[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CF6EX71P8SQPA2YEGHP6A2":3,"skill-same:01M7CF6EX71P8SQPA2YEGHP6A2":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7CF6EX71P8SQPA2YEGHP6A2","zapier-make-patterns",null,"No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: zapier-make-patterns\ndescription: No-code automation democratizes workflow building. Zapier and Make\n  (formerly Integromat) let non-developers automate business processes without\n  writing code. But no-code doesn't mean no-complexity - these platforms have\n  their own patterns, pitfalls, and breaking points.\nrisk: unknown\nsource: vibeship-spawner-skills (Apache 2.0)\ndate_added: 2026-02-27\n---\n\n# Zapier & Make Patterns\n\nNo-code automation democratizes workflow building. Zapier and Make (formerly\nIntegromat) let non-developers automate business processes without writing\ncode. But no-code doesn't mean no-complexity - these platforms have their\nown patterns, pitfalls, and breaking points.\n\nThis skill covers when to use which platform, how to build reliable\nautomations, and when to graduate to code-based solutions. Key insight:\nZapier optimizes for simplicity and integrations (7000+ apps), Make\noptimizes for power and cost-efficiency (visual branching, operations-based\npricing).\n\nCritical distinction: No-code works until it doesn't. Know the limits.\n\n## Principles\n\n- Start simple, add complexity only when needed\n- Test with real data before going live\n- Document every automation with clear naming\n- Monitor errors - 95% error rate auto-disables Zaps\n- Know when to graduate to code-based solutions\n- Operations\u002Ftasks cost money - design efficiently\n\n## Capabilities\n\n- zapier\n- make\n- integromat\n- no-code-automation\n- zaps\n- scenarios\n- workflow-builders\n- business-process-automation\n\n## Scope\n\n- code-based-workflows → workflow-automation\n- browser-automation → browser-automation\n- custom-integrations → backend\n- api-development → api-designer\n\n## Tooling\n\n### Platforms\n\n- Zapier - When: Simple automations, maximum app coverage, beginners Note: 7000+ integrations, linear workflows, task-based pricing\n- Make - When: Complex workflows, visual branching, budget-conscious Note: Visual scenarios, operations pricing, powerful data handling\n- n8n - When: Self-hosted, code-friendly, unlimited operations Note: Open-source, can add custom code, technical users\n\n### Ai_features\n\n- Zapier Agents - When: AI-powered autonomous automation Note: Natural language instructions, 7000+ app access\n- Zapier Copilot - When: Building Zaps with AI assistance Note: Describes workflow, AI builds it\n- Zapier MCP - When: LLM tools accessing Zapier actions Note: 30,000+ actions available to AI models\n\n## Patterns\n\n### Basic Trigger-Action Pattern\n\nSingle trigger leads to one or more actions\n\n**When to use**: Simple notifications, data sync, basic workflows\n\n# BASIC TRIGGER-ACTION:\n\n\"\"\"\n[Trigger] → [Action]\n  e.g., New Email → Create Task\n\"\"\"\n\n## Zapier Example\n\"\"\"\nZap Name: \"Gmail New Email → Todoist Task\"\n\nTRIGGER: Gmail - New Email\n  - From: specific-sender@example.com\n  - Has attachment: yes\n\nACTION: Todoist - Create Task\n  - Project: Inbox\n  - Content: {{Email Subject}}\n  - Description: From: {{Email From}}\n  - Due date: Tomorrow\n\"\"\"\n\n## Make Example\n\"\"\"\nScenario: \"Gmail to Todoist\"\n\n[Gmail: Watch Emails] → [Todoist: Create a Task]\n\nGmail Module:\n  - Folder: INBOX\n  - From: specific-sender@example.com\n\nTodoist Module:\n  - Project ID: (select from dropdown)\n  - Content: {{1.subject}}\n  - Due String: tomorrow\n\"\"\"\n\n## Best Practices:\n- Use descriptive Zap\u002FScenario names\n- Test with real sample data\n- Use filters to prevent unwanted runs\n\n### Multi-Step Sequential Pattern\n\nChain of actions executed in order\n\n**When to use**: Multi-app workflows, data enrichment pipelines\n\n# MULTI-STEP SEQUENTIAL:\n\n\"\"\"\n[Trigger] → [Action 1] → [Action 2] → [Action 3]\nEach step's output available to subsequent steps\n\"\"\"\n\n## Zapier Multi-Step Zap\n\"\"\"\nZap: \"New Lead → CRM → Slack → Email\"\n\n1. TRIGGER: Typeform - New Entry\n   - Form: Lead Capture Form\n\n2. ACTION: HubSpot - Create Contact\n   - Email: {{Typeform Email}}\n   - First Name: {{Typeform First Name}}\n   - Lead Source: \"Website Form\"\n\n3. ACTION: Slack - Send Channel Message\n   - Channel: #sales-leads\n   - Message: \"New lead: {{Typeform Name}} from {{Typeform Company}}\"\n\n4. ACTION: Gmail - Send Email\n   - To: {{Typeform Email}}\n   - Subject: \"Thanks for reaching out!\"\n   - Body: (template with personalization)\n\"\"\"\n\n## Make Scenario\n\"\"\"\n[Typeform] → [HubSpot] → [Slack] → [Gmail]\n\n- Each module passes data to the next\n- Use {{N.field}} to reference module N's output\n- Add error handlers between critical steps\n\"\"\"\n\n### Conditional Branching Pattern\n\nDifferent actions based on conditions\n\n**When to use**: Different handling for different data types\n\n# CONDITIONAL BRANCHING:\n\n\"\"\"\n              ┌→ [Action A] (condition met)\n[Trigger] ───┤\n              └→ [Action B] (condition not met)\n\"\"\"\n\n## Zapier Paths (Pro+ required)\n\"\"\"\nZap: \"Route Support Tickets\"\n\n1. TRIGGER: Zendesk - New Ticket\n\n2. PATH A: If priority = \"urgent\"\n   - Slack: Post to #urgent-support\n   - PagerDuty: Create incident\n\n3. PATH B: If priority = \"normal\"\n   - Slack: Post to #support\n   - Asana: Create