zapier-setup
Set up Zapier MCP and add tools to your AI assistant. Introduces what Zapier can do, walks through authentication, detects your server mode, then branches into the right flow — summary for healthy setups, reconnect for broken auth, onboarding for fresh installs, or config help when the server is missing. Use when getting started, troubleshooting connection issues, adding new tools, or when the user asks "what can I do now", "what can I do with Zapier", "show me how the Zapier plugin works", "what is Zapier MCP", "how does Zapier work", or "tell me about Zapier".
What this skill does
# Zapier setup
Introduce Zapier MCP, get the user authenticated, detect their server mode, then guide them through the appropriate setup flow.
## Step 1: Introduction
Start by describing what Zapier MCP can do for the user, then get them authenticated.
### Pitch
"Zapier MCP connects your AI assistant to 9,000+ apps — Slack, Gmail, Google Calendar, Jira, Notion, HubSpot, and thousands more. Once set up, you can search across your tools, take actions, and automate workflows, all through natural conversation. It's personalized to your workflow — you pick the apps and actions that matter to you, and your AI learns to use them."
### Check connection
Check if any Zapier MCP tools are available:
- **Tools are available** (either Agentic meta-tools or Classic action tools): The user is already authenticated. Give a shorter version of the pitch — "You've got Zapier MCP installed and connected. Let me check what you have set up." — then proceed to Step 2.
- **No Zapier tools available at all**: The server is installed but needs authentication. First, attempt to authenticate directly in the chat by calling `mcp_auth` on the Zapier MCP server. If that succeeds, re-check available tools and proceed to Step 2.
If `mcp_auth` fails or is unavailable, fall back to manual instructions based on their client:
- **In Cursor:** "Let's get you connected. Go to **Settings > Cursor Settings > Tools & MCP** and click **Connect** next to the Zapier MCP server. You can also press **Cmd+Shift+P** and search for 'MCP' to get there quickly."
- **In Claude Desktop:** "Let's get you connected. Go to **Customize > Connectors > Zapier** and click **Connect**."
- **In other clients:** "Let's get you connected. Find the Zapier MCP server in your client's MCP settings and click Connect. This will redirect you to mcp.zapier.com to sign in."
Detect which client is in use from the environment or conversation context. If unclear, give the generic instructions.
Wait for the user to confirm ("done"), then re-check available tools and proceed to Step 2.
## Step 2: Detect mode
Check which tools are available to determine the server mode:
- **Agentic mode**: `list_enabled_zapier_actions` is available as a tool. Call `get_zapier_skill` with name `"zapier-mcp-onboarding"` on the Zapier MCP server and follow its instructions. If authentication is needed, help the user through it, then retry the call. **Do not continue with the steps below** — the Zapier-hosted onboarding skill handles the entire Agentic setup flow.
- **Classic mode**: `get_configuration_url` and/or individual `app_action_name` tools are present, but `list_enabled_zapier_actions` is not. Continue to Step 3.
## Step 3: Diagnose
This step applies only to **Classic mode**.
Try calling `get_configuration_url` or any Zapier tool. The result determines which branch to follow:
| Result | Branch |
| ------------------------------------------------------------- | ------------------- |
| Zapier action tools are available (e.g., `gmail_send_email`) | **Healthy** |
| Only `get_configuration_url` is available (no action tools) | **Fresh install** |
| Fails with auth/401 error | **Auth broken** |
| No Zapier tools available at all (server not connected) | **Not connected** |
## Branch: Healthy
The server is connected and has action tools configured. Show a summary and offer next steps.
1. Look at the available Zapier MCP tools. Each action tool follows the naming pattern `app_action_name` (e.g., `slack_send_channel_message`, `gmail_find_email`). Identify the app from the tool description (e.g., "Send a **Slack** channel message" → Slack).
2. Group tools by app and show a clean summary:
"Your Zapier MCP is connected with [N] tools across [app list]:
- **Slack**: `slack_send_channel_message`, `slack_find_message`, `slack_get_message`
- **Gmail**: `gmail_find_email`, `gmail_send_email`
- **Google Calendar**: `google_calendar_find_events`, `google_calendar_create_event`
Everything's working. What would you like to do?"
3. Offer options:
- "Add more tools" → call `get_configuration_url` and direct the user there
- "Run a health check" → trigger the **zapier-status** skill
- "Create my tools profile" → trigger the **create-my-tools-profile** skill
- Or just start using the tools
## Branch: Auth broken
The server exists in the config but authentication has expired or is invalid.
1. Tell the user:
"Your Zapier MCP server is configured but the connection is broken (authentication expired).
**[Click here to reconnect](https://mcp.zapier.com)**
Sign in, find your server, and re-authenticate. Come back and say **done** when you're finished."
2. Wait for the user to confirm.
3. Try calling a Zapier tool again to verify.
4. If it works: show the Healthy summary.
5. If it still fails: suggest deleting and recreating the server config. Offer to help update the MCP config file with a fresh token (see "MCP config by client" below).
## Branch: Not connected
The Zapier MCP server is installed via the plugin but hasn't been authenticated yet. This is the most common state on a fresh install — zero Zapier tools are visible because the server hasn't been connected.
1. Tell the user the Zapier plugin is installed but needs to be connected first.
2. Attempt to authenticate directly in the chat by calling `mcp_auth` on the Zapier MCP server. If that succeeds, skip to step 5.
3. If `mcp_auth` fails or is unavailable, fall back to manual instructions based on their client:
- **In Cursor:** "Go to **Settings > Cursor Settings > Tools & MCP** and click **Connect** next to the Zapier MCP server. You can also press **Cmd+Shift+P** and search for 'MCP' to get there quickly."
- **In Claude Desktop:** "Go to **Customize > Connectors > Zapier** and click **Connect**."
- **In other clients:** "Find the Zapier MCP server in your client's MCP settings and connect it. This will redirect you to mcp.zapier.com to sign in."
Detect which client is in use from the environment or conversation context. If unclear, give the generic instructions.
4. Wait for the user to confirm ("done").
5. Re-diagnose by checking available Zapier MCP tools. Proceed to the appropriate branch — most likely **Fresh install** (server connected, no action tools yet).
## Branch: Fresh install
The server is connected but has no action tools. The user needs to add actions through the web UI.
### Step 1: Workflow-first discovery
Don't ask "what apps do you use?" Start with what they're trying to accomplish.
"You're connected but don't have any tools set up yet. Let's add some."
Call `get_configuration_url` and share the returned URL so the user can go directly to their server's tool config page.
Then help them pick what to add based on their workflow:
**Starter kits by workflow:**
| Workflow | Apps | Why these |
| ------------------------ | ------------------------------------------------------------- | ------------------------------------------------------ |
| **Dev workflow** | Jira + GitLab + Slack + Google Docs | Issue tracking, code review, team comms, documentation |
| **PM workflow** | Jira + Slack + Google Docs + Google Calendar + Notion | Planning, updates, writing, scheduling, knowledge base |
| **Sales workflow** | HubSpot + Gmail + Google Calendar + Slack | CRM, outreach, scheduling, team updates |
| **Marketing workflow** | Google Sheets + Slack + Notion + Gmail | Data, coordination, content, campaigns |
| **General productivity** | Gmail + Google Calendar + Slack + Google Docs + Google Sheets | The essentials for anyone Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.