Skip to main content
skill CX Codex

posthog-automation — Claude Code skill for PostHog via Rube MCP

posthog-automation — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode that drives PostHog through Rube MCP (Composio). Covers event capture, feature flags, projects and user profiles.

MIT 121 installs ★ 3,785 updated 2026-10-25

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

What posthog-automation does

The skill routes PostHog work through the Rube MCP server: the agent calls RUBE_SEARCH_TOOLS first, then uses POSTHOG_* tools with live schemas instead of hardcoded ones.

Core operations include sending events via POSTHOG_CAPTURE_EVENT (every call requires distinct_id), querying events by date range or person, and creating feature flags with group-based targeting. Flag filters support multiple groups with rollout_percentage per group; changes propagate in seconds. PostHog system events carry a $ prefix — custom events must not, or the API will reject them.

Rube MCP must be reachable before the skill does anything: add https://rube.app/mcp as an MCP server in your client config, then call RUBE_MANAGE_CONNECTIONS with toolkit posthog and follow the returned auth link. No separate API keys required.

What it helps with

  • send a custom analytics event with specific properties to PostHog
  • create a feature flag targeting users by email domain with a rollout percentage
  • list all projects in an organization and extract their numeric IDs
  • filter a specific user's events within a given time window
  • verify API connectivity and check the current user's permission scope

Example prompts for the agent

  • Send a purchase_completed event to PostHog with the user's distinct_id and order total
  • Create a feature flag new-dashboard-beta and roll it out to 10% of users
  • Show all events for person_id from the last 24 hours

How to install posthog-automation

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

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

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

Questions about posthog-automation

How do I install posthog-automation in Claude Code?

Run npx skills add davepoon/buildwithclaude --skill posthog-automation -a claude-code. The skill file lands at ~/.claude/skills/posthog-automation/SKILL.md.

What does the posthog-automation skill do?

It gives the agent a structured set of instructions for PostHog via Rube MCP: capturing and filtering events, managing feature flags, listing projects and reading user profiles.

Does posthog-automation need a PostHog API key?

No separate key is needed. Add https://rube.app/mcp as an MCP server, then connect the posthog toolkit through RUBE_MANAGE_CONNECTIONS and complete the OAuth flow it returns.

Source text

SKILL.md · MIT
---
name: posthog-automation
description: "Automate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations. Always search tools first for current schemas."
requires:
  mcp: [rube]
category: devops
---

# PostHog Automation via Rube MCP

Automate PostHog product analytics and feature flag management through Composio's PostHog toolkit via Rube MCP.

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

## Prerequisites

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

## Core Workflows

### 1. Capture Events

**When to use**: User wants to send event data to PostHog for analytics tracking

**Tool sequence**:
1. `POSTHOG_CAPTURE_EVENT` - Send one or more events to PostHog [Required]

**Key parameters**:
- `event`: Event name (e.g., '$pageview', 'user_signed_up', 'purchase_completed')
- `distinct_id`: Unique user identifier (required)
- `properties`: Object with event-specific properties
- `timestamp`: ISO 8601 timestamp (optional; defaults to server time)

**Pitfalls**:
- `distinct_id` is required for every event; identifies the user/device
- PostHog system events use `$` prefix (e.g., '$pageview', '$identify')
- Custom events should NOT use the `$` prefix
- Properties are freeform; maintain consistent schemas across events
- Events are processed asynchronously; ingestion delay is typically seconds

### 2. List and Filter Events

**When to use**: User wants to browse or search through captured events

**Tool sequence**:
1. `POSTHOG_LIST_AND_FILTER_PROJECT_EVENTS` - Query events with filters [Required]

**Key parameters**:
- `project_id`: PostHog project ID (required)
- `event`: Filter by event name
- `person_id`: Filter by person ID
- `after`: Events after this ISO 8601 timestamp
- `before`: Events before this ISO 8601 timestamp
- `limit`: Maximum events to return
- `offset`: Pagination offset

**Pitfalls**:
- `project_id` is required; resolve via LIST_PROJECTS first
- Date filters use ISO 8601 format (e.g., '2024-01-15T00:00:00Z')
- Large event volumes require pagination; use `offset` and `limit`
- Results are returned in reverse chronological order by default
- Event properties are nested; parse carefully

### 3. Manage Feature Flags

**When to use**: User wants to create, view, or manage feature flags

**Tool sequence**:
1. `POSTHOG_LIST_AND_MANAGE_PROJECT_FEATURE_FLAGS` - List existing feature flags [Required]
2. `POSTHOG_RETRIEVE_FEATURE_FLAG_DETAILS` - Get detailed flag configuration [Optional]
3. `POSTHOG_CREATE_FEATURE_FLAGS_FOR_PROJECT` - Create a new feature flag [Optional]

**Key parameters**:
- For listing: `project_id` (required)
- For details: `project_id`, `id` (feature flag ID)
- For creation:
  - `project_id`: Target project
  - `key`: Flag key (e.g., 'new-dashboard-beta')
  - `name`: Human-readable name
  - `filters`: Targeting rules and rollout percentage
  - `active`: Whether the flag is enabled

**Pitfalls**:
- Feature flag `key` must be unique within a project
- Flag keys should use kebab-case (e.g., 'my-feature-flag')
- `filters` define targeting groups with properties and rollout percentages
- Creating a flag with `active: true` immediately enables it for matching users
- Flag changes take effect within seconds due to PostHog's polling mechanism