task\n\n4. PATH C: Otherwise (catch-all)\n   - Slack: Post to #support-overflow\n\"\"\"\n\n## Make Router\n\"\"\"\n[Zendesk: Watch Tickets]\n      ↓\n[Router]\n   ├── Route 1: priority = urgent\n   │     └→ [Slack] → [PagerDuty]\n   │\n   ├── Route 2: priority = normal\n   │     └→ [Slack] → [Asana]\n   │\n   └── Fallback route\n         └→ [Slack: overflow]\n\n# Make's visual router makes complex branching clear\n\"\"\"\n\n## Best Practices:\n- Always have a fallback\u002Felse path\n- Test each path independently\n- Document which conditions trigger which path\n\n### Data Transformation Pattern\n\nClean, format, and transform data between apps\n\n**When to use**: Apps expect different data formats\n\n# DATA TRANSFORMATION:\n\n## Zapier Formatter\n\"\"\"\nCommon transformations:\n\n1. Text manipulation:\n   - Split text: \"John Doe\" → First: \"John\", Last: \"Doe\"\n   - Capitalize: \"john\" → \"John\"\n   - Replace: Remove special characters\n\n2. Date formatting:\n   - Convert: \"2024-01-15\" → \"January 15, 2024\"\n   - Adjust: Add 7 days to date\n\n3. Numbers:\n   - Format currency: 1000 → \"$1,000.00\"\n   - Spreadsheet formula: =SUM(A1:A10)\n\n4. Lookup tables:\n   - Map status codes: \"1\" → \"Active\", \"2\" → \"Pending\"\n\"\"\"\n\n## Make Data Functions\n\"\"\"\nMake has powerful built-in functions:\n\nText:\n  {{lower(1.email)}}           # Lowercase\n  {{substring(1.name; 0; 10)}} # First 10 chars\n  {{replace(1.text; \"-\"; \"\")}} # Remove dashes\n\nArrays:\n  {{first(1.items)}}           # First item\n  {{length(1.items)}}          # Count items\n  {{map(1.items; \"id\")}}       # Extract field\n\nDates:\n  {{formatDate(1.date; \"YYYY-MM-DD\")}}\n  {{addDays(now; 7)}}\n\nMath:\n  {{round(1.price * 0.8; 2)}}  # 20% discount, 2 decimals\n\"\"\"\n\n## Best Practices:\n- Transform early in the workflow\n- Use filters to skip invalid data\n- Log transformations for debugging\n\n### Error Handling Pattern\n\nGraceful handling of failures\n\n**When to use**: Any production automation\n\n# ERROR HANDLING:\n\n## Zapier Error Handling\n\"\"\"\n1. Built-in retry (automatic):\n   - Zapier retries failed actions automatically\n   - Exponential backoff for temporary failures\n\n2. Error handling step:\n   Zap:\n     1. [Trigger]\n     2. [Action that might fail]\n     3. [Error Handler]\n        - If error → [Slack: Alert team]\n        - If error → [Email: Send report]\n\n3. Path-based handling:\n   [Action] → Path A: Success → [Continue]\n            → Path B: Error → [Alert + Log]\n\"\"\"\n\n## Make Error Handlers\n\"\"\"\nMake has visual error handling:\n\n[Module] ──┬── Success → [Next Module]\n           │\n           └── Error → [Error Handler]\n\nError handler types:\n1. Break: Stop scenario, send notification\n2. Rollback: Undo completed operations\n3. Commit: Save partial results, continue\n4. Ignore: Skip error, continue with next item\n\nExample:\n[API Call] → Error Handler (Ignore)\n           → [Log to Airtable: \"Failed: {{error.message}}\"]\n           → Continue scenario\n\"\"\"\n\n## Best Practices:\n- Always add error handlers for external APIs\n- Log errors to a spreadsheet\u002Fdatabase\n- Set up Slack\u002Femail alerts for critical failures\n- Test failure scenarios, not just success\n\n### Batch Processing Pattern\n\nProcess multiple items efficiently\n\n**When to use**: Importing data, bulk operations\n\n# BATCH PROCESSING:\n\n## Zapier Looping\n\"\"\"\nZap: \"Process Order Items\"\n\n1. TRIGGER: Shopify - New Order\n   - Returns: order with line_items array\n\n2. LOOPING: For each item in line_items\n   - Create inventory adjustment\n   - Update product count\n   - Log to spreadsheet\n\nNote: Each loop iteration counts as tasks!\n10 items = 10 tasks consumed\n\"\"\"\n\n## Make Iterator\n\"\"\"\n[Webhook: Receive Order]\n      ↓\n[Iterator: line_items]\n      ↓ (processes each item)\n[Inventory: Adjust Stock]\n      ↓\n[Aggregator: Collect Results]\n      ↓\n[Slack: Summary Message]\n\nIterator creates one bundle per item.\nAggregator combines results back together.\nUse Array Aggregator for collecting processed items.\n\"\"\"\n\n## Best Practices:\n- Use aggregators to combine results\n- Consider batch limits (some APIs limit to 100)\n- Watch operation\u002Ftask counts for cost\n- Add delays for rate-limited APIs\n\n### Scheduled Automation Pattern\n\nTime-based triggers instead of events\n\n**When to use**: Daily reports, periodic syncs, batch jobs\n\n# SCHEDULED AUTOMATION:\n\n## Zapier Schedule Trigger\n\"\"\"\nZap: \"Daily Sales Report\"\n\nTRIGGER: Schedule by Zapier\n  - Every: Day\n  - Time: 8:00 AM\n  - Timezone: America\u002FNew_York\n\nACTIONS:\n  1. Google Sheets: Get rows (yesterday's sales)\n  2. Formatter: Calculate totals\n  3. Gmail: Send report to team\n\"\"\"\n\n## Make Scheduled Scenarios\n\"\"\"\nScenario Schedule Options:\n  - Run once (manual)\n  - At regular intervals (every X minutes)\n  - Advanced: Cron expression (0 8 * * *)\n\n[Scheduled Trigger: Every day at 8 AM]\n      ↓\n[Google Sheets: Search Rows]\n      ↓\n[Iterator: Process each row]\n      ↓\n[Aggregator: Sum totals]\n      ↓\n[Gmail: Send Report]\n\"\"\"\n\n## Best Practices:\n- Consider timezone differences\n- Add buffer time for long-running jobs\n- Log execution times for monitoring\n- Don't schedule at exactly midnight (busy period)\n\n## Sharp Edges\n\n### Using Text Instead of IDs in Dropdown Fields\n\nSeverity: CRITICAL\n\nSituation: Configuring actions with dropdown selections\n\nSymptoms:\n\"Bad Request\" errors. \"Invalid value\" messages. Action fails\ndespite correct-looking input. Works when you select from dropdown,\nfails with dynamic values.