agentleFS
Sign inStart free
windsor-aiwindsor-ai/claude-windsor-ai-plugin/skills/klaviyo/SKILL.md

klaviyo

Skill1 starsChanged 51 days agoMITView on GitHub

Analyze Klaviyo email and SMS performance and manage flows through Windsor.ai. Use when the user asks about their Klaviyo campaigns, flows, lists, or metrics — opens, clicks, conversions, revenue, unsubscribes — or wants to create a flow or change a flow's status (draft / manual / live). Do not use for other email platforms (Mailchimp, Brevo, …), ad campaigns, or writing email copy.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call get_connectors to see connected Klaviyo accounts.

    line 23
  2. Distinctive:

    Use the exact ids returned.

    line 31
  3. Very specific:

    Call list_actions first for exact ids/schemas.

    line 39
  4. Very specific:

    Write workflow — every time: build the params from the list_actions schema,

    line 48

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Klaviyo via Windsor.ai

Windsor.ai exposes live Klaviyo data (read) and flow management (write) through MCP tools. The connector id is klaviyo. Pass klaviyo as the connector on every tool call; the Windsor.ai server serves all connectors, so it is never implied.

Golden rules:

  • Never guess field, account, action, or option names — get them from get_fields, get_connectors, list_actions, and get_options. Call those first.
  • Reads are safe; setting a flow live starts sending real messages. Only call execute_action after the user confirms the specific change.
  • Report what the user asked for, concisely.

1. Ground yourself first

Call get_connectors to see connected Klaviyo accounts. If none is connected, help the user connect: get_connector_authorization_url (or get_connector_connect_info) and give them the setup link.

2. Reading performance

  1. get_fields for klaviyo — campaign, flow, list, and metric fields (opens, clicks, conversions, revenue, unsubscribes, added-to-cart, subject, status). Use the exact ids returned.
  2. get_data with the fields, target account(s), and a date range (date_from/date_to or a date_preset). Add filters as needed. Recipes: revenue by campaign/flow; open & click rates over time; top flows by conversions.

3. Managing flows (write actions)

Call list_actions first for exact ids/schemas. Klaviyo exposes:

  • create_flow — create a flow from a trigger (metric event or list-add) plus a graph of steps (time-delay, send-email referencing an existing template, send-sms with inline body, conditional-split). Created in draft, so nothing sends until activated. Klaviyo rate-limits flow creation (~100/day).
  • update_flow_status — set a flow to draft (off), manual (profiles enter, messages held for review), or live (sends automatically).

Write workflow — every time: build the params from the list_actions schema, show the user the concrete change and confirm (especially setting a flow live, which begins sending to subscribers), then call execute_action and report the result.

4. Reference real data, don't fabricate

On an error, call the relevant discovery tool and retry with correct ids, or report the specific error. Never invent open rates, revenue, flow ids, or names.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free