Skip to main content
skill CX Codex

segment-automation — Claude Code skill: Segment and setup

The segment-automation skill connects an agent to Segment through Rube MCP for events, user profiles, groups, page views, and batch requests.

MIT 123 installs ★ 3,785 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add davepoon/buildwithclaude --skill segment-automation -a claude-code
Open on GitHub

What segment-automation does

segment-automation exposes Segment operations through the Composio toolkit available over Rube MCP. It can send tracking events, update user traits, link users with organizations, record page views, join identities with aliases, and submit several messages through SEGMENT_BATCH.

The workflow starts by searching for current tool schemas with RUBE_SEARCH_TOOLS. Then the agent uses RUBE_MANAGE_CONNECTIONS with the segment toolkit and waits for an ACTIVE connection. Add Rube MCP at https://rube.app/mcp; the setup described here does not require an API key.

Tracking calls need either userId or anonymousId; group calls also require groupId. Segment processes calls asynchronously, so an accepted response does not confirm delivery. An active Segment connection is required before these workflows can run.

What it helps with

  • send a tracked event with custom properties
  • associate an anonymous ID with a user profile
  • batch events and identity updates in one request
  • connect a user to an organization
  • record a server-side page view

Example prompts for the agent

  • Send a completed-order event to Segment for userId and include the order properties.
  • Put these event and identity messages into an array, then submit them with SEGMENT_BATCH.
  • Link anonymousId to the new userId, set the user traits, and associate the user with groupId.

How to install segment-automation

1Skills CLI (Vercel)

npx skills add davepoon/buildwithclaude --skill segment-automation -a claude-code

2Manually: put the files in place

~/.claude/skills/segment-automation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/segment-automation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about segment-automation

How do I install segment-automation in Claude Code?

Run npx skills add davepoon/buildwithclaude --skill segment-automation -a claude-code. The installed skill is then available at ~/.claude/skills/segment-automation/SKILL.md.

What does segment-automation do?

It runs Segment operations through Rube MCP, including event tracking, user traits, groups, page views, aliases, and batch requests.

What does segment-automation require?

Rube MCP must expose RUBE_SEARCH_TOOLS, and Segment must have an active connection created through RUBE_MANAGE_CONNECTIONS. Current tool schemas should be searched before a workflow runs.

Source text

SKILL.md · MIT
---
name: segment-automation
description: "Automate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch operations. Always search tools first for current schemas."
requires:
  mcp: [rube]
category: analytics
---

# Segment Automation via Rube MCP

Automate Segment customer data platform operations through Composio's Segment toolkit via Rube MCP.

**Toolkit docs**: [composio.dev/toolkits/segment](https://composio.dev/toolkits/segment)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Segment connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `segment`
- 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 `segment`
3. If connection is not ACTIVE, follow the returned auth link to complete Segment authentication
4. Confirm connection status shows ACTIVE before running any workflows

## Core Workflows

### 1. Track Events

**When to use**: User wants to send event data to Segment for downstream destinations

**Tool sequence**:
1. `SEGMENT_TRACK` - Send a single track event [Required]

**Key parameters**:
- `userId`: User identifier (required if no `anonymousId`)
- `anonymousId`: Anonymous identifier (required if no `userId`)
- `event`: Event name (e.g., 'Order Completed', 'Button Clicked')
- `properties`: Object with event-specific properties
- `timestamp`: ISO 8601 timestamp (optional; defaults to server time)
- `context`: Object with contextual metadata (IP, user agent, etc.)