\n\nWhy this breaks:\nDropdown menus display human-readable text but send IDs to APIs.\nWhen you type \"Marketing Team\" instead of selecting it, Zapier\ntries to send that text as the ID, which the API doesn't recognize.\n\nRecommended fix:\n\n# ALWAYS use dropdowns to select, don't type\n\n# If you need dynamic values:\n\n## Zapier approach:\n1. Add a \"Find\" or \"Search\" action first\n   - HubSpot: Find Contact → returns contact_id\n   - Slack: Find User by Email → returns user_id\n\n2. Use the returned ID in subsequent actions\n   - Dropdown: Use Custom Value\n   - Select the ID from the search step\n\n## Make approach:\n1. Add a Search module first\n   - Search Contacts: filter by email\n   - Returns: contact_id\n\n2. Map the ID to subsequent modules\n   - Contact ID: {{2.id}} (from search module)\n\n# Common ID fields that trip people up:\n- User\u002FMember IDs in Slack, Teams\n- Contact\u002FCompany IDs in CRMs\n- Project\u002FFolder IDs in project tools\n- Category\u002FTag IDs in content systems\n\n### Zap Auto-Disabled at 95% Error Rate\n\nSeverity: CRITICAL\n\nSituation: Running a Zap with frequent errors\n\nSymptoms:\nZap suddenly stops running. Email notification about auto-disable.\n\"This Zap was automatically turned off\" message. Data stops syncing.\n\nWhy this breaks:\nZapier automatically disables Zaps that have 95% or higher error\nrate over 7 days. This prevents runaway automation failures from\nconsuming your task quota and creating data problems.\n\nRecommended fix:\n\n# Prevention:\n\n1. Add error handling steps:\n   - Use Path: If error → [Log + Alert]\n   - Add fallback actions for failures\n\n2. Use filters to prevent bad data:\n   - Only continue if email exists\n   - Only continue if amount > 0\n   - Filter out test\u002Finvalid entries\n\n3. Monitor task history regularly:\n   - Check for recurring errors\n   - Fix issues before 95% threshold\n\n# Recovery:\n\n1. Check Task History for error patterns\n2. Fix the root cause (auth, bad data, API changes)\n3. Test with sample data\n4. Re-enable the Zap manually\n5. Monitor closely for next 24 hours\n\n# Common causes:\n- Expired authentication tokens\n- API rate limits\n- Changed field names in connected apps\n- Invalid data formats\n\n### Loops Consuming Unexpected Task Counts\n\nSeverity: HIGH\n\nSituation: Processing arrays or multiple items\n\nSymptoms:\nTask quota depleted unexpectedly. One Zap run shows as 100+ tasks.\nMonthly limit reached in days. \"You've used X of Y tasks\" surprise.\n\nWhy this breaks:\nIn Zapier, each iteration of a loop counts as separate tasks.\nIf a webhook delivers an order with 50 line items and you loop\nthrough each, that's 50+ tasks for one order.\n\nRecommended fix:\n\n# Understand the math:\n\nOrder with 10 items, 5 actions per item:\n= 1 trigger + (10 items × 5 actions) = 51 tasks\n\n# Strategies to reduce task usage:\n\n1. Batch operations when possible:\n   - Use \"Create Many Rows\" instead of loop + create\n   - Use bulk API endpoints\n\n2. Aggregate before sending:\n   - Collect all items\n   - Send one summary message, not one per item\n\n3. Filter before looping:\n   - Only process items that need action\n   - Skip unchanged\u002Fduplicate items\n\n4. Consider Make for high-volume:\n   - Make uses operations, not tasks per action\n   - More cost-effective for loops\n\n# Make approach:\n[Iterator] → [Actions] → [Aggregator]\n- Pay for operations (module executions)\n- Not per-action like Zapier\n\n### App Updates Breaking Existing Zaps\n\nSeverity: HIGH\n\nSituation: App you're connected to releases updates\n\nSymptoms:\nWorking Zap suddenly fails. \"Field not found\" errors. Different\ndata format in outputs. Actions that worked yesterday fail today.\n\nWhy this breaks:\nWhen connected apps update their APIs, field names can change,\nnew required fields appear, or data formats shift. Zapier\u002FMake\nintegrations may not immediately update to match.\n\nRecommended fix:\n\n# When a Zap breaks after app update:\n\n1. Check the Task History for specific errors\n2. Open the Zap editor to see field mapping issues\n3. Re-select the trigger\u002Faction to refresh schema\n4. Re-map any fields that show as \"unknown\"\n5. Test with new sample data\n\n# Prevention:\n\n1. Subscribe to changelog for critical apps\n2. Keep connection authorizations fresh\n3. Test Zaps after major app updates\n4. Document your field mappings\n5. Use test\u002Fduplicate Zaps for experiments\n\n# If integration is outdated:\n- Check Zapier\u002FMake status pages\n- Report issue to support\n- Consider webhook alternative temporarily\n\n# Common offenders:\n- CRM field restructures\n- API version upgrades\n- OAuth scope changes\n- New required permissions\n\n### Authentication Tokens Expiring\n\nSeverity: HIGH\n\nSituation: Using OAuth connections to apps\n\nSymptoms:\n\"Authentication failed\" errors. \"Please reconnect\" messages.\nZaps fail after weeks of working. Multiple apps fail simultaneously.\n\nWhy this breaks:\nOAuth tokens expire. Some apps require re-authentication every\n60-90 days. If the user who connected the app leaves the company,\ntheir connection may stop working.