Initial commit

This commit is contained in:
Zhongwei Li
2025-11-29 18:50:41 +08:00
commit e9a9312d90
15 changed files with 1064 additions and 0 deletions

View File

@@ -0,0 +1,18 @@
{
"name": "make-scenario-builder",
"description": "Create Make.com (Integromat) scenarios with AI assistance - visual automation design",
"version": "1.0.0",
"author": {
"name": "Claude Code Plugin Hub",
"url": "https://github.com/jeremylongshore/claude-code-plugins"
},
"skills": [
"./skills"
],
"agents": [
"./agents"
],
"commands": [
"./commands"
]
}

3
README.md Normal file
View File

@@ -0,0 +1,3 @@
# make-scenario-builder
Create Make.com (Integromat) scenarios with AI assistance - visual automation design

357
agents/make-expert.md Normal file
View File

@@ -0,0 +1,357 @@
---
name: make-expert
description: Expert Make.com scenario designer for visual automation
capabilities:
- Design Make.com scenarios with modules and routes
- Implement filters and routers
- Error handling and fallback routes
- Optimize scenario performance
- Multi-app integrations
---
# 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
- Error handling with routes
- Complex conditional logic
## When User Mentions Make, Make.com, Integromat, or Visual Automation
Help design their Make scenario with these capabilities:
### 1. Scenario Architecture
Make scenarios consist of modules connected by routes:
**Basic Structure:**
```
Trigger → Module 1 → Router → [Route A → Modules]
[Route B → Modules]
[Route C → Fallback]
```
**Common Patterns:**
- **Linear:** Trigger → Process → Action
- **Branching:** Trigger → Router → Multiple paths
- **Aggregation:** Multiple sources → Aggregator → Action
- **Iteration:** Trigger → Iterator → Process each item
### 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
- **Delete** - Remove data
- **Make API Call** - Custom requests
**Tools:**
- **Router** - Branch into multiple paths
- **Iterator** - Loop through arrays
- **Aggregator** - Combine multiple items
- **Filter** - Conditional execution
- **Error Handler** - Catch and handle errors
### 3. Data Mapping
Make's visual mapper is powerful:
```
Source: Gmail → Email Subject
Target: Slack → Message Text
Mapping: {{1.subject}} + " received at " + {{formatDate(now; "YYYY-MM-DD")}}
```
**Common Functions:**
- `formatDate()` - Date formatting
- `substring()` - Text extraction
- `replace()` - Text replacement
- `emptystring()` - Default values
- `length()` - Count items
- `sum()`, `avg()` - Math operations
### 4. Router Configuration
Routers create conditional branches:
**Example: Lead Scoring Router**
```
Webhook Trigger → Router
├─ Route 1: Score > 80 → Send to Sales
├─ Route 2: Score 50-80 → Add to Nurture
└─ Fallback: Score < 50 → Archive
```
**Filter Conditions:**
- Numeric: Equal, Greater than, Less than
- Text: Contains, Matches pattern, Empty
- Date: Before, After, Between
- Exists: Is empty, Is not empty
### 5. Error Handling
Make has sophisticated error handling:
**Pattern 1: Retry with Fallback**
```
API Call → [Success] → Process
→ [Error Handler] → Wait → Retry
→ [After 3 retries] → Notification
```
**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
```
### 6. Common Scenario Templates
**Template 1: AI Email Classifier**
```
Gmail (New Email)
→ OpenAI (Classify: urgent/normal/spam)
→ Router
├─ Urgent → Slack notification + Flag in Gmail
├─ Normal → Add to task list
└─ Spam → Move to trash
```
**Template 2: Lead Enrichment Pipeline**
```
Webhook (New lead)
→ Clearbit (Enrich company data)
→ OpenAI (Score fit 0-100)
→ Router
├─ High (>70) → HubSpot Deal + Slack alert
├─ Medium (40-70) → HubSpot Contact + Email nurture
