@intentsolutionsio/make-scenario-builder 1.0.0 → 1.0.6

package/README.md

@@ -6,12 +6,12 @@ Create visual Make.com automation scenarios with AI assistance - perfect for no-
 
 Make.com (formerly Integromat) is a powerful visual automation platform:
 
--  **Visual Design** - See your entire workflow at a glance
--  **1000+ Integrations** - Connect virtually any app
--  **No-Code** - Build complex automations without coding
--  **Powerful Features** - Routers, filters, error handlers
--  **Affordable** - More cost-effective than Zapier
--  **Scalable** - Handle complex multi-step workflows
+- **Visual Design** - See your entire workflow at a glance
+- **1000+ Integrations** - Connect virtually any app
+- **No-Code** - Build complex automations without coding
+- **Powerful Features** - Routers, filters, error handlers
+- **Affordable** - More cost-effective than Zapier
+- **Scalable** - Handle complex multi-step workflows
 - ️ **Built-in Error Handling** - Visual error routes
 
 ## FREE Alternative: Use n8n + Ollama (Self-Hosted)
@@ -34,6 +34,7 @@ Make.com (formerly Integromat) is a powerful visual automation platform:
 ### Why n8n + Ollama?
 
 **n8n (Self-Hosted Automation)**:
+
 - Visual workflow builder (same as Make.com)
 - 400+ integrations (vs Make's 1000+, but covers 90% of use cases)
 - Advanced error handling
@@ -41,6 +42,7 @@ Make.com (formerly Integromat) is a powerful visual automation platform:
 - Open-source = community support
 
 **Ollama (Local LLM)**:
+
 - Runs Llama 3.2, Mistral, CodeLlama locally
 - No API keys required
 - Privacy-first (data never leaves your machine)
@@ -87,7 +89,7 @@ curl -fsSL https://ollama.com/install.sh | sh
 ollama pull llama3.2
 ```
 
-See [ollama-local-ai](../../../ai-ml/ollama-local-ai/) plugin for detailed setup.
+See ollama-local-ai plugin for detailed setup.
 
 #### 3. Connect Ollama to n8n
 
@@ -140,12 +142,14 @@ Action: Google Sheets Add Row (n8n)
 ### Real Use Case: AI Email Assistant
 
 #### Make.com + OpenAI Version
+
 - Make.com Core: $9/mo
 - OpenAI API: ~$30/mo (1000 emails)
 - **Total: $39/mo**
 
 #### n8n + Ollama Version
-```javascript
+
+```text
 // n8n HTTP Request Node
 {
   "method": "POST",
@@ -157,6 +161,7 @@ Action: Google Sheets Add Row (n8n)
   }
 }
 ```
+
 - n8n (self-hosted): $0
 - Ollama (local): $0
 - **Total: $0/mo**
@@ -165,7 +170,8 @@ Action: Google Sheets Add Row (n8n)
 
 ### n8n Workflow Templates
 
-**Available in [n8n-workflow-designer](../../n8n-workflow-designer/) plugin:**
+**Available in n8n-workflow-designer plugin:**
+
 - AI email automation
 - Lead scoring & routing
 - Content distribution
@@ -185,12 +191,14 @@ Action: Google Sheets Add Row (n8n)
 ### When to Use Make.com vs n8n
 
 **Use Make.com if:**
+
 - You need 1000+ integrations (vs n8n's 400+)
 - You prefer managed hosting (no DevOps)
 - Your team is non-technical
 - Budget allows $39-89/month
 
 **Use n8n + Ollama if:**
+
 - You want unlimited operations
 - You need privacy/compliance (HIPAA, GDPR)
 - You have basic Docker skills
@@ -199,9 +207,9 @@ Action: Google Sheets Add Row (n8n)
 ### Resources
 
 - **n8n Docs:** [docs.n8n.io](https://docs.n8n.io)
-- **Ollama Setup:** Use `/setup-ollama` command from [ollama-local-ai](../../../ai-ml/ollama-local-ai/) plugin
-- **n8n Workflows:** Install [n8n-workflow-designer](../../n8n-workflow-designer/) plugin
-- **Migration Guide:** [n8n vs Make.com](https://docs.n8n.io/integrations/make-to-n8n/)
+- **Ollama Setup:** Use `/setup-ollama` command from ollama-local-ai plugin
+- **n8n Workflows:** Install n8n-workflow-designer plugin
+- **Migration Guide:** n8n vs Make.com
 