\n\nRecommended fix:\n\n# Immediate fix:\n1. Go to Settings → Apps\n2. Find the app with issues\n3. Reconnect (re-authorize)\n4. Test affected Zaps\n\n# Prevention:\n\n1. Use service accounts for connections\n   - Don't connect with personal accounts\n   - Use shared team email\u002Faccount\n\n2. Monitor connection health\n   - Check Apps page regularly\n   - Set calendar reminders for known expiration\n\n3. Document who connected what\n   - Track in spreadsheet\n   - Handoff process when people leave\n\n4. Prefer connections that don't expire\n   - API keys over OAuth when available\n   - Long-lived tokens\n\n# Zapier Enterprise:\n- Admin controls for managing connections\n- SSO integration\n- Centralized connection management\n\n### Webhooks Missing or Duplicating Events\n\nSeverity: MEDIUM\n\nSituation: Using webhooks as triggers\n\nSymptoms:\nSome events never trigger the Zap. Same event triggers multiple\ntimes. Inconsistent automation behavior. \"Works sometimes.\"\n\nWhy this breaks:\nWebhooks are fire-and-forget. If Zapier's receiving endpoint is\nslow or unavailable, the webhook may fail. Some systems retry\nwebhooks, causing duplicates. Network issues lose events.\n\nRecommended fix:\n\n# Handle duplicates:\n\n1. Add deduplication logic:\n   - Filter: Only continue if ID not in Airtable\n   - First action: Check if already processed\n\n2. Use idempotency:\n   - Store processed IDs\n   - Skip if ID exists\n\n## Zapier example:\n[Webhook Trigger]\n   ↓\n[Airtable: Find Records] - search by event_id\n   ↓\n[Filter: Only continue if not found]\n   ↓\n[Process Event]\n   ↓\n[Airtable: Create Record] - store event_id\n\n# Handle missed events:\n\n1. Use polling triggers for critical data\n   - Less real-time but more reliable\n   - Catches events during downtime\n\n2. Implement reconciliation:\n   - Scheduled Zap to check for gaps\n   - Compare source data to processed data\n\n3. Check source system retry settings:\n   - Some systems retry on failure\n   - Configure retry count\u002Ftiming\n\n### Make Operations Consumed by Error Retries\n\nSeverity: MEDIUM\n\nSituation: Scenarios with failing modules\n\nSymptoms:\nOperations quota depleted quickly. Scenario runs \"succeeded\" but\nused many operations. Same scenario running more than expected.\n\nWhy this breaks:\nMake counts operations per module execution, including failed\nattempts and retries. Error handler modules consume operations.\nScenarios that fail and retry can use 3-5x expected operations.\n\nRecommended fix:\n\n# Understand operation counting:\n\nSuccessful run: Each module = 1 operation\nFailed + retry (3x): 3 operations for that module\nError handler: Additional operation per handler module\n\n# Reduce operation waste:\n\n1. Add error handlers that break early:\n   [Module] → Error → [Break] (1 additional op)\n   vs\n   [Module] → Error → [Log] → [Alert] → [Update] (3+ ops)\n\n2. Use ignore instead of retry when appropriate:\n   - If failure is expected (record exists)\n   - If retrying won't help (bad data)\n\n3. Pre-validate before expensive operations:\n   [Check Data] → Filter → [API Call]\n   - Fail fast before consuming operations\n\n4. Optimize scenario scheduling:\n   - Don't run every minute if hourly is enough\n   - Use webhooks for real-time when possible\n\n# Monitor usage:\n- Check Operations dashboard\n- Set up usage alerts\n- Review high-consumption scenarios\n\n### Timezone Mismatches in Scheduled Triggers\n\nSeverity: MEDIUM\n\nSituation: Setting up scheduled automations\n\nSymptoms:\nZap runs at wrong time. \"9 AM\" trigger fires at 2 PM. Different\nbehavior on different days. DST causes hour shifts.\n\nWhy this breaks:\nZapier shows times in your local timezone but may store in UTC.\nIf you change timezones or DST occurs, scheduled times shift.\nTeam members in different zones see different times.\n\nRecommended fix:\n\n# Best practices:\n\n1. Explicitly set timezone in schedule:\n   - Don't rely on browser detection\n   - Use business timezone, not personal\n\n2. Document in Zap name:\n   - \"Daily Report 9AM EST\"\n   - Include timezone in description\n\n3. Test around DST transitions:\n   - Schedule changes at DST boundaries\n   - Verify times before\u002Fafter change\n\n4. For global teams:\n   - Use UTC as standard\n   - Convert to local in descriptions\n\n5. Consider buffer times:\n   - Don't schedule at exactly midnight\n   - Avoid on-the-hour (busy periods)\n\n## Make timezone handling:\n- Scenarios use account timezone setting\n- formatDate() function respects timezone\n- Use parseDate() with explicit timezone\n\n## Collaboration\n\n### Delegation Triggers\n\n- automation requires custom code -> workflow-automation (Code-based solutions like Inngest, Temporal)\n- need browser automation in workflow -> browser-automation (Playwright\u002FPuppeteer integration)\n- building custom API integration -> api-designer (API design and implementation)\n- automation needs AI capabilities -> agent-tool-builder (AI agent tools and Zapier MCP)\n- high-volume data processing -> backend (Custom backend processing)\n- need self-hosted automation -> devops (n8n or custom workflow deployment)\n\n## Related Skills\n\nWorks well with: `workflow-automation`, `agent-tool-builder`, `backend`, `api-designer`\n\n## When to Use\n- User mentions or implies: zapier\n- User mentions or implies: make\n- User mentions or implies: integromat\n- User mentions or implies: zap\n- User mentions or implies: scenario\n- User mentions or implies: no-code automation\n- User mentions or implies: trigger action\n- User mentions or implies: workflow automation\n- User mentions or implies: connect apps\n- User mentions or implies: automate\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# Zapier & Make Patterns\n\nNo-code automation democratizes workflow building. Zapier and Make (formerly\nIntegromat) let non-developers automate business processes without writing\ncode. But no-code doesn't mean no-complexity - these platforms have their\nown patterns, pitfalls, and breaking points.