors:
 
 ```xml
 <CustomField xmlns="http://soap.sforce.com/2006/04/metadata">
@@ -295,7 +295,7 @@ ChildObjectAPIName__c.FieldAPIName__c
 - `Can not specify 'precision' for a CustomField of type Summary`
 - `Must specify the name in the CustomObject.CustomField format (e.g. Account.MyNewCustomField)`
 
-### ✅ CORRECT — Roll-Up Summary (SUM operation):
+### CORRECT — Roll-Up Summary (SUM operation):
 
 ```xml
 <CustomField xmlns="http://soap.sforce.com/2006/04/metadata">
@@ -393,7 +393,7 @@ A Formula is not a type itself. The `<formula>` tag is added to a field whose `<
 - IF formula result type = `Number`, `Currency`, or `Percent` → set `<formulaTreatBlanksAs>BlankAsZero</formulaTreatBlanksAs>`
 - IF formula result type = `Text`, `Date`, or `DateTime` → set `<formulaTreatBlanksAs>BlankAsBlank</formulaTreatBlanksAs>`
 
-### ❌ INCORRECT — Using Formula as type:
+### INCORRECT — Using Formula as type:
 
 ```xml
 <CustomField xmlns="http://soap.sforce.com/2006/04/metadata">
@@ -404,7 +404,7 @@ A Formula is not a type itself. The `<formula>` tag is added to a field whose `<
 </CustomField>
 ```
 
-### ✅ CORRECT — Formula field:
+### CORRECT — Formula field:
 
 ```xml
 <CustomField xmlns="http://soap.sforce.com/2006/04/metadata">
@@ -460,7 +460,7 @@ Before generating CustomField XML, verify:
 - [ ] Is `<label>` in Title Case?
 - [ ] Are there no XML comments (`<!-- ... -->`) before the root `<CustomField>` element? (Comments before the root element break SDR's parser)
 
-### Master-Detail Field Checks ⭐ CRITICAL
+### Master-Detail Field Checks CRITICAL
 - [ ] Is `<required>` attribute ABSENT? (Master-Detail is always required)
 - [ ] Is `<deleteConstraint>` attribute ABSENT? (Master-Detail always cascades)
 - [ ] Is `<lookupFilter>` block ABSENT? (Only for Lookup fields)
@@ -471,7 +471,7 @@ Before generating CustomField XML, verify:
 - [ ] Is `<deleteConstraint>` set to `SetNull`, `Restrict`, or `Cascade`?
 - [ ] Is `<relationshipName>` in plural PascalCase?
 
-### Roll-Up Summary Field Checks ⭐ CRITICAL
+### Roll-Up Summary Field Checks CRITICAL
 - [ ] Is `<precision>` attribute ABSENT?
 - [ ] Is `<scale>` attribute ABSENT?
 - [ ] Is `<summaryForeignKey>` in format `ChildObject__c.MasterDetailField__c`?

package/skills/platform-custom-lightning-type-generate/references/widget-rendition.md

@@ -1,15 +1,15 @@
 # Widget Generation Guide
 
-## 📋 Overview
+## Overview
 Widgets are reusable pieces of UI similar to templates, with placeholders for actual data values. The purpose of this file is to assist developers in creating mosaic renditions for CLTs.
 
-## 🎯 Purpose
+## Purpose
 Widgets render data in a structured and unified way across various Salesforce experiences like Slack, Mobile, LEX etc.
 
 ## Schema Grounding
 Widget generation is **always schema-grounded** using a CLT's schema. The schema describes the data shape the widget should render. Extract property names, types, required vs optional, and nesting from the schema; then follow the full **Workflow** below, using this extracted structure to guide every step. Do not add or remove properties relative to the schema.
 
-## ⚙️ Composition
+## Composition
 A widget is a UEM (Unified Experience Model) tree of blocks and regions. The widget you return must follow the Typescript interfaces below:
 