**Pitfalls**:
- At least one of `userId` or `anonymousId` is required
- `event` name is required and should follow consistent naming conventions
- Properties are freeform objects; ensure consistent schema across events
- Timestamp must be ISO 8601 format (e.g., '2024-01-15T10:30:00Z')
- Events are processed asynchronously; successful API response means accepted, not delivered

### 2. Identify Users

**When to use**: User wants to associate traits with a user profile in Segment

**Tool sequence**:
1. `SEGMENT_IDENTIFY` - Set user traits and identity [Required]

**Key parameters**:
- `userId`: User identifier (required if no `anonymousId`)
- `anonymousId`: Anonymous identifier
- `traits`: Object with user properties (email, name, plan, etc.)
- `timestamp`: ISO 8601 timestamp
- `context`: Contextual metadata

**Pitfalls**:
- At least one of `userId` or `anonymousId` is required
- Traits are merged with existing traits, not replaced
- To remove a trait, set it to `null`
- Identify calls should be made before track calls for new users
- Avoid sending PII in traits unless destinations are configured for it

### 3. Batch Operations

**When to use**: User wants to send multiple events, identifies, or other calls in a single request

**Tool sequence**:
1. `SEGMENT_BATCH` - Send multiple Segment calls in one request [Required]

**Key parameters**:
- `batch`: Array of message objects, each with:
  - `type`: Message type ('track', 'identify', 'group', 'page', 'alias')
  - `userId` / `anonymousId`: User identifier
  - Additional fields based on type (event, properties, traits, etc.)

**Pitfalls**:
- Each message in the batch must have a valid `type` field
- Maximum batch size limit applies; check schema for current limit
- All messages in a batch are processed independently; one failure does not affect others
- Each message must independently satisfy its type's requirements (e.g., track needs event name)
- Batch is the most efficient way to send multiple calls; prefer over individual calls

### 4. Group Users

**When to use**: User wants to associate a user with a company, team, or organization

**Tool sequence**:
1. `SEGMENT_GROUP` - Associate user with a group [Required]

**Key parameters**:
- `userId`: User identifier (required if no `anonymousId`)
- `anonymousId`: Anonymous identifier
- `groupId`: Group/organization identifier (required)
- `traits`: Object with group properties (name, industry, size, plan)
- `timestamp`: ISO 8601 timestamp

**Pitfalls**:
- `groupId` is required; it identifies the company or organization
- Group traits are merged with existing traits for that group
- A user can belong to multiple groups
- Group traits update the group profile, not the user profile

### 5. Track Page Views

**When to use**: User wants to record page view events in Segment

**Tool sequence**:
1. `SEGMENT_PAGE` - Send a page view event [Required]

**Key parameters**:
- `userId`: User identifier (required if no `anonymousId`)
- `anonymousId`: Anonymous identifier
- `name`: Page name (e.g., 'Home', 'Pricing', 'Dashboard')
- `category`: Page category (e.g., 'Docs', 'Marketing')
- `properties`: Object with page-specific properties (url, title, referrer)

**Pitfalls**:
- At least one of `userId` or `anonymousId` is required
- `name` and `category` are optional but recommended for proper analytics
- Standard properties include `url`, `title`, `referrer`, `path`, `search`
- Page calls are often automated; manual use is for server-side page tracking

### 6. Alias Users and Manage Sources

**When to use**: User wants to merge anonymous and identified users, or manage source configuration

**Tool sequence**:
1. `SEGMENT_ALIAS` - Link two user identities together [Optional]
2. `SEGMENT_LIST_SCHEMA_SETTINGS_IN_SOURCE` - View source schema settings [Optional]
3. `SEGMENT_UPDATE_SOURCE` - Update source configuration [Optional]

**Key parameters**:
- For ALIAS:
  - `userId`: New user identifier (the identified ID)
  - `previousId`: Old user identifier (the anonymous ID)
- For source operations:
  - `sourceId`: Source identifier

**Pitfalls**:
- ALIAS is a one-way operation; cannot be undone
- `previousId` is the anonymous/old ID, `userId` is the new/identified ID
- Not all destinations support alias calls; check destination documentation
- ALIAS should be called once when a user first identifies (e.g., signs up)
- Source updates may affect data collection; review changes carefully

## Common Patterns

### User Lifecycle

Standard Segment user lifecycle:
```
1. Anonymous user visits -> PAGE call with anonymousId
2. User interacts -> TRACK call with anonymousId
3. User signs up -> ALIAS (anonymousId -> userId), then IDENTIFY with traits
4. User takes action -> TRACK call with userId
5. User joins org -> GROUP call linking userId to groupId
```