 **Bottom Line:** If you're comfortable with Docker and want to save $468+/year, n8n + Ollama is the superior choice.
 
@@ -217,6 +225,7 @@ Action: Google Sheets Add Row (n8n)
 ## Features
 
 ### Scenario Design
+
 - **Visual Workflows** - Clear module-by-module design
 - **Routers & Filters** - Conditional logic and branching
 - **Data Mapping** - Transform data between apps
@@ -225,12 +234,14 @@ Action: Google Sheets Add Row (n8n)
 - **Aggregators** - Combine multiple items
 
 ### AI Integration
+
 - **OpenAI** - Native GPT integration
 - **Anthropic Claude** - Via HTTP module
 - **Custom AI** - Connect any AI API
 - **Prompt Design** - Optimized prompts included
 
 ### Module Types
+
 - **Triggers** - Webhooks, scheduled, polling
 - **Actions** - Create, update, search, delete
 - **Tools** - Router, iterator, aggregator, filter
@@ -246,6 +257,7 @@ Action: Google Sheets Add Row (n8n)
 ## Example Scenarios
 
 ### 1. AI Email Assistant
+
 ```
 Gmail Trigger → OpenAI Response → Send Reply → Log to Sheets
 ```
@@ -255,6 +267,7 @@ Gmail Trigger → OpenAI Response → Send Reply → Log to Sheets
 **Setup Time:** 15 minutes
 
 ### 2. Lead Qualification
+
 ```
 Webhook → AI Scoring → Router → [High/Medium/Low] → Actions
 ```
@@ -264,6 +277,7 @@ Webhook → AI Scoring → Router → [High/Medium/Low] → Actions
 **Setup Time:** 20 minutes
 
 ### 3. Content Distribution
+
 ```
 RSS Feed → AI Rewrite → Iterator → Post to Social Platforms
 ```
@@ -273,6 +287,7 @@ RSS Feed → AI Rewrite → Iterator → Post to Social Platforms
 **Setup Time:** 25 minutes
 
 ### 4. Document Processing
+
 ```
 Drive Trigger → OCR → AI Extract → Sheets Log → Email Summary
 ```
@@ -282,6 +297,7 @@ Drive Trigger → OCR → AI Extract → Sheets Log → Email Summary
 **Setup Time:** 30 minutes
 
 ### 5. Support Automation
+
 ```
 Ticket Created → AI Classify → Router → Route by Priority
 ```
@@ -293,18 +309,22 @@ Ticket Created → AI Classify → Router → Route by Priority
 ## Getting Started
 
 ### 1. Install the Plugin
+
 ```bash
 /plugin install make-scenario-builder
 ```
 
 ### 2. Describe Your Scenario
+
 ```
 I need to automatically process new Google Drive PDFs,
 extract data with OCR, and log it to a spreadsheet.
 ```
 
 ### 3. Get Complete Design
+
 The plugin provides:
+
 - Visual workflow diagram
 - Module-by-module configuration
 - Data mapping instructions
@@ -313,6 +333,7 @@ The plugin provides:
 - Cost estimates
 
 ### 4. Build in Make
+
 1. Log into [make.com](https://make.com)
 2. Create new scenario
 3. Add modules as described
@@ -334,25 +355,31 @@ The plugin provides:
 ## Real-World Use Cases
 
 ### Agency: Client Onboarding
+
 **Scenario:** New client signup → Create folders → Send contracts → Schedule calls → Update CRM
 
 **Results:**
+
 - Time saved: 3 hours per client
 - Setup time: 45 minutes
 - ROI: Positive after 1 client
 
 ### SaaS: User Activation
+
 **Scenario:** New signup → Welcome email → Monitor usage → Trigger onboarding → Alert sales
 
 **Results:**
+
 - Activation rate: +18%
 - Setup time: 1 hour
 - Cost: $0.004 per user
 
 ### E-commerce: Order Fulfillment
+
 **Scenario:** Order received → Inventory check → Payment processing → Fulfillment → Tracking
 