 ```ts
@@ -28,7 +28,7 @@ interface RegionType {
 ```
 ---
 
-## 🔧 Available Metadata Actions
+## Available Metadata Actions
 
 ### When to Use Each Action
 
@@ -88,7 +88,7 @@ interface RegionType {
 
 ---
 
-## 💡Workflow
+## Workflow
 
 1. **Schema Parsing**
 - Parse the schema and extract: property names, types, required vs optional, and nested structure. Use this as the **widget spec**.
@@ -115,7 +115,7 @@ interface RegionType {
 
 ---
 
-## ⚠️ Important Notes
+## Important Notes
 
 - **widget spec** includes both required and optional attributes - review carefully to ensure valid configuration.
 - When using **`execute_metadata_action`** tool, always supply **`parameters`** with the required fields above; missing `parameters` or required keys causes hard failures, not partial results.

package/skills/platform-custom-tab-generate/SKILL.md

@@ -17,16 +17,16 @@ Use this skill when you need to:
 
 # CustomTab Metadata Specification
 
-## 📋 Overview
+## Overview
 Custom tabs for navigating to objects, web content, or Visualforce pages within Salesforce applications.
 
-## 🎯 Purpose
+## Purpose
 - Provide navigation to custom objects
 - Link to external web content
 - Access Visualforce pages
 - Organize application navigation
 
-## ⚙️ Required Properties
+## Required Properties
 
 ### Core Tab Properties
 - **customObject**: `true` for custom object tabs, `false` for all others.
@@ -36,7 +36,7 @@ Custom tabs for navigating to objects, web content, or Visualforce pages within
 - **page**: Visualforce page name (for Visualforce tabs)
 
 
-### 🚨 STRICT ELEMENT ALLOWLIST — READ THIS FIRST
+### STRICT ELEMENT ALLOWLIST — READ THIS FIRST
 
 **The root element MUST always be `<CustomTab>` (NOT `<Tab>`).** The XML namespace must be `xmlns="http://soap.sforce.com/2006/04/metadata"`.
 
@@ -48,7 +48,7 @@ Only the elements listed below are valid. **Any element not on this list WILL ca
 | **Web tabs** | `<customObject>` (required, set to `false`), `<label>` (required), `<motif>` (required), `<url>` (required), `<urlEncodingKey>` (required, set to `UTF-8`), `<description>` (optional), `<frameHeight>` (optional) |
 | **Visualforce tabs** | `<customObject>` (required, set to `false`), `<label>` (required), `<motif>` (required), `<page>` (required), `<description>` (optional) |
 
-### ⚠️ FORBIDDEN ELEMENTS (every one of these causes a deployment error)
+### FORBIDDEN ELEMENTS (every one of these causes a deployment error)
 `<sobjectName>`, `<name>`, `<fullName>`, `<apiVersion>`, `<isHidden>`, `<tabVisibility>`, `<type>`, `<mobileReady>`, `<urlFrameHeight>`, `<urlType>`, `<urlRedirect>`, `<encodingKey>`, `<height>`, `<auraComponent>`
 
 Also forbidden:
@@ -57,7 +57,7 @@ Also forbidden:
 - Empty elements like `<page></page>` or `<description></description>`
 - Any element not in the allowlist table above
 
-## 🔧 Tab Types
+## Tab Types
 
 ### Object Tabs
 - **Purpose**: Navigate to custom or standard objects
@@ -123,7 +123,7 @@ Also forbidden:
 </CustomTab>
 ```
 
-## 🎨 Tab Configuration
+## Tab Configuration
 
 ### Tab Style
 - **Default**: Use standard tab styling
@@ -133,17 +133,17 @@ Also forbidden:
 - **Default**: Visible to all users with access
 - **Custom**: Can be configured for specific user profiles
 
-## 📱 Supported Applications
+## Supported Applications
 - **Standard Apps**: Available in standard Salesforce applications
 - **Custom Apps**: Can be included in custom applications
 - **Community Apps**: Available in community applications
 