\n\nThis skill covers when to use which platform, how to build reliable\nautomations, and when to graduate to code-based solutions. Key insight:\nZapier optimizes for simplicity and integrations (7000+ apps), Make\noptimizes for power and cost-efficiency (visual branching, operations-based\npricing).\n\nCritical distinction: No-code works until it doesn't. Know the limits.\n\n## Principles\n\n- Start simple, add complexity only when needed\n- Test with real data before going live\n- Document every automation with clear naming\n- Monitor errors - 95% error rate auto-disables Zaps\n- Know when to graduate to code-based solutions\n- Operations\u002Ftasks cost money - design efficiently\n\n## Capabilities\n\n- zapier\n- make\n- integromat\n- no-code-automation\n- zaps\n- scenarios\n- workflow-builders\n- business-process-automation\n\n## Scope\n\n- code-based-workflows → workflow-automation\n- browser-automation → browser-automation\n- custom-integrations → backend\n- api-development → api-designer\n\n## Tooling\n\n### Platforms\n\n- Zapier - When: Simple automations, maximum app coverage, beginners Note: 7000+ integrations, linear workflows, task-based pricing\n- Make - When: Complex workflows, visual branching, budget-conscious Note: Visual scenarios, operations pricing, powerful data handling\n- n8n - When: Self-hosted, code-friendly, unlimited operations Note: Open-source, can add custom code, technical users\n\n### Ai_features\n\n- Zapier Agents - When: AI-powered autonomous automation Note: Natural language instructions, 7000+ app access\n- Zapier Copilot - When: Building Zaps with AI assistance Note: Describes workflow, AI builds it\n- Zapier MCP - When: LLM tools accessing Zapier actions Note: 30,000+ actions available to AI models\n\n## Patterns\n\n### Basic Trigger-Action Pattern\n\nSingle trigger leads to one or more actions\n\n**When to use**: Simple notifications, data sync, basic workflows\n\n# BASIC TRIGGER-ACTION:\n\n\"\"\"\n[Trigger] → [Action]\n  e.g., New Email → Create Task\n\"\"\"\n\n## Zapier Example\n\"\"\"\nZap Name: \"Gmail New Email → Todoist Task\"\n\nTRIGGER: Gmail - New Email\n  - From: specific-sender@example.com\n  - Has attachment: yes\n\nACTION: Todoist - Create Task\n  - Project: Inbox\n  - Content: {{Email Subject}}\n  - Description: From: {{Email From}}\n  - Due date: Tomorrow\n\"\"\"\n\n## Make Example\n\"\"\"\nScenario: \"Gmail to Todoist\"\n\n[Gmail: Watch Emails] → [Todoist: Create a Task]\n\nGmail Module:\n  - Folder: INBOX\n  - From: specific-sender@example.com\n\nTodoist Module:\n  - Project ID: (select from dropdown)\n  - Content: {{1.subject}}\n  - Due String: tomorrow\n\"\"\"\n\n## Best Practices:\n- Use descriptive Zap\u002FScenario names\n- Test with real sample data\n- Use filters to prevent unwanted runs\n\n### Multi-Step Sequential Pattern\n\nChain of actions executed in order\n\n**When to use**: Multi-app workflows, data enrichment pipelines\n\n# MULTI-STEP SEQUENTIAL:\n\n\"\"\"\n[Trigger] → [Action 1] → [Action 2] → [Action 3]\nEach step's output available to subsequent steps\n\"\"\"\n\n## Zapier Multi-Step Zap\n\"\"\"\nZap: \"New Lead → CRM → Slack → Email\"\n\n1. TRIGGER: Typeform - New Entry\n   - Form: Lead Capture Form\n\n2. ACTION: HubSpot - Create Contact\n   - Email: {{Typeform Email}}\n   - First Name: {{Typeform First Name}}\n   - Lead Source: \"Website Form\"\n\n3. ACTION: Slack - Send Channel Message\n   - Channel: #sales-leads\n   - Message: \"New lead: {{Typeform Name}} from {{Typeform Company}}\"\n\n4. ACTION: Gmail - Send Email\n   - To: {{Typeform Email}}\n   - Subject: \"Thanks for reaching out!\"\n   - Body: (template with personalization)\n\"\"\"\n\n## Make Scenario\n\"\"\"\n[Typeform] → [HubSpot] → [Slack] → [Gmail]\n\n- Each module passes data to the next\n- Use {{N.field}} to reference module N's output\n- Add error handlers between critical steps\n\"\"\"\n\n### Conditional Branching Pattern\n\nDifferent actions based on conditions\n\n**When to use**: Different handling for different data types\n\n# CONDITIONAL BRANCHING:\n\n\"\"\"\n              ┌→ [Action A] (condition met)\n[Trigger] ───┤\n              └→ [Action B] (condition not met)\n\"\"\"\n\n## Zapier Paths (Pro+ required)\n\"\"\"\nZap: \"Route Support Tickets\"\n\n1. TRIGGER: Zendesk - New Ticket\n\n2. PATH A: If priority = \"urgent\"\n   - Slack: Post to #urgent-support\n   - PagerDuty: Create incident\n\n3. PATH B: If priority = \"normal\"\n   - Slack: Post to #support\n   - Asana: Create task\n\n4. PATH C: Otherwise (catch-all)\n   - Slack: Post to #support-overflow\n\"\"\"\n\n## Make Router\n\"\"\"\n[Zendesk: Watch Tickets]\n      ↓\n[Router]\n   ├── Route 1: priority = urgent\n   │     └→ [Slack] → [PagerDuty]\n   │\n   ├── Route 2: priority = normal\n   │     └→ [Slack] → [Asana]\n   │\n   └── Fallback route\n         └→ [Slack: overflow]\n\n# Make's visual router makes complex branching clear\n\"\"\"\n\n## Best Practices:\n- Always have a fallback\u002Felse path\n- Test each path independently\n- Document which conditions trigger which path\n\n### Data