### Batch Optimization

For bulk data ingestion:
```
1. Collect events in memory (array of message objects)
2. Each message includes type, userId/anonymousId, and type-specific fields
3. Call SEGMENT_BATCH with the collected messages
4. Check response for any individual message errors
```

### Naming Conventions

Segment recommends consistent event naming:
- **Events**: Use "Object Action" format (e.g., 'Order Completed', 'Article Viewed')
- **Properties**: Use snake_case (e.g., 'order_total', 'product_name')
- **Traits**: Use snake_case (e.g., 'first_name', 'plan_type')

## Known Pitfalls

**Identity Resolution**:
- Always include `userId` or `anonymousId` on every call
- Use ALIAS only once per user identity merge
- Identify before tracking to ensure proper user association

**Data Quality**:
- Event names should be consistent across all sources
- Properties should follow a defined schema for downstream compatibility
- Avoid sending sensitive PII unless destinations are configured for it

**Rate Limits**:
- Use BATCH for bulk operations to stay within rate limits
- Individual calls are rate-limited per source
- Batch calls are more efficient and less likely to be throttled

**Response Parsing**:
- Successful responses indicate acceptance, not delivery to destinations
- Response data may be nested under `data` key
- Check for error fields in batch responses for individual message failures

**Timestamps**:
- Must be ISO 8601 format with timezone (e.g., '2024-01-15T10:30:00Z')
- Omitting timestamp uses server receive time
- Historical data imports should include explicit timestamps

## Quick Reference

| Task | Tool Slug | Key Params |
|------|-----------|------------|
| Track event | SEGMENT_TRACK | userId, event, properties |
| Identify user | SEGMENT_IDENTIFY | userId, traits |
| Batch calls | SEGMENT_BATCH | batch (array of messages) |
| Group user | SEGMENT_GROUP | userId, groupId, traits |
| Page view | SEGMENT_PAGE | userId, name, properties |
| Alias identity | SEGMENT_ALIAS | userId, previousId |
| Source schema | SEGMENT_LIST_SCHEMA_SETTINGS_IN_SOURCE | sourceId |
| Update source | SEGMENT_UPDATE_SOURCE | sourceId |
| Warehouses | SEGMENT_LIST_CONNECTED_WAREHOUSES_FROM_SOURCE | sourceId |

---
*Powered by [Composio](https://composio.dev)*

© davepoon · MIT · davepoon/buildwithclaude

Similar skills

All skills for Automation and no-code: n8n, Zapier, Make →

From the same set235

The whole set →
datadog-automation datadog-automation automates Datadog tasks: query metrics, search logs, manage monitors and dashboards, create events and downtimes. Requires connected Rube MCP and active Datadog authentication. CX Codex +1 124installs helpdesk-automation helpdesk-automation reads HelpDesk tickets, agent views, and canned replies through Rube MCP and Composio. Built for support agents managing ticket backlogs. CX Codex +1 124installs sentry-automation sentry-automation is a Claude Code skill for managing Sentry errors, alerts, and releases via Rube MCP. Search issues, inspect events, and track deployments from your IDE. CX Codex +1 123installs cal-com-automation cal-com-automation automates Cal.com scheduling, availability lookups, and webhooks via Rube MCP. Useful when an agent needs to manage booking slots or team calendars directly. CX Codex +1 123installs convertkit-automation convertkit-automation automates ConvertKit (Kit) workflows via Rube MCP: search and filter subscribers, assign tags, view broadcasts, and pull campaign stats. Requires Rube MCP and an active Kit connection. CX Codex +1 123installs miro-automation miro-automation automates Miro boards through Rube MCP, creating sticky notes, frames, and connectors or managing team sharing. CX Codex +1 123installs vercel-automation vercel-automation is a Claude Code skill that manages Vercel projects through Rube MCP, including deployments, settings, environment variables, domains, and DNS. CX Codex +1 123installs close-automation close-automation automates Close CRM operations through Rube MCP, managing leads, call logging, SMS, tasks, and notes directly from your coding agent. CX Codex +1 122installs

Project sponsors

Companies that keep this analytics open