-## 🔗 Integration Points
+## Integration Points
 - **Object Relationships**: Links to related object records
 - **Web Content**: External website integration
 - **Visualforce Pages**: Custom page functionality
 - **Lightning Components**: Modern component integration
-## ✅ Best Practices
+## Best Practices
 - Use clear, descriptive tab labels
 - Choose appropriate tab types for functionality
 - **Select a unique, contextually relevant motif for each tab** — do not default every tab to the same icon

package/skills/platform-data-manage/references/orchestration.md

@@ -27,7 +27,7 @@ This document details how platform-data-manage fits into the multi-skill workflo
 
 ---
 
-## ⚠️ Why platform-data-manage Goes LAST
+## Why platform-data-manage Goes LAST
 
 **platform-data-manage operates on REMOTE org data.** Objects/fields must be deployed before platform-data-manage can:
 - Insert records

package/skills/platform-list-view-generate/SKILL.md

@@ -17,14 +17,14 @@ Use this skill when you need to:
 
 # Salesforce List View Metadata Knowledge
 
-## 📋 Overview
+## Overview
 Salesforce List Views define filtered, column-based record listings on an object's tab.
 
-## 🎯 Purpose
+## Purpose
 - Provide curated, role- or task-specific subsets of records
 - Standardize commonly used filters and visible fields across teams
 
-## 🔧 Configuration
+## Configuration
 
 Unless specifically requested to be generated inline, List Views are stored at:
 - force-app/main/default/objects/<ObjectName>/listViews/<fullName>.listView-meta.xml

package/skills/platform-metadata-api-context-get/README.md

@@ -49,7 +49,7 @@ This skill is designed for use with Claude Code. To use it:
 
 - **SKILL.md**: Complete skill documentation with usage guidelines
 - **references/metadata_index_table.md**: Index of all metadata types
-- **data/metadata_api/**: JSON files for each metadata type
+- **assets/metadata_api/**: JSON files for each metadata type
 
 ## Token Optimization
 

package/skills/platform-metadata-api-context-get/SKILL.md

@@ -28,11 +28,11 @@ The Salesforce Metadata API allows you to retrieve, deploy, create, update, or d
 
 ## How to Use This Skill
 
-### ⚡ CRITICAL: Section-Specific Consumption
+### CRITICAL: Section-Specific Consumption
 
 **ALWAYS consume only the specific sections you need from JSON files, NOT entire files.**
 
-**CRITICAL: For `data/metadata_api/*.json` files, always use `jq` or programmatic JSON parsing to extract only the specific sections you need.** Do not load these files whole via `Read`, `cat`, `read_file`, or any other tool that injects the complete file — they contain verbose WSDL segments and other sections that waste 60-80% of tokens. (Loading small files like this SKILL.md or the index table with `Read` is fine; the rule applies specifically to the large metadata-type JSON files.)
+**CRITICAL: For `assets/metadata_api/*.json` files, always use `jq` or programmatic JSON parsing to extract only the specific sections you need.** Do not load these files whole via `Read`, `cat`, `read_file`, or any other tool that injects the complete file — they contain verbose WSDL segments and other sections that waste 60-80% of tokens. (Loading small files like this SKILL.md or the index table with `Read` is fine; the rule applies specifically to the large metadata-type JSON files.)
 
 Each JSON file contains multiple sections (fields, description, wsdl_segment, etc.). Most use cases only require 1-2 sections:
 
@@ -62,7 +62,7 @@ To get information about a specific metadata type:
 
