skills_categorized/domain-utilities/zapier-workflows/SKILL.md
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
npx skillsauth add activer007/ordinary-claude-skills zapier-workflowsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Zapier MCP gives Claude access to 8,000+ individual tools (every Zapier action), but there are critical limitations:
❌ No memory - Claude doesn't remember which tools YOU use or why ❌ No context - Doesn't know when to use specific tools for your workflows ❌ Only one-off actions - Can't trigger your complex, multi-step Zaps ❌ Fresh start every session - All context lost between conversations
1. MCP Tools (One-Off Actions)
2. Multi-Step Zaps (Webhook-Triggered)
This skill solves both problems by giving Claude persistent memory for your Zapier workflows:
✅ Remembers your MCP tool preferences - "Use Google Sheets for expenses, Notion for tasks" ✅ Knows when/why to use each tool - "Search with Perplexity when researching, not Google" ✅ Triggers multi-step Zaps - "Run my daily digest" = webhook POST to your complex Zap ✅ Self-learning - Claude updates the skill as you teach it, never forgets ✅ Cross-session persistence - Works across all conversations (global install)
For Multi-Step Zaps:
For MCP Tools:
Self-Learning:
Global (~/.claude/skills/) - RECOMMENDED:
Project-level (./.claude/skills/):
IMPORTANT: This skill stores webhook URLs and workflow details in plain text files.
Webhook URLs contain authentication tokens. If someone has your webhook URL, they can trigger your Zaps.
Best practices:
~/.claude/skills/ (not in project repos).claude/ to your .gitignore if installed in a projectIf you need to share this skill:
Required:
Optional:
To connect Zapier's MCP tools to Claude Code:
Go to Zapier MCP servers:
Create a new MCP server:
Add tools:
Connect to Claude Code:
claude mcp add zapier https://mcp.zapier.com/api/mcp/mcp -t http -H "Authorization: Bearer ZjFmZGJkN..................1NjBhYzc2MDRlYg=="
Restart Claude Code:
Tip: You can add more tools later by editing your MCP server in Zapier and running the connect command again.
For pre-built, optimized workflows that you want to trigger on-demand:
In Zapier dashboard:
Build your workflow:
Document it in this skill:
references/zaps.md automaticallyWebhook vs MCP Tools:
CRITICAL: This skill can and should edit itself to learn from user feedback.
When the user teaches you something new or corrects your approach:
Identify what to update:
references/zaps.mdreferences/mcp-patterns.mdreferences/mcp-patterns.mdMake the edit using Claude Code tools:
old_string and new_string)Update format:
User: "Use Apollo instead of Clearbit for company data"
Claude: [uses Read tool on references/mcp-patterns.md]
[uses Edit tool to update the preference]
"Updated! I'll use Apollo for company enrichment from now on.
This change is now permanent in the skill."
What to capture in skill updates:
Use webhooks when:
references/zaps.md)Use MCP tools when:
CRITICAL: After you successfully help the user with MCP tools or workflows, proactively suggest saving valuable patterns.
After completing a task using MCP tools, check if this is a pattern worth saving:
Look for:
Suggest saving if:
After completing the task successfully:
"That worked well! I noticed I [describe what you did, e.g., 'used Perplexity to research, then saved results to Google Sheets'].
Would you like me to save this as a pattern? If you tell me:
- What trigger words to listen for
- When/why to use this workflow
- Any preferences or variations
I'll remember it and do this automatically next time!"
If user says yes:
references/mcp-patterns.mdExamples of patterns worth saving:
Don't save:
When user requests MCP tool functionality but Zapier MCP is not connected, tell them:
"I don't see the Zapier MCP tools connected. Here's how to set them up:
1. Go to https://mcp.zapier.com/mcp/servers
2. Login to your Zapier account
3. Click 'New MCP Server' (top left)
4. Select 'Claude Code' in the MCP Client dropdown
5. Give it a name (e.g., 'My Zapier Tools')
6. Click 'Add tools' and select the Zapier actions you want
7. Click 'Connect' and copy the command shown
8. Run that command in your terminal (it looks like):
claude mcp add zapier https://mcp.zapier.com/api/mcp/mcp -t http -H "Authorization: Bearer [your-token]"
9. Restart Claude Code
Once setup, I'll be able to use those Zapier actions directly!"
IMPORTANT: When Zapier MCP is connected (tools starting with mcp__zapier__ are available), proactively help the user document them with rich context:
List available tools:
Prompt for detailed documentation:
"I see you have these Zapier MCP tools available:
- mcp__zapier__google_sheets_create_spreadsheet_row
- mcp__zapier__perplexity_chat_completion
- [etc.]
