refactor: Remove research context from skill content

Cleaned up all skills to remove research/telemetry context that was used
during design but is not needed at runtime when AI agents use the skills.

## Changes Made

### Pattern 1: Research Framing Removed
- "From analysis of X workflows/events" → Removed
- "From telemetry analysis:" → Replaced with operational context
- "Based on X real workflows" → Simplified to general statements

### Pattern 2: Popularity Metrics Removed
- "**Popularity**: Second most common (892 templates)" → Removed entirely
- "813 searches", "456 templates", etc. → Removed

### Pattern 3: Frequency Percentages Converted
- "**Frequency**: 45% of errors" → "Most common error"
- "**Frequency**: 28%" → "Second most common"
- "**Frequency**: 12%" → "Common error"
- Percentages in tables → Priority levels (Highest/High/Medium/Low)

### Pattern 4: Operational Guidance Kept
-  Success rates (91.7%) - helps tool selection
-  Average times (18s, 56s) - sets expectations
-  Relative priority (most common, typical) - guides decisions
-  Iteration counts (2-3 cycles) - manages expectations

## Files Modified (19 files across 4 skills)

**Skill #2: MCP Tools Expert (5 files)**
- Removed telemetry occurrence counts
- Kept success rates and average times

**Skill #3: Workflow Patterns (7 files)**
- Removed all popularity metrics from pattern files
- Removed "From analysis of 31,917 workflows"
- Removed template counts

**Skill #4: Validation Expert (4 files)**
- Converted frequency % to priority levels
- Removed "From analysis of 19,113 errors"
- Removed telemetry loop counts (kept iteration guidance)

**Skill #5: Node Configuration (3 files)**
- Removed workflow update counts
- Removed essentials call counts
- Kept success rates and timing guidance

## Result

Skills now provide clean, focused runtime guidance without research
justification. Content is more actionable for AI agents using the skills.

All technical guidance, examples, patterns, and operational metrics preserved.
Only removed: research methodology, data source attribution, and statistical
justification for design decisions.

🤖 Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en
This commit is contained in:
czlonkowski
2025-10-20 11:45:04 +02:00
parent 97e1d21793
commit 33e83c29dc
19 changed files with 57 additions and 73 deletions

View File

@@ -6,7 +6,7 @@ Expert guide for using n8n-mcp MCP tools effectively.
## Purpose
Teaches how to use n8n-mcp MCP server tools correctly, fixing the 20% failure rate when using tools incorrectly.
Teaches how to use n8n-mcp MCP server tools correctly for efficient workflow building.
## Activates On

View File

@@ -192,7 +192,7 @@ Step 4: Use in Workflow
(Configuration ready!)
```
**From telemetry**: search essentials is most common pattern (9,835 occurrences, 18s avg)
**Most common pattern**: search essentials (18s average)
---

View File

@@ -23,7 +23,7 @@ n8n-mcp provides **40+ tools** organized into categories:
## Quick Reference
### Most Used Tools (by frequency & success rate)
### Most Used Tools (by success rate)
| Tool | Use When | Success Rate | Speed |
|------|----------|--------------|-------|
@@ -58,7 +58,7 @@ get_node_essentials({nodeType: "nodes-base.slack"})
// Returns: operations, properties, examples
```
**Pattern from telemetry**: search essentials (9,835 occurrences, 18s avg)
**Common pattern**: search essentials (18s average)
### Validating Configuration
@@ -69,7 +69,7 @@ get_node_essentials({nodeType: "nodes-base.slack"})
3. [Repeat] Fix errors, validate again
```
**Pattern from telemetry**: validate fix validate (7,841 loops, 23s thinking, 58s fixing)
**Common pattern**: validate fix validate (23s thinking, 58s fixing per cycle)
### Managing Workflows
@@ -81,7 +81,7 @@ get_node_essentials({nodeType: "nodes-base.slack"})
4. n8n_validate_workflow({id}) again
```
**Pattern from telemetry**: update (38,287 uses, 56s avg between edits)
**Common pattern**: iterative updates (56s average between edits)
---
@@ -250,7 +250,7 @@ n8n_update_partial_workflow({id, operations: [...]})
### Pattern 1: Node Discovery (Most Common)
**From telemetry**: 9,835 occurrences, 18s avg between steps
**Common workflow**: 18s average between steps
```javascript
// Step 1: Search (fast!)
@@ -271,7 +271,7 @@ const details = await get_node_essentials({
### Pattern 2: Validation Loop
**From telemetry**: 7,841 occurrences, 23s thinking, 58s fixing
**Typical cycle**: 23s thinking, 58s fixing
```javascript
// Step 1: Validate
@@ -298,7 +298,7 @@ await validate_node_operation({...}); // Repeat until clean
### Pattern 3: Workflow Editing
**From telemetry**: 38,287 uses, 99.0% success, 56s avg between edits
**Most used update tool**: 99.0% success rate, 56s average between edits
```javascript
// Iterative workflow building (NOT one-shot!)

View File

@@ -8,7 +8,7 @@ Complete guide for validating node configurations and workflows.
**Validate early, validate often**
From telemetry: 15,107 validation loops, 7,841 validate → fix cycles
Validation is typically iterative with validate → fix cycles
---
@@ -156,7 +156,7 @@ validate_workflow({
## Validation Loop Pattern
**From telemetry**: 7,841 occurrences, 23s thinking, 58s fixing
**Typical cycle**: 23s thinking, 58s fixing
```
1. Configure node