Transformation Pattern\n\nClean, format, and transform data between apps\n\n**When to use**: Apps expect different data formats\n\n# DATA TRANSFORMATION:\n\n## Zapier Formatter\n\"\"\"\nCommon transformations:\n\n1. Text manipulation:\n   - Split text: \"John Doe\" → First: \"John\", Last: \"Doe\"\n   - Capitalize: \"john\" → \"John\"\n   - Replace: Remove special characters\n\n2. Date formatting:\n   - Convert: \"2024-01-15\" → \"January 15, 2024\"\n   - Adjust: Add 7 days to date\n\n3. Numbers:\n   - Format currency: 1000 → \"$1,000.00\"\n   - Spreadsheet formula: =SUM(A1:A10)\n\n4. Lookup tables:\n   - Map status codes: \"1\" → \"Active\", \"2\" → \"Pending\"\n\"\"\"\n\n## Make Data Functions\n\"\"\"\nMake has powerful built-in functions:\n\nText:\n  {{lower(1.email)}}           # Lowercase\n  {{substring(1.name; 0; 10)}} # First 10 chars\n  {{replace(1.text; \"-\"; \"\")}} # Remove dashes\n\nArrays:\n  {{first(1.items)}}           # First item\n  {{length(1.items)}}          # Count items\n  {{map(1.items; \"id\")}}       # Extract field\n\nDates:\n  {{formatDate(1.date; \"YYYY-MM-DD\")}}\n  {{addDays(now; 7)}}\n\nMath:\n  {{round(1.price * 0.8; 2)}}  # 20% discount, 2 decimals\n\"\"\"\n\n## Best Practices:\n- Transform early in the workflow\n- Use filters to skip invalid data\n- Log transformations for debugging\n\n### Error Handling Pattern\n\nGraceful handling of failures\n\n**When to use**: Any production automation\n\n# ERROR HANDLING:\n\n## Zapier Error Handling\n\"\"\"\n1. Built-in retry (automatic):\n   - Zapier retries failed actions automatically\n   - Exponential backoff for temporary failures\n\n2. Error handling step:\n   Zap:\n     1. [Trigger]\n     2. [Action that might fail]\n     3. [Error Handler]\n        - If error → [Slack: Alert team]\n        - If error → [Email: Send report]\n\n3. Path-based handling:\n   [Action] → Path A: Success → [Continue]\n            → Path B: Error → [Alert + Log]\n\"\"\"\n\n## Make Error Handlers\n\"\"\"\nMake has visual error handling:\n\n[Module] ──┬── Success → [Next Module]\n           │\n           └── Error → [Error Handler]\n\nError handler types:\n1. Break: Stop scenario, send notification\n2. Rollback: Undo completed operations\n3. Commit: Save partial results, continue\n4. Ignore: Skip error, continue with next item\n\nExample:\n[API Call] → Error Handler (Ignore)\n           → [Log to Airtable: \"Failed: {{error.message}}\"]\n           → Continue scenario\n\"\"\"\n\n## Best Practices:\n- Always add error handlers for external APIs\n- Log errors to a spreadsheet\u002Fdatabase\n- Set up Slack\u002Femail alerts for critical failures\n- Test failure scenarios, not just success\n\n### Batch Processing Pattern\n\nProcess multiple items efficiently\n\n**When to use**: Importing data, bulk operations\n\n# BATCH PROCESSING:\n\n## Zapier Looping\n\"\"\"\nZap: \"Process Order Items\"\n\n1. TRIGGER: Shopify - New Order\n   - Returns: order with line_items array\n\n2. LOOPING: For each item in line_items\n   - Create inventory adjustment\n   - Update product count\n   - Log to spreadsheet\n\nNote: Each loop iteration counts as tasks!\n10 items = 10 tasks consumed\n\"\"\"\n\n## Make Iterator\n\"\"\"\n[Webhook: Receive Order]\n      ↓\n[Iterator: line_items]\n      ↓ (processes each item)\n[Inventory: Adjust Stock]\n      ↓\n[Aggregator: Collect Results]\n      ↓\n[Slack: Summary Message]\n\nIterator creates one bundle per item.\nAggregator combines results back together.\nUse Array Aggregator for collecting processed items.\n\"\"\"\n\n## Best Practices:\n- Use aggregators to combine results\n- Consider batch limits (some APIs limit to 100)\n- Watch operation\u002Ftask counts for cost\n- Add delays for rate-limited APIs\n\n### Scheduled Automation Pattern\n\nTime-based triggers instead of events\n\n**When to use**: Daily reports, periodic syncs, batch jobs\n\n# SCHEDULED AUTOMATION:\n\n## Zapier Schedule Trigger\n\"\"\"\nZap: \"Daily Sales Report\"\n\nTRIGGER: Schedule by Zapier\n  - Every: Day\n  - Time: 8:00 AM\n  - Timezone: America\u002FNew_York\n\nACTIONS:\n  1. Google Sheets: Get rows (yesterday's sales)\n  2. Formatter: Calculate totals\n  3. Gmail: Send report to team\n\"\"\"\n\n## Make Scheduled Scenarios\n\"\"\"\nScenario Schedule Options:\n  - Run once (manual)\n  - At regular intervals (every X minutes)\n  - Advanced: Cron expression (0 8 * * *)\n\n[Scheduled Trigger: Every day at 8 AM]\n      ↓\n[Google Sheets: Search Rows]\n      ↓\n[Iterator: Process each row]\n      ↓\n[Aggregator: Sum totals]\n      ↓\n[Gmail: Send Report]\n\"\"\"\n\n## Best Practices:\n- Consider timezone differences\n- Add buffer time for long-running jobs\n- Log execution times for monitoring\n- Don't schedule at exactly midnight (busy period)\n\n## Sharp Edges\n\n### Using Text Instead of IDs in Dropdown Fields\n\nSeverity: CRITICAL\n\nSituation: Configuring actions with dropdown selections\n\nSymptoms:\n\"Bad Request\" errors. \"Invalid value\" messages. Action fails\ndespite correct-looking input. Works when you select from dropdown,\nfails with dynamic values.\n\nWhy this breaks:\nDropdown menus display human-readable text but send IDs to APIs.\nWhen you type \"Marketing Team\" instead of selecting it, Zapier\ntries to send that text as the ID, which the API doesn't recognize.