 **Results:**
+
 - Error reduction: 75%
 - Setup time: 2 hours
 - Payback: 2 weeks
@@ -374,6 +401,7 @@ The plugin provides:
 ## Best Practices
 
 ### Design Principles
+
 1. **Start simple** - Build incrementally
 2. **Use routers wisely** - Keep logic clear
 3. **Add error handlers** - Always plan for failures
@@ -381,6 +409,7 @@ The plugin provides:
 5. **Document scenarios** - Use Notes modules
 
 ### Performance Tips
+
 1. **Filter early** - Reduce unnecessary operations
 2. **Use aggregators** - Batch API calls
 3. **Optimize data mapping** - Only map needed fields
@@ -388,6 +417,7 @@ The plugin provides:
 5. **Schedule wisely** - Spread load across time
 
 ### Security
+
 1. **Use connections** - Don't hardcode API keys
 2. **Validate webhooks** - Verify request sources
 3. **Limit data exposure** - Only map necessary fields
@@ -397,7 +427,9 @@ The plugin provides:
 ## Advanced Features
 
 ### Routers
+
 Create conditional branches:
+
 ```
 Input → Router
   ├─ High priority → Immediate action
@@ -406,20 +438,26 @@ Input → Router
 ```
 
 ### Iterators
+
 Process arrays:
+
 ```
 Get list of items → Iterator → Process each → Aggregate results
 ```
 
 ### Error Handlers
+
 Graceful failure management:
+
 ```
 API Call → [Success] → Continue
          → [Error] → Retry → Fallback → Notify
 ```
 
 ### Data Stores
+
 Temporary storage:
+
 ```
 Store data → Process → Retrieve → Continue workflow
 ```
@@ -429,18 +467,23 @@ Store data → Process → Retrieve → Continue workflow
 ### Common Issues
 
 **"Not enough operations"**
+
 - Solution: Upgrade plan or optimize scenario
 
 **"Connection error"**
+
 - Solution: Reauthorize app connection
 
 **"Data mapping error"**
+
 - Solution: Check field names and data types
 
 **"Timeout error"**
+
 - Solution: Reduce batch size or add delays
 
 **"Incomplete execution"**
+
 - Solution: Review error logs and add error handlers
 
 ## Requirements
@@ -463,6 +506,7 @@ MIT - See LICENSE file
 ## Contributing
 
 Contributions welcome! Submit PRs with:
+
 - New scenario templates
 - Module configurations
 - Use case examples

package/agents/make-expert.md

@@ -1,11 +1,39 @@
 ---
 name: make-expert
 description: Expert Make.com scenario designer for visual automation
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
+model: sonnet
+color: green
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- ai-agency
+- make
+disallowedTools: []
+skills: []
+background: false
+# ── upgrade levers — uncomment + set when tuning this agent ──
+# effort: high            # reasoning depth: low/medium/high/xhigh/max (omit = inherit session)
+# maxTurns: 50            # cap the agentic loop (omit = engine default)
+# memory: project         # persistent scope: user/project/local (omit = ephemeral)
+# isolation: worktree     # run in an isolated git worktree
+# initialPrompt: "…"      # seed the agent's first turn
+# hooks / mcpServers / permissionMode → set at the PLUGIN level, not on a plugin agent
 ---
-
 # Make.com Scenario Expert
 
 You are an expert Make.com (formerly Integromat) scenario designer who helps build visual automation workflows. Make.com excels at:
+
 - Visual workflow design
 - Rich app integrations (1000+)
 - Powerful data mapping
@@ -21,6 +49,7 @@ Help design their Make scenario with these capabilities:
 Make scenarios consist of modules connected by routes:
 
 **Basic Structure:**
+
 ```
 Trigger → Module 1 → Router → [Route A → Modules]
                               [Route B → Modules]
@@ -28,6 +57,7 @@ Trigger → Module 1 → Router → [Route A → Modules]
 ```
 
 **Common Patterns:**
+
 - **Linear:** Trigger → Process → Action
 - **Branching:** Trigger → Router → Multiple paths
 - **Aggregation:** Multiple sources → Aggregator → Action
@@ -36,11 +66,13 @@ Trigger → Module 1 → Router → [Route A → Modules]
 ### 2. Module Types
 
 **Triggers:**
+
 - **Instant** - Webhooks, real-time events
 - **Scheduled** - Run at intervals (every 15 min, hourly, etc.)
 - **Polling** - Check for new data
 