 ## JSON File Structure
 
-Each metadata type is stored as a JSON file in `data/metadata_api/` with the following structure:
+Each metadata type is stored as a JSON file in `assets/metadata_api/` with the following structure:
 
 ```json
 {
@@ -142,13 +142,13 @@ See [`examples/README.md`](examples/README.md) for complete documentation and us
 
 **❌ NEVER use the `read_file` tool on these JSON files**:
 ```text
-read_file data/metadata_api/CustomObject.json  # Loads entire file into context!
-read_file data/metadata_api/Flow.json          # Wastes 60-80% tokens!
+read_file assets/metadata_api/CustomObject.json  # Loads entire file into context!
+read_file assets/metadata_api/Flow.json          # Wastes 60-80% tokens!
 ```
 
 **❌ NEVER load all files**:
 ```text
-read_file data/metadata_api/*.json  # This loads ~15MB of data!
+read_file assets/metadata_api/*.json  # This loads ~15MB of data!
 ```
 
 **Token Impact**:
@@ -194,7 +194,7 @@ Use one of these methods:
 - **Index search**: Check `references/metadata_index_table.md` for related types
 - **Common types**: See the "Quick Reference: Common Metadata Types" section below
 
-### Step 3: Load Selectively (Section-Specific) ⚡
+### Step 3: Load Selectively (Section-Specific)
 
 **Decision Tree for Section Loading**:
 
@@ -235,7 +235,7 @@ Use the loaded information to:
 All metadata type JSON files are located in:
 
 ```text
-data/metadata_api/
+assets/metadata_api/
 ├── CustomObject.json
 ├── Flow.json
 ├── ApexClass.json
@@ -247,8 +247,8 @@ data/metadata_api/
 ### Path Resolution
 
 When using this skill, files are referenced as:
-- Absolute: `data/metadata_api/CustomObject.json`
-- Relative to skill root: `./data/metadata_api/CustomObject.json`
+- Absolute: `assets/metadata_api/CustomObject.json`
+- Relative to skill root: `./assets/metadata_api/CustomObject.json`
 
 The skill will automatically resolve paths based on the working directory.
 
@@ -409,11 +409,11 @@ When the `fields` section gives a complex type name like `ProfileObjectPermissio
 
 ```bash
 # 1. Get the field type name from the fields section
-jq '.fields.objectPermissions' data/metadata_api/Profile.json
+jq '.fields.objectPermissions' assets/metadata_api/Profile.json
 # → {"type": "ProfileObjectPermissions[]", ...}
 
 # 2. Pull just the matching complexType from wsdl_segment using grep -A
-jq -r '.wsdl_segment' data/metadata_api/Profile.json   | grep -A 30 'complexType name="ProfileObjectPermissions"'
+jq -r '.wsdl_segment' assets/metadata_api/Profile.json   | grep -A 30 'complexType name="ProfileObjectPermissions"'
 ```
 
 The `grep -A N` window keeps token cost ~150 tokens instead of loading the whole `wsdl_segment` (which can be 5K+ tokens on large types). Use this pattern any time `fields` returns a `Foo[]` type and you need Foo's sub-fields.

package/skills/platform-metadata-api-context-get/examples/README.md

@@ -2,7 +2,7 @@
 
 This directory contains working code examples demonstrating how to programmatically load only specific sections from metadata JSON files.
 
-## ⚠️ Critical Warning
+## Critical Warning
 
 **NEVER use built-in tools like Read, cat, or any other tool that loads entire JSON files into context!**
 
@@ -27,7 +27,7 @@ python3 examples/python_section_loading.py
 **Key Pattern**:
 ```python
 import json
-with open('data/metadata_api/CustomObject.json') as f:
+with open('assets/metadata_api/CustomObject.json') as f:
     data = json.load(f)
     fields_only = data.get('fields', {})  # Only extract 'fields'
 ```
@@ -49,7 +49,7 @@ node examples/javascript_section_loading.js
 **Key Pattern**:
 ```javascript
 const fs = require('fs');
-const data = JSON.parse(fs.readFileSync('data/metadata_api/CustomObject.json', 'utf-8'));
+const data = JSON.parse(fs.readFileSync('assets/metadata_api/CustomObject.json', 'utf-8'));
 const fieldsOnly = data.fields || {};  // Only extract 'fields'
 ```
 
@@ -82,7 +82,7 @@ chmod +x examples/bash_section_loading.sh
 **Key Pattern**:
 ```bash
 # Extract only the 'fields' section
-jq '.fields' data/metadata_api/CustomObject.json
+jq '.fields' assets/metadata_api/CustomObject.json
 ```
 