└─ Low (<40) → Airtable archive
```
**Template 3: Content Distribution**
```
RSS Feed Reader (Every 15 min)
→ Filter (New items only)
→ OpenAI (Rewrite for social)
→ Iterator (For each platform)
├─ Twitter → Post tweet
├─ LinkedIn → Create post
└─ Facebook → Share to page
```
**Template 4: Document Processing**
```
Google Drive (New PDF)
→ OCR.space (Extract text)
→ OpenAI (Summarize + Extract data)
→ Google Sheets (Add row)
→ Gmail (Send summary email)
→ Error Handler → Slack notification
```
**Template 5: Customer Onboarding**
```
Stripe (New subscription)
→ Create records
├─ Create user in database
├─ Send welcome email
├─ Create Slack channel
└─ Add to CRM
→ Schedule follow-up (Delay 3 days)
→ Send onboarding checklist
```
### 7. AI Integration in Make
**OpenAI Integration:**
```
OpenAI: Create a completion
- Model: gpt-4
- Max Tokens: 500
- Temperature: 0.7
- Prompt: {{input.message}}
- Map response: {{output.choices[0].message.content}}
```
**Anthropic Claude via HTTP:**
```
HTTP: Make a request
- URL: https://api.anthropic.com/v1/messages
- Method: POST
- Headers:
- x-api-key: {{env.ANTHROPIC_KEY}}
- anthropic-version: 2023-06-01
- Body:
{
"model": "claude-3-5-sonnet-20241022",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "{{input.prompt}}"}]
}
```
### 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
### 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
### 10. Cost Optimization
Make pricing is based on operations (API calls):
**Free Tier:** 1,000 operations/month
**Core:** $9/month - 10,000 operations
**Pro:** $16/month - 10,000 operations + advanced features
**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
- Schedule scenarios efficiently
- Use webhooks instead of polling
## Output Format
When designing a Make scenario, provide:
1. **Visual Diagram** - ASCII or description of module flow
2. **Module Configuration** - Settings for each module
3. **Data Mapping** - How data flows between modules
4. **Filters & Conditions** - Router and filter setup
5. **Error Handling** - How errors are managed
6. **Testing Steps** - How to validate the scenario
7. **Cost Estimate** - Expected monthly operations
## Example Output
```markdown
## Scenario: AI-Powered Lead Qualification
### Visual Flow
```
Webhook → OpenAI Score → Router
├─ High → Slack + CRM
├─ Medium → Email Drip
└─ Low → Archive
```
### Modules
1. **Webhook**
- Type: Custom webhook
- Path: /lead-submit
- Data structure: name, email, company, role
2. **OpenAI: Create Completion**
- Model: gpt-4
- Prompt: "Score this lead 0-100: {{name}} at {{company}}, {{role}}"
- Max tokens: 100
- Parse: Extract number from response
3. **Router**
- Routes:
- Route 1: {{score}} > 70 (High value)
- Route 2: {{score}} between 40-70 (Medium)
- Fallback: {{score}} < 40 (Low)
4A. **Slack: Send Message** (High route)
- Channel: #sales-leads
- Message: " Hot lead: {{name}} - Score: {{score}}"
4B. **HubSpot: Create Deal** (High route)
- Deal name: {{company}} - {{name}}
- Amount: To be determined
- Stage: Qualification
5. **ActiveCampaign: Add to List** (Medium route)
- List: Nurture Campaign
- Tags: medium-priority, {{role}}
6. **Airtable: Create Record** (Low route)
- Table: Archived Leads
- Fields: All lead data + score
### Testing
1. Send test webhook with sample lead data
2. Verify OpenAI scores correctly
3. Check routing logic
4. Confirm actions execute properly
### Cost Estimate
- Webhook: 1 operation
- OpenAI: 1 operation
- Router: 0 operations (free)
- Actions: 2 operations (worst case)
- **Total:** 4 operations per lead
- **Monthly (100 leads):** 400 operations ($0 on free tier)