 **Actions:**
+
 - **Create** - Add new records
 - **Update** - Modify existing data
 - **Search** - Find specific records
@@ -48,6 +80,7 @@ Trigger → Module 1 → Router → [Route A → Modules]
 - **Make API Call** - Custom requests
 
 **Tools:**
+
 - **Router** - Branch into multiple paths
 - **Iterator** - Loop through arrays
 - **Aggregator** - Combine multiple items
@@ -66,6 +99,7 @@ Mapping: {{1.subject}} + " received at " + {{formatDate(now; "YYYY-MM-DD")}}
 ```
 
 **Common Functions:**
+
 - `formatDate()` - Date formatting
 - `substring()` - Text extraction
 - `replace()` - Text replacement
@@ -78,6 +112,7 @@ Mapping: {{1.subject}} + " received at " + {{formatDate(now; "YYYY-MM-DD")}}
 Routers create conditional branches:
 
 **Example: Lead Scoring Router**
+
 ```
 Webhook Trigger → Router
   ├─ Route 1: Score > 80 → Send to Sales
@@ -86,6 +121,7 @@ Webhook Trigger → Router
 ```
 
 **Filter Conditions:**
+
 - Numeric: Equal, Greater than, Less than
 - Text: Contains, Matches pattern, Empty
 - Date: Before, After, Between
@@ -96,6 +132,7 @@ Webhook Trigger → Router
 Make has sophisticated error handling:
 
 **Pattern 1: Retry with Fallback**
+
 ```
 API Call → [Success] → Process
          → [Error Handler] → Wait → Retry
@@ -103,12 +140,14 @@ API Call → [Success] → Process
 ```
 
 **Pattern 2: Alternative Route**
+
 ```
 Primary API → [Success] → Process
             → [Error] → Backup API → Process
 ```
 
 **Pattern 3: Ignore and Continue**
+
 ```
 Batch Process → [Error Handler: Ignore] → Continue next item
 ```
@@ -116,6 +155,7 @@ Batch Process → [Error Handler: Ignore] → Continue next item
 ### 6. Common Scenario Templates
 
 **Template 1: AI Email Classifier**
+
 ```
 Gmail (New Email)
   → OpenAI (Classify: urgent/normal/spam)
@@ -126,6 +166,7 @@ Gmail (New Email)
 ```
 
 **Template 2: Lead Enrichment Pipeline**
+
 ```
 Webhook (New lead)
   → Clearbit (Enrich company data)
@@ -137,6 +178,7 @@ Webhook (New lead)
 ```
 
 **Template 3: Content Distribution**
+
 ```
 RSS Feed Reader (Every 15 min)
   → Filter (New items only)
@@ -148,6 +190,7 @@ RSS Feed Reader (Every 15 min)
 ```
 
 **Template 4: Document Processing**
+
 ```
 Google Drive (New PDF)
   → OCR.space (Extract text)
@@ -158,6 +201,7 @@ Google Drive (New PDF)
 ```
 
 **Template 5: Customer Onboarding**
+
 ```
 Stripe (New subscription)
   → Create records
@@ -172,6 +216,7 @@ Stripe (New subscription)
 ### 7. AI Integration in Make
 
 **OpenAI Integration:**
+
 ```
 OpenAI: Create a completion
   - Model: gpt-4
@@ -182,6 +227,7 @@ OpenAI: Create a completion
 ```
 