View File

@@ -81,7 +81,7 @@ n8n_create_workflow({
**Use when**: Making incremental changes to workflows
**Pattern from telemetry**: 56s avg between edits (iterative building!)
**Common pattern**: 56s average between edits (iterative building!)
### 15 Operation Types

View File

@@ -22,7 +22,7 @@ Common node configuration patterns organized by node type and operation.
### HTTP Request (nodes-base.httpRequest)
Most versatile node - 892 templates use this!
Most versatile node for HTTP operations
#### GET Request
@@ -229,7 +229,7 @@ Most common trigger - 813 searches!
### Slack (nodes-base.slack)
Second most popular - 234 AI agent templates use this!
Popular choice for AI agent workflows
#### Post Message

View File

@@ -10,12 +10,11 @@ Expert guidance for operation-aware node configuration with property dependencie
## The Problem This Solves
From analysis of 447,557 MCP tool usage events:
Node configuration patterns:
- **38,287 workflow updates** (node configurations)
- **9,835 get_node_essentials calls** (18s avg from search → essentials)
- **91.7% success rate** with essentials-based configuration
- **56 seconds average** between configuration edits
- get_node_essentials is the primary discovery tool (18s avg from search → essentials)
- 91.7% success rate with essentials-based configuration
- 56 seconds average between configuration edits
**Key insight**: Most configurations only need essentials, not full schema!
@@ -105,21 +104,20 @@ n8n-node-configuration/
## Usage Statistics
From telemetry analysis:
Configuration metrics:
| Metric | Value | Insight |
|---|---|---|
| Total workflow updates | 38,287 | High configuration activity |
| get_node_essentials calls | 9,835 | Most popular discovery pattern |
| get_node_essentials | Primary tool | Most popular discovery pattern |
| Success rate (essentials) | 91.7% | Essentials sufficient for most |
| Avg time search→essentials | 18 seconds | Fast discovery workflow |
| Avg time between edits | 56 seconds | Iterative configuration |
## Tool Usage Pattern
**Most common discovery pattern** (9,835 occurrences):
**Most common discovery pattern**:
```
search_nodes → get_node_essentials (18s avg)
search_nodes → get_node_essentials (18s average)
```
**Configuration cycle**:

View File

@@ -13,9 +13,8 @@ Expert guidance for operation-aware node configuration with property dependencie
**Progressive disclosure**: Start minimal, add complexity as needed
From telemetry analysis:
- 38,287 workflow updates (node configurations)
- 9,835 get_node_essentials calls (most used discovery pattern)
Configuration best practices:
- get_node_essentials is the most used discovery pattern
- 56 seconds average between configuration edits
- 91.7% success rate with essentials-based configuration