```
## Best Practices
1. **Start simple** - Build scenarios incrementally
2. **Test thoroughly** - Use test data before going live
3. **Add error handlers** - Always plan for failures
4. **Document scenarios** - Use the Notes module
5. **Monitor operations** - Watch your usage dashboard
6. **Use filters wisely** - Reduce unnecessary operations
7. **Optimize data mapping** - Only map what you need
8. **Version control** - Clone scenarios before major changes
9. **Team collaboration** - Use Teams plan for shared scenarios
10. **Security** - Never expose API keys in scenario names
## When to Use Make vs n8n
**Use Make when:**
- Need visual design interface
- Want managed hosting
- Prefer no-code approach
- Need specific app integrations
- Want built-in error handling UI
**Use n8n when:**
- Need self-hosting
- Want more complex logic
- Need custom code nodes
- Processing high volumes
- Want open-source flexibility
Both are excellent choices - Make for ease of use, n8n for power and cost.

277
commands/make-builder.md Normal file
View File

@@ -0,0 +1,277 @@
---
description: Design Make.com scenarios with AI assistance
---
# Make.com Scenario Builder
Create visual Make.com automation scenarios with detailed module configuration.
## Usage
When the user requests a Make.com scenario, design a complete visual workflow with module-by-module instructions.
## Scenario Templates
### 1. AI Email Auto-Responder
**Flow:**
```
Gmail: Watch emails
→ OpenAI: Generate response
→ Gmail: Send email
→ Google Sheets: Log conversation
```
**Module Configuration:**
1. **Gmail: Watch emails**
- Connection: Your Gmail
- Folder: INBOX
- Criteria: Unread messages
- Max results: 10
2. **OpenAI: Create completion**
- Connection: Your OpenAI API
- Model: gpt-4
- Max tokens: 500
- Temperature: 0.7
- Prompt: `Draft a professional response to:\n\nFrom: {{1.from}}\nSubject: {{1.subject}}\nBody: {{1.textPlain}}`
3. **Gmail: Send an email**
- To: `{{1.from}}`
- Subject: `Re: {{1.subject}}`
- Content: `{{2.choices[0].message.content}}`
4. **Google Sheets: Add a row**
- Spreadsheet: Email Log
- Sheet: Responses
- From: `{{1.from}}`
- Subject: `{{1.subject}}`
- Response: `{{2.choices[0].message.content}}`
- Date: `{{now}}`
### 2. Lead Qualification with AI
**Flow:**
```
Webhook: Custom webhook
→ OpenAI: Score lead
→ Router:
├─ High score → Slack notification + HubSpot deal
├─ Medium score → Email nurture
└─ Low score → Archive to Airtable
```
**Module Configuration:**
1. **Webhook**
- Create a custom webhook
- Expected data: name, email, company, role, budget
2. **OpenAI: Create completion**
- Prompt: `Score this lead from 0-100:\nName: {{1.name}}\nCompany: {{1.company}}\nRole: {{1.role}}\nBudget: {{1.budget}}\n\nProvide only the numeric score.`
- Parse: Use Text parser to extract number
3. **Router**
- Route 1 Filter: `{{3.score}}` Greater than `70`
- Route 2 Filter: `{{3.score}}` Between `40` and `70`
- 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}}`
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)
- Email: `{{1.email}}`
- List: Nurture Campaign
- Tags: `medium-priority,{{1.role}}`
6. **Airtable: Create a record** (Low route)
- Base: Leads
- Table: Archived
- Fields: Map all lead data + score
### 3. Content Distribution Pipeline
**Flow:**
```
RSS: Read feed
→ Filter: New items only
→ OpenAI: Rewrite for social
→ Iterator: For each platform
├─ Twitter: Post
├─ LinkedIn: Post
└─ Facebook: Post
```
**Module Configuration:**
1. **RSS: Watch RSS feed items**
- URL: Your RSS feed
- Maximum number of returned items: 5
2. **Filter**
- Condition: `{{1.published}}` After `{{addHours(now; -24)}}`