 ## Token Savings
@@ -130,23 +130,23 @@ Choose based on your need:
 
 ## Anti-Patterns (What NOT to Do)
 
-### ❌ Wrong: Using Read Tool
+### Wrong: Using Read Tool
 ```bash
 # This loads the ENTIRE file into context (2,000 tokens)
-Read data/metadata_api/CustomObject.json
+Read assets/metadata_api/CustomObject.json
 ```
 
-### ❌ Wrong: Using cat/type
+### Wrong: Using cat/type
 ```bash
 # This loads the ENTIRE file into context (2,000 tokens)
-cat data/metadata_api/CustomObject.json
-type data/metadata_api/CustomObject.json
+cat assets/metadata_api/CustomObject.json
+type assets/metadata_api/CustomObject.json
 ```
 
-### ✅ Correct: Programmatic Section Extraction
+### Correct: Programmatic Section Extraction
 ```bash
 # This loads only the 'fields' section (200 tokens)
-jq '.fields' data/metadata_api/CustomObject.json
+jq '.fields' assets/metadata_api/CustomObject.json
 ```
 
 ## Adapting to Other Languages

package/skills/platform-metadata-api-context-get/examples/bash_section_loading.sh

@@ -17,7 +17,7 @@
 # Ensure jq is available before doing anything else
 command -v jq >/dev/null 2>&1 || { echo "Error: jq is required but not installed." >&2; exit 1; }
 
-METADATA_DIR="data/metadata_api"
+METADATA_DIR="assets/metadata_api"
 
 
 # Example 1: Load ONLY the 'fields' section from CustomObject.json
@@ -115,10 +115,10 @@ extract_specific_fields() {
 # This is what NOT to do - it loads the entire file into context:
 #
 # Read tool approach (WRONG):
-# Read data/metadata_api/CustomObject.json  # Loads ALL sections!
+# Read assets/metadata_api/CustomObject.json  # Loads ALL sections!
 #
 # cat approach (WRONG):
-# cat data/metadata_api/CustomObject.json  # Loads entire file!
+# cat assets/metadata_api/CustomObject.json  # Loads entire file!
 #
 # This injects the entire file (including massive WSDL segments)
 # into your context, wasting 60-80% of tokens.

package/skills/platform-metadata-api-context-get/examples/javascript_section_loading.js

@@ -32,7 +32,7 @@ function loadMetadataJson(metadataFile) {
  * Token savings: ~70-80% compared to loading entire file
  */
 function loadSingleSectionExample() {
-    const metadataFile = path.join('data', 'metadata_api', 'CustomObject.json');
+    const metadataFile = path.join('assets', 'metadata_api', 'CustomObject.json');
 
     // Read and parse the JSON file
     const data = loadMetadataJson(metadataFile);
@@ -52,7 +52,7 @@ function loadSingleSectionExample() {
  * Token savings: ~60-75% compared to loading entire file
  */
 function loadMultipleSectionsExample() {
-    const metadataFile = path.join('data', 'metadata_api', 'Flow.json');
+    const metadataFile = path.join('assets', 'metadata_api', 'Flow.json');
 
     const data = loadMetadataJson(metadataFile);
 
@@ -72,7 +72,7 @@ function loadMultipleSectionsExample() {
  * Best practice: Always check what sections are available
  */
 function loadWithSectionCheck() {
-    const metadataFile = path.join('data', 'metadata_api', 'Profile.json');
+    const metadataFile = path.join('assets', 'metadata_api', 'Profile.json');
 
     const data = loadMetadataJson(metadataFile);
 
@@ -102,7 +102,7 @@ function loadWithSectionCheck() {
  * Example 4: Async/Promise version (modern Node.js)
  */
 async function loadSingleSectionAsync() {
-    const metadataFile = path.join('data', 'metadata_api', 'ApexClass.json');
+    const metadataFile = path.join('assets', 'metadata_api', 'ApexClass.json');
 