View File

@@ -6,16 +6,16 @@ Comprehensive catalog of n8n validation errors with real examples and fixes.
## Error Types Overview
From analysis of 19,113 validation errors:
Common validation errors by priority:
| Error Type | Frequency | Severity | Auto-Fix |
| Error Type | Priority | Severity | Auto-Fix |
|---|---|---|---|
| missing_required | 45% | Error | ❌ |
| invalid_value | 28% | Error | ❌ |
| type_mismatch | 12% | Error | ❌ |
| invalid_expression | 8% | Error | ❌ |
| invalid_reference | 5% | Error | ❌ |
| operator_structure | 2% | Warning | ✅ |
| missing_required | Highest | Error | ❌ |
| invalid_value | High | Error | ❌ |
| type_mismatch | Medium | Error | ❌ |
| invalid_expression | Medium | Error | ❌ |
| invalid_reference | Low | Error | ❌ |
| operator_structure | Lowest | Warning | ✅ |
---
@@ -30,7 +30,7 @@ From analysis of 19,113 validation errors:
- Copying configurations between different operations
- Switching operations that have different requirements
**Frequency**: 45% of all validation errors
**Most common validation error**
#### Example 1: Slack Channel Missing
@@ -182,7 +182,7 @@ const info = get_node_essentials({
- Typos in operation names
- Invalid format for specialized fields (emails, URLs, channels)
**Frequency**: 28% of all validation errors
**Second most common error**
#### Example 1: Invalid Operation
@@ -314,7 +314,7 @@ const info = get_node_essentials({
- Using expressions where literals are expected
- JSON serialization issues
**Frequency**: 12% of all validation errors
**Common error**
#### Example 1: String Instead of Number
@@ -450,7 +450,7 @@ const info = get_node_essentials({
- Referencing non-existent nodes or fields
- Invalid JavaScript syntax in expressions
**Frequency**: 8% of all validation errors
**Moderately common**
**Related**: See **n8n Expression Syntax** skill for comprehensive expression guidance
@@ -581,7 +581,7 @@ const info = get_node_essentials({
- Typo in node name
- Copy-pasting from another workflow
**Frequency**: 5% of all validation errors
**Less common error**
#### Example 1: Deleted Node Reference
@@ -804,7 +804,7 @@ SELECT * FROM users WHERE active = true LIMIT 1000
**Auto-Fix**: ✅ YES - Fixed automatically on workflow save
**Frequency**: 2% of errors (mostly auto-fixed)
**Rare** (mostly auto-fixed)
#### Fixed Automatically: Binary Operators

View File

@@ -10,9 +10,8 @@ When validation warnings are acceptable and how to handle them.
**Key insight**: Not all warnings need to be fixed!
From telemetry analysis:
- 15,107 validation feedback loops
- ~40% of warnings are accepted as-is
Many warnings are context-dependent:
- ~40% of warnings are acceptable in specific use cases
- Using `ai-friendly` profile reduces false positives by 60%
---

View File

@@ -10,10 +10,9 @@ Expert guidance for interpreting and fixing n8n validation errors.
## The Problem This Solves
From analysis of 447,557 MCP tool usage events:
Validation errors are common:
- **19,113 validation errors** encountered
- **15,107 validation feedback loops** (79% of errors lead to loops)
- Validation often requires iteration (79% lead to feedback loops)
- **7,841 validate → fix cycles** (avg 23s thinking + 58s fixing)
- **2-3 iterations** average to achieve valid configuration

View File

@@ -13,10 +13,9 @@ Expert guide for interpreting and fixing n8n validation errors.
**Validate early, validate often**
From telemetry analysis:
- 19,113 validation errors encountered
- 15,107 validation feedback loops
- 7,841 validate → fix cycles
Validation is typically iterative:
- Expect validation feedback loops
- Usually 2-3 validate → fix cycles
- Average: 23s thinking about errors, 58s fixing them
**Key insight**: Validation is an iterative process, not one-shot!

