Zapier Demo logo

Zapier Demo

Organization
zapier
zapier-demo

Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up my first action", "give me a quick demo", "I want to try it", "what's the fastest way to see this work", "minimal setup", "hello world", or "smallest example".

Overview

Publisherzapier
Repositoryzapier-mcp
Skill namezapier-demo
Stars
444
Forks
72
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zapier on GitHub. Read the source before you install it.

Installation

Install the Zapier Demo AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zapier/zapier-mcp/tree/main/plugins/zapier/skills/zapier-demo
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zapier/zapier-mcp.git /tmp/zapier-mcp
mkdir -p .claude/skills
cp -r /tmp/zapier-mcp/plugins/zapier/skills/zapier-demo .claude/skills/zapier-demo
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zapier Demo in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Zapier Demo on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Zapier Demo is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Zapier demo

Walk a new user through the smallest possible first win — one app, one read action, one prompt that actually runs. The whole flow should feel quick: a few minutes from "I'm curious" to "oh, that worked."

This is the natural next step after zapier-onboard for users who want to see Zapier work before configuring a full toolkit.

When to use vs. other skills

  • zapier-demo (this skill) — one app, one action, immediate demo. Fastest path to "oh, this works."
  • zapier-onboard — pitch + connect + diagnose. Run this first if the server isn't connected yet.
  • zapier-explore — role-tailored expansion. Run this after demo to set up a full toolkit for the user's role.
  • zapier-status — health checks and audits on an existing setup.

If the user says "show me," lean here. If they haven't connected the server yet, route to zapier-onboard first.

Step 1: Confirm the server is connected

Inspect available Zapier MCP tools. If none exist, the server isn't authenticated yet — authenticate first via mcp_auth or the client's MCP settings (same pattern as zapier-onboard's connection step). Don't continue until at least the configuration tools are available.

Once connected, set the tone:

"Let's get one Zapier action working so you can see this in action. We'll pick one app, enable one thing, and try it — should take just a couple minutes."

Step 2: Ask what app to start with

Lead with concrete popular options — most people find it easier to react to a list than to come up with one cold:

"Which app do you want to try first? A few popular ones to pick from:

  • Gmail — find or draft emails
  • Slack — find messages and ping channels
  • Google Sheets — look up rows in a sheet
  • Google Calendar — check your schedule
  • HubSpot — find contacts and deals
  • Jira — look up tickets
  • Notion — find pages

Or name something else — Zapier supports 9,000+ apps."

Confirm support and pull app details

Once the user picks, fetch the app's Zapier marketing page to confirm Zapier supports it and surface action details for Step 3:

https://zapier.com/apps/{app-slug}.md

Examples: https://zapier.com/apps/slack.md, https://zapier.com/apps/hubspot.md, https://zapier.com/apps/google-calendar.md.

Slug conventions: lowercase and hyphenated. Google Calendar → google-calendar. Microsoft Teams → microsoft-teams. HubSpot → hubspot. When uncertain, check https://zapier.com/find-apps/{letter} (the alphabetical browse) to confirm the canonical slug.

The fetched page tells you:

  • Whether Zapier supports the app — a successful fetch = yes
  • Available read/write actions and triggers — use these to recommend the right starter in Step 3
  • Popular cross-app Zaps — useful for the Step 6 "what's next" pitch

If the .md mirror 404s, try the HTML page at https://zapier.com/apps/{app-slug} as a fallback. If both 404, be honest with the user:

"I'm not finding [App] in Zapier's catalog under that name. Want to pick a different one, or check zapier.com/apps to verify the spelling?"

If they're stuck choosing:

"If nothing jumps out — Google Calendar is the easiest first one. Everyone has a calendar, and the 'what's tomorrow?' demo lands every time."

Step 3: Recommend one starter action (read-only)

Use the action list from the Step 2 marketing-page fetch to pick one read action — search/find/get/lookup. Read-only matters here: write actions need confirmation, which adds friction to a first demo. We want the simplest possible "click run, see result" loop.

Tell the user what you're recommending and why, in plain language:

"Great — for Calendar, the simplest first action is Find Events. It lets your AI look up what's on your schedule. We'll add that one and try it."

Fallback starter actions by app

If the marketing-page fetch didn't surface a clear read action, fall back to this table for the most common apps:

AppRecommended first actionWhy
Google CalendarFind EventsUniversal, easy to verify ("what's tomorrow?")
GmailFind EmailHigh-impact, every user has emails to find
SlackFind MessageMost-used in chat-heavy workflows
Google DriveFind a FileWorks for any user with Drive
Google SheetsLookup Spreadsheet RowNeeds a specific sheet but very tangible
JiraFind Issue by KeyNeeds a Jira ticket key (e.g., PROJ-123) — easy to test
LinearFind IssueSame pattern as Jira
GitHubFind Pull RequestRead-heavy use, fast demo
GitLabFind Merge RequestsSame as GitHub
NotionFind PageUseful for note-takers
HubSpotFind ContactSales-flavored, easy to test with own email
SalesforceFind RecordLike HubSpot — pick by email or name
TrelloFind CardVisible, easy to verify
AsanaFind TaskProject-management equivalent
AirtableFind RecordDatabase-flavored
Google DocsGet Document ContentPull a doc you have open

If the user names an app not on this list, default to a "Find [Thing]" pattern — almost every Zapier-supported app has a search/find action. If you're unsure of the exact name, say "the find/search action for [App]" and let them pick the right one in the configuration UI.