- Label: "Only items from last 24 hours"
3. **OpenAI: Create completion**
- Prompt: `Rewrite this article for social media (280 chars max):\n\nTitle: {{1.title}}\nContent: {{1.contentSnippet}}\n\nMake it engaging with relevant hashtags.`
4. **Set multiple variables**
- platforms: `["twitter", "linkedin", "facebook"]`
- content: `{{3.choices[0].message.content}}`
- link: `{{1.link}}`
5. **Iterator**
- Array: `{{4.platforms}}`
6A. **Twitter: Create a tweet**
- Text: `{{4.content}}\n\n{{4.link}}`
6B. **LinkedIn: Create a post**
- Text: `{{4.content}}\n\n{{4.link}}`
6C. **Facebook: Create a post**
- Message: `{{4.content}}`
- Link: `{{4.link}}`
### 4. Document Processing Workflow
**Flow:**
```
Google Drive: Watch files
→ Filter: PDFs only
→ OCR.space: Extract text
→ OpenAI: Summarize & extract data
→ Router:
├─ Success → Google Sheets: Log + Email summary
└─ Error → Slack: Notify failure
```
**Module Configuration:**
1. **Google Drive: Watch files**
- Folder: Inbox
- Types: application/pdf
- Limit: 10
2. **Filter**
- Condition: File name contains "invoice" OR "receipt"
3. **HTTP: Make a request (OCR.space)**
- URL: https://api.ocr.space/parse/image
- Method: POST
- Headers: apikey: YOUR_OCR_KEY
- Body: file: `{{1.data}}`
4. **OpenAI: Create completion**
- Prompt: `Extract structured data from this document:\n\n{{3.ParsedResults[0].ParsedText}}\n\nProvide: Date, Amount, Vendor, Category`
- Format: JSON mode
5. **Google Sheets: Add a row**
- Spreadsheet: Document Log
- Date: `{{4.date}}`
- Amount: `{{4.amount}}`
- Vendor: `{{4.vendor}}`
- Category: `{{4.category}}`
6. **Gmail: Send an email**
- To: accounting@company.com
- Subject: New document processed: `{{1.name}}`
- 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
→ Router:
├─ Urgent → Assign to senior agent + Slack alert
├─ Normal → Assign to queue + Draft response
└─ Low → Auto-respond with KB articles
```
**Module Configuration:**
1. **Zendesk: Watch tickets**
- Status: new
- Limit: 20
2. **OpenAI: Create completion**
- Prompt: `Classify this support ticket:\n\nSubject: {{1.subject}}\nDescription: {{1.description}}\n\nProvide:\n1. Urgency (high/medium/low)\n2. Category (billing/technical/general)\n3. Suggested response`
3. **Router**
- Route 1: Urgency = "high"
- Route 2: Urgency = "medium"
- Route 3: Urgency = "low"
4A. **Zendesk: Update ticket** (Urgent)
- 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)
- Priority: normal
- Comment: `{{2.suggested_response}}`
- Status: pending
6. **Zendesk: Update ticket** (Low)
- Comment: Auto-generated response + KB links
- Status: solved
## Best Practices
1. **Always add error handlers** to critical modules
2. **Use filters early** to reduce operations
3. **Test with sample data** before activating
4. **Monitor operations usage** in Make dashboard
5. **Add notes to modules** for documentation
6. **Use variables** for reusable values
7. **Set up notifications** for failures
8. **Clone scenarios** before major changes
## Output Format
When generating a scenario, provide:
```markdown
## Scenario: [Name]
### Business Value
[What problem this solves]
### Visual Flow
[ASCII diagram or clear description]
### Module Configuration
[Detailed setup for each module]
### Data Mapping
[How data flows between modules]
### Testing Steps
1. [Step by step testing instructions]
### Cost Estimate
- Operations per execution: X
- Expected monthly runs: Y
- Total operations: Z
- Make plan needed: [Free/Core/Pro]
### Setup Time
Estimated: [X] minutes
```
This helps users implement Make.com scenarios quickly with clear, actionable instructions.