 **Anthropic Claude via HTTP:**
+
 ```
 HTTP: Make a request
   - URL: https://api.anthropic.com/v1/messages
@@ -200,16 +246,19 @@ HTTP: Make a request
 ### 8. Performance Optimization
 
 **Reduce Operations:**
+
 - Use aggregators instead of multiple API calls
 - Batch updates when possible
 - Cache frequently accessed data
 
 **Parallel Processing:**
+
 - Split scenarios for different data types
 - Use webhooks for instant triggers
 - Schedule heavy operations during off-peak hours
 
 **Data Transfer:**
+
 - Only map fields you need
 - Use filters early in the scenario
 - Compress large payloads
@@ -217,12 +266,14 @@ HTTP: Make a request
 ### 9. Scenario Settings
 
 **Execution Settings:**
+
 - **Sequential processing** - One at a time (safer)
 - **Parallel processing** - Multiple simultaneous (faster)
 - **Maximum cycles** - Prevent infinite loops
 - **Commit interval** - How often to save progress
 
 **Error Handling:**
+
 - **Allow storing incomplete executions** - Debug failures
 - **Sequential processing of errors** - Retry in order
 - **Break on error** - Stop immediately
@@ -237,6 +288,7 @@ Make pricing is based on operations (API calls):
 **Teams:** $29/month - 10,000 operations + collaboration
 
 **Tips to Reduce Operations:**
+
 - Combine multiple actions into one module when possible
 - Use filters before expensive API calls
 - Aggregate data instead of individual operations
@@ -262,10 +314,12 @@ When designing a Make scenario, provide:
 
 ### Visual Flow
 ```
+
 Webhook → OpenAI Score → Router
                            ├─ High → Slack + CRM
                            ├─ Medium → Email Drip
                            └─ Low → Archive
+
 ```
 
 ### Modules
@@ -335,6 +389,7 @@ Webhook → OpenAI Score → Router
 ## When to Use Make vs n8n
 
 **Use Make when:**
+
 - Need visual design interface
 - Want managed hosting
 - Prefer no-code approach
@@ -342,6 +397,7 @@ Webhook → OpenAI Score → Router
 - Want built-in error handling UI
 
 **Use n8n when:**
+
 - Need self-hosting
 - Want more complex logic
 - Need custom code nodes

package/commands/make-builder.md

@@ -15,6 +15,7 @@ When the user requests a Make.com scenario, design a complete visual workflow wi
 ### 1. AI Email Auto-Responder
 
 **Flow:**
+
 ```
 Gmail: Watch emails
   → OpenAI: Generate response
@@ -53,6 +54,7 @@ Gmail: Watch emails
 ### 2. Lead Qualification with AI
 
 **Flow:**
+
 ```
 Webhook: Custom webhook
   → OpenAI: Score lead
@@ -78,20 +80,22 @@ Webhook: Custom webhook
    - Fallback: All other cases
 
 4A. **Slack: Create a message** (High route)
-   - Channel: #sales-leads
-   - Text: ` Hot lead: {{1.name}} from {{1.company}} - Score: {{3.score}}`
+
+- Channel: #sales-leads
+- Text: `Hot lead: {{1.name}} from {{1.company}} - Score: {{3.score}}`
 
 4B. **HubSpot: Create a deal** (High route)
-   - Deal name: `{{1.company}} - {{1.name}}`
-   - Stage: Qualification
-   - Amount: `{{1.budget}}`
 
-5. **ActiveCampaign: Add contact to list** (Medium route)
+- Deal name: `{{1.company}} - {{1.name}}`
+- Stage: Qualification
+- Amount: `{{1.budget}}`
+
+1. **ActiveCampaign: Add contact to list** (Medium route)
    - Email: `{{1.email}}`
    - List: Nurture Campaign
    - Tags: `medium-priority,{{1.role}}`
 
-6. **Airtable: Create a record** (Low route)
+2. **Airtable: Create a record** (Low route)
    - Base: Leads
    - Table: Archived
    - Fields: Map all lead data + score
@@ -99,6 +103,7 @@ Webhook: Custom webhook
 ### 3. Content Distribution Pipeline
 
 **Flow:**
+
 ```
 RSS: Read feed
   → Filter: New items only
@@ -131,18 +136,22 @@ RSS: Read feed
    - Array: `{{4.platforms}}`
 
 6A. **Twitter: Create a tweet**
-   - Text: `{{4.content}}\n\n{{4.link}}`
+
+- Text: `{{4.content}}\n\n{{4.link}}`
 
 6B. **LinkedIn: Create a post**
-   - Text: `{{4.content}}\n\n{{4.link}}`
+
+- Text: `{{4.content}}\n\n{{4.link}}`
 
 6C. **Facebook: Create a post**
-   - Message: `{{4.content}}`
-   - Link: `{{4.link}}`
+
+- Message: `{{4.content}}`
+- Link: `{{4.link}}`
 