     // Use async file operations
     const fileContent = await fs.promises.readFile(metadataFile, 'utf-8');
@@ -127,7 +127,7 @@ async function loadSingleSectionAsync() {
  * This is what NOT to do - it loads the entire file into context:
  *
  * // Read tool approach (WRONG):
- * // Read data/metadata_api/CustomObject.json  // Loads ALL sections!
+ * // Read assets/metadata_api/CustomObject.json  // Loads ALL sections!
  *
  * // This injects the entire file (including massive WSDL segments)
  * // into your context, wasting 60-80% of tokens.

package/skills/platform-metadata-api-context-get/examples/python_section_loading.py

@@ -14,7 +14,7 @@ from pathlib import Path
 
 # Resolve the data directory relative to this file, so the examples work
 # regardless of the current working directory.
-METADATA_DIR = Path(__file__).resolve().parent.parent / 'data' / 'metadata_api'
+METADATA_DIR = Path(__file__).resolve().parent.parent / 'assets' / 'metadata_api'
 
 
 def load_single_section_example():
@@ -93,7 +93,7 @@ def wrong_approach_example():
     This is what NOT to do - it loads the entire file into context:
 
     # Read tool approach (WRONG):
-    # Read data/metadata_api/CustomObject.json  # Loads ALL sections!
+    # Read assets/metadata_api/CustomObject.json  # Loads ALL sections!
 
     # This injects the entire file (including massive WSDL segments)
     # into your context, wasting 60-80% of tokens.

package/skills/platform-metadata-api-context-get/references/usage_guide.md

@@ -95,7 +95,7 @@ Approximate token counts for different loading strategies:
 **User**: "I need to create a custom object metadata file for a Student object"
 
 **Response approach** (Token-efficient):
-1. Load ONLY the `fields` section from `data/metadata_api/CustomObject.json`
+1. Load ONLY the `fields` section from `assets/metadata_api/CustomObject.json`
 2. Review required fields: `label`, `nameField`, `deploymentStatus`, `sharingModel`
 3. If needed, also load the `declarative_metadata_sample_definition` section for XML structure example
 4. Generate XML with correct namespace
@@ -108,7 +108,7 @@ Approximate token counts for different loading strategies:
 **User**: "What fields are available in a Flow metadata type?"
 
 **Response approach** (Token-efficient):
-1. Load ONLY the `fields` section from `data/metadata_api/Flow.json`
+1. Load ONLY the `fields` section from `assets/metadata_api/Flow.json`
 2. List field names, types, and descriptions
 3. Highlight required fields and common patterns
 4. Skip `wsdl_segment`, `description`, and other sections
@@ -120,7 +120,7 @@ Approximate token counts for different loading strategies:
 **User**: "How do I add object permissions to a Profile?"
 
 **Response approach** (Token-efficient):
-1. Load ONLY the `fields` section from `data/metadata_api/Profile.json`
+1. Load ONLY the `fields` section from `assets/metadata_api/Profile.json`
 2. Find `objectPermissions` field definition within that section
 3. Show structure and required sub-fields
 4. If XML example needed, separately load `declarative_metadata_sample_definition`
@@ -132,7 +132,7 @@ Approximate token counts for different loading strategies:
 **User**: "What's the metadata file structure for an Apex class?"
 
 **Response approach** (Token-efficient):
-1. Load the `fields` and `description` sections from `data/metadata_api/ApexClass.json`
+1. Load the `fields` and `description` sections from `assets/metadata_api/ApexClass.json`
 2. Show the simple structure (apiVersion, status)
 3. Explain the relationship between `.cls` and `.cls-meta.xml` files
 4. Load `file_information` section only if directory structure details needed

package/skills/platform-metadata-retrieve/SKILL.md

@@ -12,7 +12,7 @@ Retrieves metadata from a Salesforce org to your local project using `sf project
 
 ---
 
-## ⚠️ Tool Restrictions
+## Tool Restrictions
 
 **Use ONLY the Bash tool** to execute `sf project retrieve start`. Do NOT use MCP tools — ignore them completely.
 

package/skills/platform-soql-query/references/field-coverage-rules.md

@@ -36,7 +36,7 @@ This error is particularly common in LLM-generated code because the LLM may:
 