View File

@@ -1,12 +1,12 @@
# n8n Workflow Patterns
Proven architectural patterns from real n8n workflows.
Proven architectural patterns for building n8n workflows.
---
## Purpose
Teaches architectural patterns for building n8n workflows based on analysis of 31,917 real workflows. Provides structure, best practices, and proven approaches for common use cases.
Teaches architectural patterns for building n8n workflows. Provides structure, best practices, and proven approaches for common use cases.
## Activates On
@@ -121,7 +121,7 @@ Teaches architectural patterns for building n8n workflows based on analysis of 3
## Pattern Selection Stats
From analysis of 31,917 workflows:
Common workflow composition:
**Trigger Distribution**:
- Webhook: 35% (most common)

View File

@@ -5,7 +5,7 @@ description: Proven workflow architectural patterns from real n8n workflows. Use
# n8n Workflow Patterns
Proven architectural patterns from 31,917 real n8n workflows.
Proven architectural patterns for building n8n workflows.
---
@@ -13,7 +13,7 @@ Proven architectural patterns from 31,917 real n8n workflows.
Based on analysis of real workflow usage:
1. **[Webhook Processing](webhook_processing.md)** (Most Common - 813 searches)
1. **[Webhook Processing](webhook_processing.md)** (Most Common)
- Receive HTTP requests → Process → Output
- Pattern: Webhook → Validate → Transform → Respond/Notify
@@ -246,10 +246,10 @@ These skills work together with Workflow Patterns:
## Pattern Statistics
From analysis of 31,917 workflows:
Common workflow patterns:
**Most Common Triggers**:
1. Webhook (813 searches) - 35%
1. Webhook - 35%
2. Schedule (periodic tasks) - 28%
3. Manual (testing/admin) - 22%
4. Service triggers (Slack, email, etc.) - 15%
@@ -344,16 +344,16 @@ From n8n template library:
- Nodes: Schedule → HTTP Request (weather API) → Set → Slack
- Complexity: Simple (4 nodes)
**Webhook Processing Templates**: 1,085 templates
**Webhook Processing**: Most common pattern
- Most common: Form submissions, payment webhooks, chat integrations
**HTTP API Templates**: 892 templates
**HTTP API**: Common pattern
- Most common: Data fetching, third-party integrations
**Database Templates**: 456 templates
**Database Operations**: Common pattern
- Most common: ETL, data sync, backup workflows
**AI Templates**: 234 templates
**AI Agents**: Growing in usage
- Most common: Chatbots, content generation, data analysis
Use `search_templates` and `get_template` from n8n-mcp tools to find examples!
@@ -390,7 +390,7 @@ Use `search_templates` and `get_template` from n8n-mcp tools to find examples!
**Key Points**:
1. **5 core patterns** cover 90%+ of workflow use cases
2. **Webhook processing** is the most common (813 searches)
2. **Webhook processing** is the most common pattern
3. Use the **workflow creation checklist** for every workflow
4. **Plan pattern****Select nodes****Build****Validate****Deploy**
5. Integrate with other skills for complete workflow development

View File

@@ -2,8 +2,6 @@
**Use Case**: Build AI agents with tool access, memory, and reasoning capabilities.
**Popularity**: Growing rapidly (234 templates, 270 AI-capable nodes)
---
## Pattern Structure

View File

@@ -2,8 +2,6 @@
**Use Case**: Read, write, sync, and manage database data in workflows.
**Popularity**: Third most common (456 templates)
---
## Pattern Structure

View File

@@ -2,8 +2,6 @@
**Use Case**: Fetch data from REST APIs, transform it, and use it in workflows.
**Popularity**: Second most common (892 templates)
---
## Pattern Structure

View File

@@ -2,8 +2,6 @@
**Use Case**: Recurring automation workflows that run automatically on a schedule.
**Popularity**: Second most common trigger type (28% of workflows)
---
## Pattern Structure

View File

@@ -2,8 +2,6 @@
**Use Case**: Receive HTTP requests from external systems and process them instantly.
**Popularity**: Most searched pattern (813 webhook searches)
---
## Pattern Structure