To help me use these effectively, I need to understand:
For each tool you want me to use, please tell me:
1. WHEN should I use this tool?
- What trigger words or phrases?
- What situations or contexts?
- What types of requests?
2. WHY should I use this tool vs alternatives?
- What's it best for?
- When should I NOT use it?
3. HOW should I use it?
- Any specific parameters or preferences?
- Default values I should use?
- Sheet names, formats, or other specifics?
4. Any PATTERNS or workflows involving this tool?
- Multi-step sequences?
- Common combinations with other tools?
Take your time - the more detail you give me, the better I can serve you!"
Document in skill:
references/mcp-patterns.mdWhen to trigger this:
references/mcp-patterns.mdWhen user mentions creating or adding a multi-step Zap for webhook triggering, provide these instructions:
"To get your webhook URL from an existing Zap:
1. Go to your Zap in the Zapier dashboard
2. Make sure the trigger is a 'Webhooks by Zapier' node
3. In the 'Trigger Event' dropdown, select 'Catch Hook'
4. Go to the 'Test' tab
5. Copy the 'Webhook URL' shown
6. Give me that URL and tell me:
- What the Zap does (step-by-step)
- What trigger phrases you want to use
- Any other details (timing, cost, etc.)
I'll add it to my knowledge so you can trigger it anytime just by asking!"
references/zaps.mdreferences/mcp-patterns.mdTriggering a Zap:
User: "Run my daily digest"
Claude: [uses Read tool on references/zaps.md for webhook details]
[uses Bash tool to trigger webhook with curl POST]
"Started your Daily AI Digest. You'll get the report via email
in ~3 minutes, with SMS alerts for any high-priority items."
Using MCP orchestration:
User: "Research the latest on quantum computing"
Claude: [uses Read tool on references/mcp-patterns.md]
[calls Perplexity Search MCP tool]
[analyzes results, identifies gaps]
[calls Perplexity Search again for deeper dive]
"Here's what I found... [summary]"
Learning and updating:
User: "No, when tracking expenses use my 'Personal Budget' sheet, not 'Expenses'"
Claude: [uses Read tool on references/mcp-patterns.md]
[uses Edit tool to update the Google Sheets section]
"Got it - updated the skill. I'll use 'Personal Budget' sheet
for expense tracking from now on."
Check if MCP is connected:
mcp__zapier__ in your available toolsIf not showing up:
Pattern detection triggers when:
Try explicitly asking:
Common issues:
Test manually:
curl -X POST https://hooks.zapier.com/hooks/catch/[your-url]
Likely causes:
Fix:
references/mcp-patterns.md has your tools~/.claude/skills/ (global) vs ./.claude/skills/ (project)Signs it's working:
Quick test:
references/zaps.mdIf reference files grow too large:
Performance tips:
To start fresh:
~/.claude/skills/Yes! The skill works with:
Each mode is independent and valuable on its own.
Immediate actions:
.claude/ to .gitignorePrevention:
~/.claude/skills/).claude/ directory in projectsThis skill uses the following Claude Code tools:
tools
Generate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts verbose JSON-RPC curl commands to clean function calls (docs.createDocument() vs curl). Auto-detects MCP tools from server modules, generates TypeScript types and client methods, creates runnable example scripts. Use when: building MCP-enabled applications, need typed programmatic access to MCP tools, want Claude Code to manage apps via scripts, eliminating manual JSON-RPC curl commands, validating MCP inputs/outputs, or creating reusable agent automation.
testing
Generate structured task lists from specs or requirements. IMPORTANT: After completing ANY spec via ExitSpecMode, ALWAYS ask the user: "Would you like me to generate a task list for this spec?" Use when user confirms or explicitly requests task generation from a plan/spec/PRD.
tools
Create compelling story-format summaries using UltraThink to find the best narrative framing. Support multiple formats - 3-part narrative, n-length with inline links, abridged 5-line, or comprehensive via Foundry MCP. USE WHEN user says 'create story explanation', 'narrative summary', 'explain as a story', or wants content in Daniel's conversational first-person voice.
testing
Navigate through the original three-world shamanic technology. Deploy when soul retrieval, power animal guidance, or journey between realms emerges. Deeply respectful of Tungus, Buryat, Yakut, Evenki traditions. Use for consciousness navigation, NOT cultural appropriation.