Install and connect Zapier, routing to the right surface (MCP, SDK, or CLI) for what the person needs. Use when someone says "install Zapier", "add Zapier", "connect Zapier", or "set up Zapier", or when they want an AI client (Claude, ChatGPT, Cursor) to use their apps, want to call Zapier from code, or want Zapier in the terminal.
npx skills add https://github.com/zapier/gtm-cheat-codes --skill install-zapier
Use this skill when a person says "install Zapier" and may not know which Zapier surface they need. Do not make them pick a product. Ask what they want to do, then walk them through the right path one step at a time.
Ask one or two plain questions, then map the answer.
| What they want | Path | Why |
|---|---|---|
| Claude, ChatGPT, or Cursor to use their apps now | Zapier MCP | Connect tools to an AI client, no code |
| To build an app or agent in code | Zapier SDK | Call Zapier as a library: code, state, retries, schedules |
| To drive Zapier from the terminal | Zapier CLI | Standalone global install; bundles the SDK |
| Not sure | Start with Zapier MCP | Fastest path to a working agent |
The SDK and CLI are separate installs. Pick the SDK for a code project, the CLI for terminal-only work. If they want an AI client now and durable workflows later, set up MCP first, then the SDK.
These three paths are how a person installs Zapier itself. Individual app connectors are a separate thing: per-app integration skills (for example Notion) that a person installs when they need a specific app. Point them to those only after the core install, and only for the app they named. See the note at the end of INSTALL-PATHS.md.
Open INSTALL-PATHS.md and follow the section for the chosen path. Do one step at a time. Confirm each step worked before moving to the next.
Run the verify check at the end of the chosen path section before telling the person they are done. Confirm the connection works with a read-only or draft-only action first.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take zapier/install-zapier from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.