feat: Complete Skill #3 - n8n Workflow Patterns

Implements comprehensive workflow pattern guidance from 31,917 real workflows.
Addresses the most common use case (813 webhook searches).

Files created:
- 5 evaluations testing pattern selection and implementation
- SKILL.md (486 lines) - Pattern overview, selection guide, workflow checklist
- webhook_processing.md (554 lines) - Webhook patterns, $json.body gotcha, auth
- http_api_integration.md (763 lines) - REST APIs, pagination, rate limiting
- database_operations.md (854 lines) - DB ops, batch processing, SQL injection prevention
- ai_agent_workflow.md (918 lines) - AI agents, 8 connection types, tool configuration
- scheduled_tasks.md (845 lines) - Cron schedules, timezone handling, monitoring
- README.md - Skill metadata with pattern statistics

Key features:
- 5 core patterns: Webhook (35%), HTTP API (892 templates), Database (456), AI (234), Scheduled (28%)
- Workflow creation checklist (planning → implementation → validation → deployment)
- Pattern selection guide with statistics
- Common gotchas documented (webhook $json.body, SQL injection, timezone, etc.)
- Error handling strategies for each pattern
- Performance optimization techniques
- Security best practices
- Testing approaches
- Real template examples

Critical insights:
- Webhook data under $json.body (not $json) - #1 gotcha
- Always use parameterized queries (SQL injection prevention)
- ANY node can be an AI tool (connect to ai_tool port)
- Set workflow timezone explicitly (DST handling)
- Authentication via credentials (never hardcode)

Pattern statistics:
- Trigger distribution: Webhook 35%, Schedule 28%, Manual 22%, Service 15%
- Transformation: Set 68%, Code 42%, IF 38%, Switch 18%
- Output: HTTP 45%, Slack 32%, Database 28%, Email 24%
- Complexity: Simple 42%, Medium 38%, Complex 20%

Total: ~4,420 lines across 12 files

Based on analysis of 31,917 real workflows and usage patterns.

🤖 Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en

evaluations/workflow-patterns/eval-001-webhook-workflow.json

@@ -0,0 +1,14 @@
+{
+  "id": "pattern-001",
+  "skills": ["n8n-workflow-patterns"],
+  "query": "I need to build a workflow that receives webhook data and sends it to Slack. What's the best way to structure this?",
+  "expected_behavior": [
+    "Identifies this as a Webhook Processing pattern",
+    "References the webhook_processing.md pattern file",
+    "Explains the basic structure: Webhook → Transform → Output",
+    "Mentions data is nested under $json.body for webhook payloads",
+    "Suggests validation and error handling",
+    "May reference real template examples",
+    "Provides checklist: trigger, validation, transformation, output, error handling"
+  ]
+}

evaluations/workflow-patterns/eval-002-http-api-workflow.json

@@ -0,0 +1,14 @@
+{
+  "id": "pattern-002",
+  "skills": ["n8n-workflow-patterns"],
+  "query": "I want to fetch data from a REST API, transform it, and store it in my database. How should I structure this workflow?",
+  "expected_behavior": [
+    "Identifies this as an HTTP API Integration pattern",
+    "References the http_api_integration.md pattern file",
+    "Explains the structure: Trigger → HTTP Request → Transform → Database → Error Handler",
+    "Discusses authentication handling (credentials)",
+    "Mentions pagination for large datasets",
+    "Suggests retry logic for API failures",
+    "Provides guidance on response parsing and data mapping"
+  ]
+}

evaluations/workflow-patterns/eval-003-database-sync.json

@@ -0,0 +1,15 @@
+{
+  "id": "pattern-003",
+  "skills": ["n8n-workflow-patterns"],
+  "query": "How do I build a workflow that syncs data between two databases? I need to read from Postgres and write to MySQL.",
+  "expected_behavior": [
+    "Identifies this as a Database Operations pattern",
+    "References the database_operations.md pattern file",
+    "Explains the structure: Schedule/Trigger → Read DB → Transform → Write DB → Error Handler",
+    "Discusses batch processing for large datasets",
+    "Mentions transaction handling and rollback considerations",
+    "Suggests incremental sync strategies (last_modified timestamps)",
+    "Warns about connection pooling and performance",
+    "Provides guidance on data type mapping between databases"
+  ]
+}

evaluations/workflow-patterns/eval-004-ai-agent.json

@@ -0,0 +1,15 @@
+{
+  "id": "pattern-004",
+  "skills": ["n8n-workflow-patterns"],
+  "query": "I want to build an AI agent that can use tools to answer questions. What's the recommended workflow pattern?",
+  "expected_behavior": [
+    "Identifies this as an AI Agent Workflow pattern",
+    "References the ai_agent_workflow.md pattern file",
+    "Explains the structure: Trigger → AI Agent (with Language Model + Tools + Memory)",
+    "Discusses the 8 AI connection types (ai_languageModel, ai_tool, ai_memory, etc.)",
+    "Mentions that ANY node can be an AI tool (connected via ai_tool port)",
+    "Suggests memory integration for conversation context",
+    "Provides guidance on tool configuration and result handling",
+    "May mention langchain package nodes"
+  ]
+}

evaluations/workflow-patterns/eval-005-scheduled-report.json

@@ -0,0 +1,15 @@
+{
+  "id": "pattern-005",
+  "skills": ["n8n-workflow-patterns"],
+  "query": "I need to generate a daily report that fetches analytics data and emails it to my team. What's the best workflow structure?",
+  "expected_behavior": [
+    "Identifies this as a Scheduled Tasks pattern",
+    "References the scheduled_tasks.md pattern file",
+    "Explains the structure: Schedule Trigger → Fetch Data → Transform/Aggregate → Format Report → Send Email",
+    "Discusses cron expression configuration",
+    "Mentions timezone considerations",
+    "Suggests error handling and failure notifications",
+    "Provides guidance on data aggregation and report formatting",
+    "May suggest using templates for consistent report structure"
+  ]
+}