Klaviyo Automation logo

Klaviyo Automation

CommunityPopular
davepoon
klaviyo-automation

Automate Klaviyo tasks via Rube MCP (Composio): manage email/SMS campaigns, inspect campaign messages, track tags, and monitor send jobs. Always search tools first for current schemas.

Overview

Publisherdavepoon
Repositorybuildwithclaude
Skill nameklaviyo-automation
Stars
3.6K
Forks
586
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 davepoon on GitHub. Read the source before you install it.

Installation

Install the Klaviyo Automation 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/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/klaviyo-automation
  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/davepoon/buildwithclaude.git /tmp/buildwithclaude
mkdir -p .claude/skills
cp -r /tmp/buildwithclaude/plugins/all-skills/skills/klaviyo-automation .claude/skills/klaviyo-automation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Klaviyo Automation 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 Klaviyo Automation 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 Klaviyo Automation 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.

Klaviyo Automation via Rube MCP

Automate Klaviyo email and SMS marketing operations through Composio's Klaviyo toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/klaviyo

Prerequisites

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Klaviyo connection via RUBE_MANAGE_CONNECTIONS with toolkit klaviyo
  • Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

  1. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
  2. Call RUBE_MANAGE_CONNECTIONS with toolkit klaviyo
  3. If connection is not ACTIVE, follow the returned auth link to complete Klaviyo authentication
  4. Confirm connection status shows ACTIVE before running any workflows

Core Workflows

1. List and Filter Campaigns

When to use: User wants to browse, search, or filter marketing campaigns

Tool sequence:

  1. KLAVIYO_GET_CAMPAIGNS - List campaigns with channel and status filters [Required]

Key parameters:

  • channel: Campaign channel - 'email' or 'sms' (required by Klaviyo API)
  • filter: Additional filter string (e.g., equals(status,"draft"))
  • sort: Sort field with optional - prefix for descending (e.g., '-created_at', 'name')
  • page_cursor: Pagination cursor for next page
  • include_archived: Include archived campaigns (default: false)

Pitfalls:

  • channel is required; omitting it can produce incomplete or unexpected results
  • Pagination is mandatory for full coverage; a single call returns only one page (default ~10)
  • Follow page_cursor until exhausted to get all campaigns
  • Status filtering via filter (e.g., equals(status,"draft")) can return mixed statuses; always validate data[].attributes.status client-side
  • Status strings are case-sensitive and can be compound (e.g., 'Cancelled: No Recipients')
  • Response shape is nested: response.data.data with status at data[].attributes.status

2. Get Campaign Details

When to use: User wants detailed information about a specific campaign

Tool sequence:

  1. KLAVIYO_GET_CAMPAIGNS - Find campaign to get its ID [Prerequisite]
  2. KLAVIYO_GET_CAMPAIGN - Retrieve full campaign details [Required]

Key parameters:

  • campaign_id: Campaign ID string (e.g., '01GDDKASAP8TKDDA2GRZDSVP4H')
  • include_messages: Include campaign messages in response
  • include_tags: Include tags in response

Pitfalls:

  • Campaign IDs are alphanumeric strings, not numeric
  • include_messages and include_tags add related data to the response via Klaviyo's include mechanism
  • Campaign details include audiences, send strategy, tracking options, and scheduling info

3. Inspect Campaign Messages

When to use: User wants to view the email/SMS content of a campaign

Tool sequence:

  1. KLAVIYO_GET_CAMPAIGN - Find campaign and its message IDs [Prerequisite]
  2. KLAVIYO_GET_CAMPAIGN_MESSAGE - Get message content details [Required]

Key parameters:

  • id: Message ID string
  • fields__campaign__message: Sparse fieldset for message attributes (e.g., 'content.subject', 'content.from_email', 'content.body')
  • fields__campaign: Sparse fieldset for campaign attributes
  • fields__template: Sparse fieldset for template attributes
  • include: Related resources to include ('campaign', 'template')

Pitfalls:

  • Message IDs are separate from campaign IDs; extract from campaign response
  • Sparse fieldset syntax uses dot notation for nested fields: 'content.subject', 'content.from_email'
  • Email messages have content fields: subject, preview_text, from_email, from_label, reply_to_email
  • SMS messages have content fields: body
  • Including 'template' provides the HTML/text content of the email