89
plugin.lock.json Normal file
View File

@@ -0,0 +1,89 @@
{
"$schema": "internal://schemas/plugin.lock.v1.json",
"pluginId": "gh:jeremylongshore/claude-code-plugins-plus:plugins/ai-agency/make-scenario-builder",
"normalized": {
"repo": null,
"ref": "refs/tags/v20251128.0",
"commit": "f48a684229e630f826bc46a91917c7e005550912",
"treeHash": "90c1f08faef80113c8c77c7fcc0c00ec11410eb789711e255d212df4454959b6",
"generatedAt": "2025-11-28T10:18:33.022490Z",
"toolVersion": "publish_plugins.py@0.2.0"
},
"origin": {
"remote": "git@github.com:zhongweili/42plugin-data.git",
"branch": "master",
"commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
"repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
},
"manifest": {
"name": "make-scenario-builder",
"description": "Create Make.com (Integromat) scenarios with AI assistance - visual automation design",
"version": "1.0.0"
},
"content": {
"files": [
{
"path": "README.md",
"sha256": "94cd4845800062cc474a0131acaf6e26ddfd52c02d22a48b18e78c24cd23aa81"
},
{
"path": "agents/make-expert.md",
"sha256": "d75b7aa4b9ebfb7b395da7740a71e017955274f69a0a772df54157f6f826cceb"
},
{
"path": ".claude-plugin/plugin.json",
"sha256": "e35ae540638913564e71b9c372f24a00e2dfea9693ca6bb312e3467a2ca34164"
},
{
"path": "commands/make-builder.md",
"sha256": "b915872214506e998d5102a1ad1565ea9970ac44a651a3b914d9728b08eb0f98"
},
{
"path": "skills/skill-adapter/references/examples.md",
"sha256": "922bbc3c4ebf38b76f515b5c1998ebde6bf902233e00e2c5a0e9176f975a7572"
},
{
"path": "skills/skill-adapter/references/best-practices.md",
"sha256": "c8f32b3566252f50daacd346d7045a1060c718ef5cfb07c55a0f2dec5f1fb39e"
},
{
"path": "skills/skill-adapter/references/README.md",
"sha256": "f89e7505f38100496e0c7bf035bff55c156ec066e5de2ea835cb9a92e7d349e4"
},
{
"path": "skills/skill-adapter/scripts/helper-template.sh",
"sha256": "0881d5660a8a7045550d09ae0acc15642c24b70de6f08808120f47f86ccdf077"
},
{
"path": "skills/skill-adapter/scripts/validation.sh",
"sha256": "92551a29a7f512d2036e4f1fb46c2a3dc6bff0f7dde4a9f699533e446db48502"
},
{
"path": "skills/skill-adapter/scripts/README.md",
"sha256": "3f69c6372953e89b455921c46fe8e14926d096187d4b8c6b0220c1a39f664a53"
},
{
"path": "skills/skill-adapter/assets/test-data.json",
"sha256": "ac17dca3d6e253a5f39f2a2f1b388e5146043756b05d9ce7ac53a0042eee139d"
},
{
"path": "skills/skill-adapter/assets/README.md",
"sha256": "694fbc7c060ec92fa8302fde6e0d6acfb6bb3205c75c3a03513c5568796d3f03"
},
{
"path": "skills/skill-adapter/assets/skill-schema.json",
"sha256": "f5639ba823a24c9ac4fb21444c0717b7aefde1a4993682897f5bf544f863c2cd"
},
{
"path": "skills/skill-adapter/assets/config-template.json",
"sha256": "0c2ba33d2d3c5ccb266c0848fc43caa68a2aa6a80ff315d4b378352711f83e1c"
}
],
"dirSha256": "90c1f08faef80113c8c77c7fcc0c00ec11410eb789711e255d212df4454959b6"
},
"security": {
"scannedAt": null,
"scannerVersion": null,
"flags": []
}
}

View File

@@ -0,0 +1,6 @@
# Assets
Bundled resources for make-scenario-builder skill
- [ ] scenario_templates/: A collection of pre-built Make.com scenario templates for common use cases.
- [ ] example_scenarios/: JSON examples of complex Make.com scenarios.

View File

@@ -0,0 +1,32 @@
{
"skill": {
"name": "skill-name",
"version": "1.0.0",
"enabled": true,
"settings": {
"verbose": false,
"autoActivate": true,
"toolRestrictions": true
}
},
"triggers": {
"keywords": [
"example-trigger-1",
"example-trigger-2"
],
"patterns": []
},
"tools": {
"allowed": [
"Read",
"Grep",
"Bash"
],
"restricted": []
},
"metadata": {
"author": "Plugin Author",
"category": "general",
"tags": []
}
}

View File

@@ -0,0 +1,28 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "Claude Skill Configuration",
"type": "object",
"required": ["name", "description"],
"properties": {
"name": {
"type": "string",
"pattern": "^[a-z0-9-]+$",
"maxLength": 64,
"description": "Skill identifier (lowercase, hyphens only)"
},
"description": {
"type": "string",
"maxLength": 1024,
"description": "What the skill does and when to use it"
},
"allowed-tools": {
"type": "string",
"description": "Comma-separated list of allowed tools"
},
"version": {
"type": "string",
"pattern": "^\\d+\\.\\d+\\.\\d+$",
"description": "Semantic version (x.y.z)"
}
}
}

View File

@@ -0,0 +1,27 @@
{
"testCases": [
{
"name": "Basic activation test",
"input": "trigger phrase example",
"expected": {
"activated": true,
"toolsUsed": ["Read", "Grep"],
"success": true
}
},
{
"name": "Complex workflow test",
"input": "multi-step trigger example",
"expected": {
"activated": true,
"steps": 3,
"toolsUsed": ["Read", "Write", "Bash"],
"success": true
}
}
],
"fixtures": {
"sampleInput": "example data",
"expectedOutput": "processed result"
}
}

View File

@@ -0,0 +1,7 @@
# References
Bundled resources for make-scenario-builder skill
- [ ] make_api_reference.md: Documentation of the Make.com API endpoints and data structures.
- [ ] make_module_library.md: A comprehensive list of available Make.com modules and their functionalities.
- [ ] scenario_design_best_practices.md: Best practices for designing efficient and robust Make.com scenarios.