\n\nRecommended fix:\n\n# ALWAYS use dropdowns to select, don't type\n\n# If you need dynamic values:\n\n## Zapier approach:\n1. Add a \"Find\" or \"Search\" action first\n   - HubSpot: Find Contact → returns contact_id\n   - Slack: Find User by Email → returns user_id\n\n2. Use the returned ID in subsequent actions\n   - Dropdown: Use Custom Value\n   - Select the ID from the search step\n\n## Make approach:\n1. Add a Search module first\n   - Search Contacts: filter by email\n   - Returns: contact_id\n\n2. Map the ID to subsequent modules\n   - Contact ID: {{2.id}} (from search module)\n\n# Common ID fields that trip people up:\n- User\u002FMember IDs in Slack, Teams\n- Contact\u002FCompany IDs in CRMs\n- Project\u002FFolder IDs in project tools\n- Category\u002FTag IDs in content systems\n\n### Zap Auto-Disabled at 95% Error Rate\n\nSeverity: CRITICAL\n\nSituation: Running a Zap with frequent errors\n\nSymptoms:\nZap suddenly stops running. Email notification about auto-disable.\n\"This Zap was automatically turned off\" message. Data stops syncing.\n\nWhy this breaks:\nZapier automatically disables Zaps that have 95% or higher error\nrate over 7 days. This prevents runaway automation failures from\nconsuming your task quota and creating data problems.\n\nRecommended fix:\n\n# Prevention:\n\n1. Add error handling steps:\n   - Use Path: If error → [Log + Alert]\n   - Add fallback actions for failures\n\n2. Use filters to prevent bad data:\n   - Only continue if email exists\n   - Only continue if amount > 0\n   - Filter out test\u002Finvalid entries\n\n3. Monitor task history regularly:\n   - Check for recurring errors\n   - Fix issues before 95% threshold\n\n# Recovery:\n\n1. Check Task History for error patterns\n2. Fix the root cause (auth, bad data, API changes)\n3. Test with sample data\n4. Re-enable the Zap manually\n5. Monitor closely for next 24 hours\n\n# Common causes:\n- Expired authentication tokens\n- API rate limits\n- Changed field names in connected apps\n- Invalid data formats\n\n### Loops Consuming Unexpected Task Counts\n\nSeverity: HIGH\n\nSituation: Processing arrays or multiple items\n\nSymptoms:\nTask quota depleted unexpectedly. One Zap run shows as 100+ tasks.\nMonthly limit reached in days. \"You've used X of Y tasks\" surprise.\n\nWhy this breaks:\nIn Zapier, each iteration of a loop counts as separate tasks.\nIf a webhook delivers an order with 50 line items and you loop\nthrough each, that's 50+ tasks for one order.\n\nRecommended fix:\n\n# Understand the math:\n\nOrder with 10 items, 5 actions per item:\n= 1 trigger + (10 items × 5 actions) = 51 tasks\n\n# Strategies to reduce task usage:\n\n1. Batch operations when possible:\n   - Use \"Create Many Rows\" instead of loop + create\n   - Use bulk API endpoints\n\n2. Aggregate before sending:\n   - Collect all items\n   - Send one summary message, not one per item\n\n3. Filter before looping:\n   - Only process items that need action\n   - Skip unchanged\u002Fduplicate items\n\n4. Consider Make for high-volume:\n   - Make uses operations, not tasks per action\n   - More cost-effective for loops\n\n# Make approach:\n[Iterator] → [Actions] → [Aggregator]\n- Pay for operations (module executions)\n- Not per-action like Zapier\n\n### App Updates Breaking Existing Zaps\n\nSeverity: HIGH\n\nSituation: App you're connected to releases updates\n\nSymptoms:\nWorking Zap suddenly fails. \"Field not found\" errors. Different\ndata format in outputs. Actions that worked yesterday fail today.\n\nWhy this breaks:\nWhen connected apps update their APIs, field names can change,\nnew required fields appear, or data formats shift. Zapier\u002FMake\nintegrations may not immediately update to match.\n\nRecommended fix:\n\n# When a Zap breaks after app update:\n\n1. Check the Task History for specific errors\n2. Open the Zap editor to see field mapping issues\n3. Re-select the trigger\u002Faction to refresh schema\n4. Re-map any fields that show as \"unknown\"\n5. Test with new sample data\n\n# Prevention:\n\n1. Subscribe to changelog for critical apps\n2. Keep connection authorizations fresh\n3. Test Zaps after major app updates\n4. Document your field mappings\n5. Use test\u002Fduplicate Zaps for experiments\n\n# If integration is outdated:\n- Check Zapier\u002FMake status pages\n- Report issue to support\n- Consider webhook alternative temporarily\n\n# Common offenders:\n- CRM field restructures\n- API version upgrades\n- OAuth scope changes\n- New required permissions\n\n### Authentication Tokens Expiring\n\nSeverity: HIGH\n\nSituation: Using OAuth connections to apps\n\nSymptoms:\n\"Authentication failed\" errors. \"Please reconnect\" messages.\nZaps fail after weeks of working. Multiple apps fail simultaneously.\n\nWhy this breaks:\nOAuth tokens expire. Some apps require re-authentication every\n60-90 days. If the user who connected the app leaves the company,\ntheir connection may stop working.\n\nRecommended fix:\n\n# Immediate fix:\n1. Go to Settings → Apps\n2. Find the app with issues\n3. Reconnect (re-authorize)\n4. Test affected Zaps\n\n# Prevention:\n\n1. Use service accounts for connections\n   - Don't connect with personal accounts\n   - Use shared team email\u002Faccount\n\n2. Monitor connection health\n   - Check Apps page regularly\n   - Set calendar reminders for known expiration\n\n3. Document who connected what\n   - Track in spreadsheet\n   - Handoff process when people leave\n\n4. Prefer connections that don't expire\n   - API keys over OAuth when available\n   - Long-lived tokens\n\n# Zapier Enterprise:\n- Admin controls for managing connections\n- SSO integration\n- Centralized connection management\n\n### Webhooks Missing or Duplicating Events\n\nSeverity: MEDIUM\n\nSituation: Using webhooks as triggers\n\nSymptoms:\nSome events never trigger the Zap. Same event triggers multiple\ntimes. Inconsistent automation behavior. \"Works sometimes.