 ### Rule: Every field accessed must be in the SELECT clause
 
-### ❌ BAD: Accessing Unqueried Fields
+### BAD: Accessing Unqueried Fields
 
 ```apex
 // Query only includes Id and Name
@@ -54,7 +54,7 @@ for (Account acc : accounts) {
 }
 ```
 
-### ✅ GOOD: Query All Accessed Fields
+### GOOD: Query All Accessed Fields
 
 ```apex
 // Query ALL fields that will be accessed
@@ -91,7 +91,7 @@ Fields can be accessed in many places—ensure coverage for all:
 
 ### Rule: Parent relationship fields require dot notation in SELECT
 
-### ❌ BAD: Missing Relationship Fields
+### BAD: Missing Relationship Fields
 
 ```apex
 // Contact query without Account relationship fields
@@ -108,7 +108,7 @@ for (Contact c : contacts) {
 }
 ```
 
-### ✅ GOOD: Include Relationship Fields
+### GOOD: Include Relationship Fields
 
 ```apex
 // Use dot notation to include parent fields
@@ -136,7 +136,7 @@ for (Contact c : contacts) {
 | Parent (lookup/master-detail) | 5 levels | `Contact.Account.Owner.Manager.Name` |
 | Child (subquery) | 1 level | `Account -> Contacts` (cannot nest subqueries) |
 
-### ❌ BAD: Assuming Relationship is Populated
+### BAD: Assuming Relationship is Populated
 
 ```apex
 List<Contact> contacts = [SELECT Id, AccountId FROM Contact];
@@ -150,7 +150,7 @@ for (Contact c : contacts) {
 }
 ```
 
-### ✅ GOOD: Query Relationship or Use Separate Query
+### GOOD: Query Relationship or Use Separate Query
 
 ```apex
 // Option 1: Include relationship field
@@ -189,7 +189,7 @@ for (Contact c : contacts) {
 
 ### Rule: Dynamic field access (using `get()`) also requires queried fields
 
-### ❌ BAD: Dynamic Access to Unqueried Field
+### BAD: Dynamic Access to Unqueried Field
 
 ```apex
 List<Account> accounts = [SELECT Id, Name FROM Account];
@@ -201,7 +201,7 @@ for (Account acc : accounts) {
 }
 ```
 
-### ✅ GOOD: Query Fields Used Dynamically
+### GOOD: Query Fields Used Dynamically
 
 ```apex
 // If you know which fields will be accessed dynamically, query them
@@ -213,7 +213,7 @@ for (Account acc : accounts) {
 }
 ```
 
-### ✅ GOOD: Build Dynamic Query
+### GOOD: Build Dynamic Query
 
 ```apex
 // For truly dynamic scenarios, build the query dynamically
@@ -232,7 +232,7 @@ List<Account> accounts = Database.query(query);
 
 ### Rule: Aggregate queries return `AggregateResult`, not sObjects
 
-### ❌ BAD: Treating Aggregate as sObject
+### BAD: Treating Aggregate as sObject
 
 ```apex
 // This returns AggregateResult, not Account
@@ -255,7 +255,7 @@ for (AggregateResult ar : results) {
 }
 ```
 
-### ✅ GOOD: Use get() for Aggregate Results
+### GOOD: Use get() for Aggregate Results
 
 ```apex
 AggregateResult[] results = [
@@ -291,7 +291,7 @@ for (AggregateResult ar : results) {
 
 ### Rule: Child relationship subqueries create nested lists
 
-### ❌ BAD: Accessing Subquery Fields Incorrectly
+### BAD: Accessing Subquery Fields Incorrectly
 
 ```apex
 // Query with contact subquery
@@ -312,7 +312,7 @@ for (Account acc : accounts) {
 }
 ```
 
-### ✅ GOOD: Proper Subquery Field Access
+### GOOD: Proper Subquery Field Access
 
 ```apex
 // Query all needed fields in subquery