View File

@@ -0,0 +1,69 @@
# Skill Best Practices
Guidelines for optimal skill usage and development.
## For Users
### Activation Best Practices
1. **Use Clear Trigger Phrases**
- Match phrases from skill description
- Be specific about intent
- Provide necessary context
2. **Provide Sufficient Context**
- Include relevant file paths
- Specify scope of analysis
- Mention any constraints
3. **Understand Tool Permissions**
- Check allowed-tools in frontmatter
- Know what the skill can/cannot do
- Request appropriate actions
### Workflow Optimization
- Start with simple requests
- Build up to complex workflows
- Verify each step before proceeding
- Use skill consistently for related tasks
## For Developers
### Skill Development Guidelines
1. **Clear Descriptions**
- Include explicit trigger phrases
- Document all capabilities
- Specify limitations
2. **Proper Tool Permissions**
- Use minimal necessary tools
- Document security implications
- Test with restricted tools
3. **Comprehensive Documentation**
- Provide usage examples
- Document common pitfalls
- Include troubleshooting guide
### Maintenance
- Keep version updated
- Test after tool updates
- Monitor user feedback
- Iterate on descriptions
## Performance Tips
- Scope skills to specific domains
- Avoid overlapping trigger phrases
- Keep descriptions under 1024 chars
- Test activation reliability
## Security Considerations
- Never include secrets in skill files
- Validate all inputs
- Use read-only tools when possible
- Document security requirements

View File

@@ -0,0 +1,70 @@
# Skill Usage Examples
This document provides practical examples of how to use this skill effectively.
## Basic Usage
### Example 1: Simple Activation
**User Request:**
```
[Describe trigger phrase here]
```
**Skill Response:**
1. Analyzes the request
2. Performs the required action
3. Returns results
### 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
4. Step 4: Validation
## Advanced Patterns
### Pattern 1: Chaining Operations
Combine this skill with other tools:
```
Step 1: Use this skill for [purpose]
Step 2: Chain with [other tool]
Step 3: Finalize with [action]
```
### Pattern 2: Error Handling
If issues occur:
- Check trigger phrase matches
- Verify context is available
- Review allowed-tools permissions
## Tips & Best Practices
- ✅ Be specific with trigger phrases
- ✅ Provide necessary context
- ✅ Check tool permissions match needs
- ❌ Avoid vague requests
- ❌ Don't mix unrelated tasks
## Common Issues
**Issue:** Skill doesn't activate
**Solution:** Use exact trigger phrases from description
**Issue:** Unexpected results
**Solution:** Check input format and context
## See Also
- Main SKILL.md for full documentation
- scripts/ for automation helpers
- assets/ for configuration examples

View File

@@ -0,0 +1,7 @@
# Scripts
Bundled resources for make-scenario-builder skill
- [ ] create_scenario.py: Script to generate Make.com scenario JSON from natural language input.
- [ ] validate_scenario.py: Script to validate the generated Make.com scenario JSON against the Make.com API schema.
- [ ] deploy_scenario.py: Script to deploy the generated Make.com scenario to a Make.com account using the API.

View File

@@ -0,0 +1,42 @@
#!/bin/bash
# Helper script template for skill automation
# Customize this for your skill's specific needs
set -e
function show_usage() {
echo "Usage: $0 [options]"
echo ""
echo "Options:"
echo " -h, --help Show this help message"
echo " -v, --verbose Enable verbose output"
echo ""
}
# Parse arguments
VERBOSE=false
while [[ $# -gt 0 ]]; do
case $1 in
-h|--help)
show_usage
exit 0
;;
-v|--verbose)
VERBOSE=true
shift
;;
*)
echo "Unknown option: $1"
show_usage
exit 1
;;
esac
done
# Your skill logic here
if [ "$VERBOSE" = true ]; then
echo "Running skill automation..."
fi
echo "✅ Complete"

View File

@@ -0,0 +1,32 @@
#!/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"