### 4. Manage Projects

**When to use**: User wants to list or inspect PostHog projects and organizations

**Tool sequence**:
1. `POSTHOG_LIST_PROJECTS_IN_ORGANIZATION_WITH_PAGINATION` - List all projects [Required]

**Key parameters**:
- `organization_id`: Organization identifier (may be optional depending on auth)
- `limit`: Number of results per page
- `offset`: Pagination offset

**Pitfalls**:
- Project IDs are numeric; used as parameters in most other endpoints
- Organization ID may be required; check your PostHog setup
- Pagination is offset-based; iterate until results are empty
- Project settings include API keys and configuration details

### 5. User Profile and Authentication

**When to use**: User wants to check current user details or verify API access

**Tool sequence**:
1. `POSTHOG_WHOAMI` - Get current API user information [Optional]
2. `POSTHOG_RETRIEVE_CURRENT_USER_PROFILE` - Get detailed user profile [Optional]

**Key parameters**:
- No required parameters for either call
- Returns current authenticated user's details, permissions, and organization info

**Pitfalls**:
- WHOAMI is a lightweight check; use for verifying API connectivity
- User profile includes organization membership and permissions
- These endpoints confirm the API key's access level and scope

## Common Patterns

### ID Resolution

**Organization -> Project ID**:
```
1. Call POSTHOG_LIST_PROJECTS_IN_ORGANIZATION_WITH_PAGINATION
2. Find project by name in results
3. Extract id (numeric) for use in other endpoints
```

**Feature flag name -> Flag ID**:
```
1. Call POSTHOG_LIST_AND_MANAGE_PROJECT_FEATURE_FLAGS with project_id
2. Find flag by key or name
3. Extract id for detailed operations
```

### Feature Flag Targeting

Feature flags support sophisticated targeting:
```json
{
  "filters": {
    "groups": [
      {
        "properties": [
          {"key": "email", "value": "@company.com", "operator": "icontains"}
        ],
        "rollout_percentage": 100
      },
      {
        "properties": [],
        "rollout_percentage": 10
      }
    ]
  }
}
```
- Groups are evaluated in order; first matching group determines the rollout
- Properties filter users by their traits
- Rollout percentage determines what fraction of matching users see the flag

### Pagination

- Events: Use `offset` and `limit` (offset-based)
- Feature flags: Use `offset` and `limit` (offset-based)
- Projects: Use `offset` and `limit` (offset-based)
- Continue until results array is empty or smaller than `limit`

## Known Pitfalls

**Project IDs**:
- Required for most API endpoints
- Always resolve project names to numeric IDs first
- Multiple projects can exist in one organization

**Event Naming**:
- System events use `$` prefix ($pageview, $identify, $autocapture)
- Custom events should NOT use `$` prefix
- Event names are case-sensitive; maintain consistency

**Feature Flags**:
- Flag keys must be unique within a project
- Use kebab-case for flag keys
- Changes propagate within seconds
- Deleting a flag is permanent; consider disabling instead

**Rate Limits**:
- Event ingestion has throughput limits
- Batch events where possible for efficiency
- API endpoints have per-minute rate limits

**Response Parsing**:
- Response data may be nested under `data` or `results` key
- Paginated responses include `count`, `next`, `previous` fields
- Event properties are nested objects; access carefully
- Parse defensively with fallbacks for optional fields

## Quick Reference

| Task | Tool Slug | Key Params |
|------|-----------|------------|
| Capture event | POSTHOG_CAPTURE_EVENT | event, distinct_id, properties |
| List events | POSTHOG_LIST_AND_FILTER_PROJECT_EVENTS | project_id, event, after, before |
| List feature flags | POSTHOG_LIST_AND_MANAGE_PROJECT_FEATURE_FLAGS | project_id |
| Get flag details | POSTHOG_RETRIEVE_FEATURE_FLAG_DETAILS | project_id, id |
| Create flag | POSTHOG_CREATE_FEATURE_FLAGS_FOR_PROJECT | project_id, key, filters |
| List projects | POSTHOG_LIST_PROJECTS_IN_ORGANIZATION_WITH_PAGINATION | organization_id |
| Who am I | POSTHOG_WHOAMI | (none) |
| User profile | POSTHOG_RETRIEVE_CURRENT_USER_PROFILE | (none) |

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

© davepoon · MIT · davepoon/buildwithclaude

Similar skills

All skills for DevOps and infrastructure →

From the same set235

The whole set →
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 circleci-automation circleci-automation is a Claude Code skill for CircleCI via Rube MCP: trigger pipelines, check workflow and job status, and download artifacts and test results. Requires an active CircleCI connection via Composio. CX Codex +1 122installs wrike-automation wrike-automation controls Wrike work through Rube MCP: tasks, folders, projects, assignees, and status tracking. Useful when project actions should start in an AI coding client. CX Codex +1 121installs zoho-crm-automation zoho-crm-automation — a skill for automating Zoho CRM operations via Rube MCP: create and update records, search contacts, manage leads, and convert them. Requires active Zoho subscription and Rube MCP connection. CX Codex +1 121installs freshservice-automation freshservice-automation handles Freshservice ITSM workflows through Rube MCP, covering ticket creation, searches, bulk updates, and service requests. CX Codex +1 121installs stripe-automation stripe-automation handles Stripe customers, invoices, subscriptions, and refunds through Rube MCP directly in your coding agent. CX Codex +1 120installs

Project sponsors

Companies that keep this analytics open