Step 4: Walk them through enabling it

If the server exposes a get_configuration_url tool, call it first and give the user the direct link. Otherwise, point them at mcp.zapier.com.

Then tell them what to do:

"Open [that link], find your server, and add the [App] – [Action] action. You'll also need to connect your [App] account when prompted (OAuth). Come back and say done when it's added."

Wait for confirmation. If they hit issues:

  • "It's not showing up after I added it" — they need to restart their MCP client so it re-reads the tool list (Cursor: Cmd+Shift+P → "Reload Window"; Claude Desktop: quit and reopen; Claude Code: quit and restart — /mcp shows status but won't re-fetch tools).
  • "It says I need to authenticate [App]" — that's the OAuth flow on mcp.zapier.com. Have them complete it and retry.

Once they confirm, re-inspect tools and verify the action is now available.

Step 5: Try it live

Now the moment of truth. Suggest a prompt tailored to what they enabled:

ActionSuggested prompt
Calendar: Find Events"What's on my calendar tomorrow?"
Gmail: Find Email"Find my last email from [their colleague's name or domain]"
Slack: Find Message"Find the most recent message I sent in #[a channel they're in]"
Drive: Find File"Find a file in my Drive called [something they remember]"
Sheets: Lookup Row"Look up [row identifier] in my [sheet name] sheet"
Jira: Find Issue"Look up Jira issue [PROJ-123]" (use their real ticket)
Linear: Find Issue"Find Linear issue [ENG-42]"
GitHub/GitLab: Find PR/MR"Show me the most recent PR in [repo]"
Notion: Find Page"Find my Notion page called [page title]"
HubSpot: Find Contact"Find the HubSpot contact for [their own email]"
Trello: Find Card"Find Trello cards on my [board name] board"

Frame it as:

"Now try saying to me: 'What's on my calendar tomorrow?' — I'll run that action and pull the data."

Then actually run it when they ask. Show the result cleanly: top 3–5 events with titles and times, not a wall of JSON.

If the call fails (auth issue, action not found, etc.), troubleshoot quickly without panicking the user:

"Looks like the [App] connection needs a quick re-auth — head to mcp.zapier.com and click Connect on [App], then we'll retry."

Step 6: Celebrate and offer next steps

When the action returns data, name the win:

"There you go — that's Zapier MCP working. You just asked a question in plain English and your AI pulled real data from [App]. Same pattern works for thousands of other apps and actions."

Then offer the natural next moves, one at a time — don't dump all the options:

"From here, a couple of directions:

  • Want me to set up a full toolkit for your role? → run /zapier-explore
  • Or just keep using this one and add more as you need them."

Progress checklist

Track these as you go so nothing slips:

  • Server connection verified (or freshly authenticated)
  • User picked an app from the popular list (or named their own)
  • Marketing page fetched at zapier.com/apps/{slug}.md to confirm support
  • One read action recommended with a one-line reason
  • User confirmed the action is enabled
  • Demo prompt suggested, then run live
  • Win named, next-step handoff offered

Gotchas

  • Never recommend a write action for the first demo. Read-only is the rule — write confirmations add friction at the exact moment we want a smooth "it works" experience.
  • Don't dump the full app or action tables. The 7-app list in Step 2 is the menu; the action table in Step 3 is fallback reference. The user sees one recommendation, not the buffet.
  • If a tool doesn't appear after enabling, restart the client first, not re-authentication. Cursor: Cmd+Shift+P → "Reload Window." Claude Desktop: quit and reopen. Claude Code: quit and restart (/mcp only shows status — it doesn't re-fetch tools).
  • Sheets: Lookup Row needs the spreadsheet ID upfront. It's the most-failed first demo because users don't have the ID handy. If they pick Sheets, ask them to grab a share link before adding the action.
  • Slug accuracy matters. Google Calendar → google-calendar, not googlecalendar. Get the slug right before fetching the marketing page or the lookup will 404 for the wrong reason.
  • Don't declare "Zapier doesn't support [App]" until both zapier.com/apps/{slug}.md and zapier.com/apps/{slug} HTML return 404. The .md mirror is spotty on some routes.

Tone

Friendly, low-pressure, action-oriented. This is someone's first impression — keep it light. Avoid jargon ("OAuth", "MCP server", "actions") in the user-facing copy unless they bring it up first. Say "Zapier action" instead of "MCP tool," "connect your account" instead of "authenticate the integration."

If something breaks, don't apologize at length. Just say what to do next: "Quick re-auth and we're back."

Frequently asked questions

What does the Zapier Demo AI skill do?

Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up my first action", "give me a quick demo", "I want to try it", "what's the fastest way to see this work", "minimal setup", "hello world", or "smallest example".

Why use Zapier Demo on TypingMind?

Because you install it once and use it with any model. Zapier Demo is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Zapier Demo in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zapier/zapier-mcp/tree/main/plugins/zapier/skills/zapier-demo. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Zapier Demo?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Zapier Demo?

As many as you like. As long as a model supports skills, you can use Zapier Demo with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Zapier Demo AI skill free?

Yes. It is published on GitHub by zapier under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