\"\n\nWhy this breaks:\nWebhooks are fire-and-forget. If Zapier's receiving endpoint is\nslow or unavailable, the webhook may fail. Some systems retry\nwebhooks, causing duplicates. Network issues lose events.\n\nRecommended fix:\n\n# Handle duplicates:\n\n1. Add deduplication logic:\n   - Filter: Only continue if ID not in Airtable\n   - First action: Check if already processed\n\n2. Use idempotency:\n   - Store processed IDs\n   - Skip if ID exists\n\n## Zapier example:\n[Webhook Trigger]\n   ↓\n[Airtable: Find Records] - search by event_id\n   ↓\n[Filter: Only continue if not found]\n   ↓\n[Process Event]\n   ↓\n[Airtable: Create Record] - store event_id\n\n# Handle missed events:\n\n1. Use polling triggers for critical data\n   - Less real-time but more reliable\n   - Catches events during downtime\n\n2. Implement reconciliation:\n   - Scheduled Zap to check for gaps\n   - Compare source data to processed data\n\n3. Check source system retry settings:\n   - Some systems retry on failure\n   - Configure retry count\u002Ftiming\n\n### Make Operations Consumed by Error Retries\n\nSeverity: MEDIUM\n\nSituation: Scenarios with failing modules\n\nSymptoms:\nOperations quota depleted quickly. Scenario runs \"succeeded\" but\nused many operations. Same scenario running more than expected.\n\nWhy this breaks:\nMake counts operations per module execution, including failed\nattempts and retries. Error handler modules consume operations.\nScenarios that fail and retry can use 3-5x expected operations.\n\nRecommended fix:\n\n# Understand operation counting:\n\nSuccessful run: Each module = 1 operation\nFailed + retry (3x): 3 operations for that module\nError handler: Additional operation per handler module\n\n# Reduce operation waste:\n\n1. Add error handlers that break early:\n   [Module] → Error → [Break] (1 additional op)\n   vs\n   [Module] → Error → [Log] → [Alert] → [Update] (3+ ops)\n\n2. Use ignore instead of retry when appropriate:\n   - If failure is expected (record exists)\n   - If retrying won't help (bad data)\n\n3. Pre-validate before expensive operations:\n   [Check Data] → Filter → [API Call]\n   - Fail fast before consuming operations\n\n4. Optimize scenario scheduling:\n   - Don't run every minute if hourly is enough\n   - Use webhooks for real-time when possible\n\n# Monitor usage:\n- Check Operations dashboard\n- Set up usage alerts\n- Review high-consumption scenarios\n\n### Timezone Mismatches in Scheduled Triggers\n\nSeverity: MEDIUM\n\nSituation: Setting up scheduled automations\n\nSymptoms:\nZap runs at wrong time. \"9 AM\" trigger fires at 2 PM. Different\nbehavior on different days. DST causes hour shifts.\n\nWhy this breaks:\nZapier shows times in your local timezone but may store in UTC.\nIf you change timezones or DST occurs, scheduled times shift.\nTeam members in different zones see different times.\n\nRecommended fix:\n\n# Best practices:\n\n1. Explicitly set timezone in schedule:\n   - Don't rely on browser detection\n   - Use business timezone, not personal\n\n2. Document in Zap name:\n   - \"Daily Report 9AM EST\"\n   - Include timezone in description\n\n3. Test around DST transitions:\n   - Schedule changes at DST boundaries\n   - Verify times before\u002Fafter change\n\n4. For global teams:\n   - Use UTC as standard\n   - Convert to local in descriptions\n\n5. Consider buffer times:\n   - Don't schedule at exactly midnight\n   - Avoid on-the-hour (busy periods)\n\n## Make timezone handling:\n- Scenarios use account timezone setting\n- formatDate() function respects timezone\n- Use parseDate() with explicit timezone\n\n## Collaboration\n\n### Delegation Triggers\n\n- automation requires custom code -> workflow-automation (Code-based solutions like Inngest, Temporal)\n- need browser automation in workflow -> browser-automation (Playwright\u002FPuppeteer integration)\n- building custom API integration -> api-designer (API design and implementation)\n- automation needs AI capabilities -> agent-tool-builder (AI agent tools and Zapier MCP)\n- high-volume data processing -> backend (Custom backend processing)\n- need self-hosted automation -> devops (n8n or custom workflow deployment)\n\n## Related Skills\n\nWorks well with: `workflow-automation`, `agent-tool-builder`, `backend`, `api-designer`\n\n## When to Use\n- User mentions or implies: zapier\n- User mentions or implies: make\n- User mentions or implies: integromat\n- User mentions or implies: zap\n- User mentions or implies: scenario\n- User mentions or implies: no-code automation\n- User mentions or implies: trigger action\n- User mentions or implies: workflow automation\n- User mentions or implies: connect apps\n- User mentions or implies: automate\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":7},"unknown","vibeship-spawner-skills (Apache 2.0)",1772150400000,"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fzapier-make-patterns",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill zapier-make-patterns",{"tool":42,"command":43},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill zapier-make-patterns",{"tool":45,"command":46},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill zapier-make-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]