4. Manage Campaign Tags

When to use: User wants to view tags associated with campaigns for organization

Tool sequence:

  1. KLAVIYO_GET_CAMPAIGN_RELATIONSHIPS_TAGS - Get tag IDs for a campaign [Required]

Key parameters:

  • id: Campaign ID string

Pitfalls:

  • Returns only tag IDs, not tag names/details
  • Tag IDs can be used with Klaviyo's tag endpoints for full details
  • Rate limit: 3/s burst, 60/m steady (stricter than other endpoints)

5. Monitor Campaign Send Jobs

When to use: User wants to check the status of a campaign send operation

Tool sequence:

  1. KLAVIYO_GET_CAMPAIGN_SEND_JOB - Check send job status [Required]

Key parameters:

  • id: Send job ID

Pitfalls:

  • Send job IDs are returned when a campaign send is initiated
  • Job statuses indicate whether the send is queued, in progress, complete, or failed
  • Rate limit: 10/s burst, 150/m steady

Common Patterns

Campaign Discovery Pattern

1. Call KLAVIYO_GET_CAMPAIGNS with channel='email'
2. Paginate through all results via page_cursor
3. Filter by status client-side for accuracy
4. Extract campaign IDs for detailed inspection

Sparse Fieldset Pattern

Klaviyo supports sparse fieldsets to reduce response size:

fields__campaign__message=['content.subject', 'content.from_email', 'send_times']
fields__campaign=['name', 'status', 'send_time']
fields__template=['name', 'html', 'text']

Pagination

  • Klaviyo uses cursor-based pagination
  • Check response for page_cursor in the pagination metadata
  • Pass cursor as page_cursor in next request
  • Default page size is ~10 campaigns
  • Continue until no more cursor is returned

Filter Syntax

- equals(status,"draft") - Campaigns in draft status
- equals(name,"Newsletter") - Campaign named "Newsletter"
- greater-than(created_at,"2024-01-01T00:00:00Z") - Created after date

Known Pitfalls

API Version:

  • Klaviyo API uses versioned endpoints (e.g., v2024-07-15)
  • Response schemas may change between API versions
  • Tool responses follow the version configured in the Composio integration

Response Nesting:

  • Data is nested: response.data.data[].attributes
  • Campaign status at data[].attributes.status
  • Mis-parsing the nesting yields empty or incorrect results
  • Always navigate through the full path defensively

Rate Limits:

  • Burst: 10/s (3/s for tag endpoints)
  • Steady: 150/m (60/m for tag endpoints)
  • Required scope: campaigns:read
  • Implement backoff on 429 responses

Status Values:

  • Status strings are case-sensitive
  • Compound statuses exist (e.g., 'Cancelled: No Recipients')
  • Server-side filtering may return mixed statuses; always validate client-side

Quick Reference

TaskTool SlugKey Params
List campaignsKLAVIYO_GET_CAMPAIGNSchannel, filter, sort, page_cursor
Get campaign detailsKLAVIYO_GET_CAMPAIGNcampaign_id, include_messages, include_tags
Get campaign messageKLAVIYO_GET_CAMPAIGN_MESSAGEid, fields__campaign__message
Get campaign tagsKLAVIYO_GET_CAMPAIGN_RELATIONSHIPS_TAGSid
Get send job statusKLAVIYO_GET_CAMPAIGN_SEND_JOBid

Powered by Composio

Frequently asked questions

What does the Klaviyo Automation AI skill do?

Automate Klaviyo tasks via Rube MCP (Composio): manage email/SMS campaigns, inspect campaign messages, track tags, and monitor send jobs. Always search tools first for current schemas.

Why use Klaviyo Automation on TypingMind?

Because you install it once and use it with any model. Klaviyo Automation 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 Klaviyo Automation in TypingMind?

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

Which AI models can use Klaviyo Automation?

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 Klaviyo Automation?

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

Is the Klaviyo Automation AI skill free?

Yes. It is published on GitHub by davepoon 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 👇