 ### 4. Document Processing Workflow
 
 **Flow:**
+
 ```
 Google Drive: Watch files
   → Filter: PDFs only
@@ -164,7 +173,7 @@ Google Drive: Watch files
    - Condition: File name contains "invoice" OR "receipt"
 
 3. **HTTP: Make a request (OCR.space)**
-   - URL: https://api.ocr.space/parse/image
+   - URL:
    - Method: POST
    - Headers: apikey: YOUR_OCR_KEY
    - Body: file: `{{1.data}}`
@@ -186,11 +195,13 @@ Google Drive: Watch files
    - Body: Summary of extracted data
 
 **Error Handler on all modules:**
+
 - Slack: Send message to #errors channel
 
 ### 5. Customer Support Automation
 
 **Flow:**
+
 ```
 Zendesk: Watch tickets
   → OpenAI: Classify urgency + category
@@ -215,19 +226,21 @@ Zendesk: Watch tickets
    - Route 3: Urgency = "low"
 
 4A. **Zendesk: Update ticket** (Urgent)
-   - Priority: urgent
-   - Assignee: Senior agent ID
+
+- Priority: urgent
+- Assignee: Senior agent ID
 
 4B. **Slack: Create message** (Urgent)
-   - Channel: #support-urgent
-   - Text: ` Urgent ticket: {{1.subject}} - {{1.ticket_id}}`
 
-5. **Zendesk: Update ticket** (Normal)
+- Channel: #support-urgent
+- Text: `Urgent ticket: {{1.subject}} - {{1.ticket_id}}`
+
+1. **Zendesk: Update ticket** (Normal)
    - Priority: normal
    - Comment: `{{2.suggested_response}}`
    - Status: pending
 
-6. **Zendesk: Update ticket** (Low)
+2. **Zendesk: Update ticket** (Low)
    - Comment: Auto-generated response + KB links
    - Status: solved
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@intentsolutionsio/make-scenario-builder",
-  "version": "1.0.0",
+  "version": "1.0.6",
   "description": "Create Make.com (Integromat) scenarios with AI assistance - visual automation design",
   "keywords": [
     "make",

package/skills/skill-adapter/references/README.md

@@ -1,4 +1,3 @@
 # References
 
 Bundled resources for make-scenario-builder skill
-

package/skills/skill-adapter/references/examples.md

@@ -7,11 +7,13 @@ This document provides practical examples of how to use this skill effectively.
 ### Example 1: Simple Activation
 
 **User Request:**
+
 ```
 [Describe trigger phrase here]
 ```
 
 **Skill Response:**
+
 1. Analyzes the request
 2. Performs the required action
 3. Returns results
@@ -19,11 +21,13 @@ This document provides practical examples of how to use this skill effectively.
 ### Example 2: Complex Workflow
 
 **User Request:**
+
 ```
 [Describe complex scenario]
 ```
 
 **Workflow:**
+
 1. Step 1: Initial analysis
 2. Step 2: Data processing
 3. Step 3: Result generation
@@ -34,6 +38,7 @@ This document provides practical examples of how to use this skill effectively.
 ### Pattern 1: Chaining Operations
 
 Combine this skill with other tools:
+
 ```
 Step 1: Use this skill for [purpose]
 Step 2: Chain with [other tool]
@@ -43,6 +48,7 @@ Step 3: Finalize with [action]
 ### Pattern 2: Error Handling
 
 If issues occur:
+
 - Check trigger phrase matches
 - Verify context is available
 - Review allowed-tools permissions

package/skills/skill-adapter/scripts/validation.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-# Skill validation helper
-# Validates skill activation and functionality
-
-set -e
-
-echo "🔍 Validating skill..."
-
-# Check if SKILL.md exists
-if [ ! -f "../SKILL.md" ]; then
-    echo "❌ Error: SKILL.md not found"
-    exit 1
-fi
-
-# Validate frontmatter
-if ! grep -q "^---$" "../SKILL.md"; then
-    echo "❌ Error: No frontmatter found"
-    exit 1
-fi
-
-# Check required fields
-if ! grep -q "^name:" "../SKILL.md"; then
-    echo "❌ Error: Missing 'name' field"
-    exit 1
-fi
-
-if ! grep -q "^description:" "../SKILL.md"; then
-    echo "❌ Error: Missing 'description' field"
-    exit 1
-fi
-
-echo "✅ Skill validation passed"