skills/amplitude-automation/SKILL.md
Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas.
npx skillsauth add williamlimasilva/.copilot amplitude-automationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Automate Amplitude product analytics through Composio's Amplitude toolkit via Rube MCP.
RUBE_MANAGE_CONNECTIONS with toolkit amplitudeRUBE_SEARCH_TOOLS first to get current tool schemasGet 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.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit amplitudeWhen to use: User wants to track events or send event data to Amplitude
Tool sequence:
AMPLITUDE_SEND_EVENTS - Send one or more events to Amplitude [Required]Key parameters:
events: Array of event objects, each containing:
event_type: Name of the event (e.g., 'page_view', 'purchase')user_id: Unique user identifier (required if no device_id)device_id: Device identifier (required if no user_id)event_properties: Object with custom event propertiesuser_properties: Object with user properties to settime: Event timestamp in milliseconds since epochPitfalls:
user_id or device_id is required per eventevent_type is required for every event; cannot be emptytime must be in milliseconds (13-digit epoch), not secondsWhen to use: User wants to view event history for a specific user
Tool sequence:
AMPLITUDE_FIND_USER - Find user by ID or property [Prerequisite]AMPLITUDE_GET_USER_ACTIVITY - Retrieve user's event stream [Required]Key parameters:
user: Amplitude internal user ID (from FIND_USER)offset: Pagination offset for event listlimit: Maximum number of events to returnPitfalls:
user parameter requires Amplitude's internal user ID, NOT your application's user_idoffsetWhen to use: User wants to look up users or set user properties
Tool sequence:
AMPLITUDE_FIND_USER - Search for a user by various identifiers [Required]AMPLITUDE_IDENTIFY - Set or update user properties [Optional]Key parameters:
user: Search term (user_id, email, or Amplitude ID)user_id: Your application's user identifierdevice_id: Device identifier (alternative to user_id)user_properties: Object with $set, $unset, $add, $append operationsPitfalls:
$set, $unset, $add, $append)$set overwrites existing values; $setOnce only sets if not already setuser_id or device_id is required for IDENTIFYWhen to use: User wants to list cohorts, view cohort details, or update cohort membership
Tool sequence:
AMPLITUDE_LIST_COHORTS - List all saved cohorts [Required]AMPLITUDE_GET_COHORT - Get detailed cohort information [Optional]AMPLITUDE_UPDATE_COHORT_MEMBERSHIP - Add/remove users from a cohort [Optional]AMPLITUDE_CHECK_COHORT_STATUS - Check async cohort operation status [Optional]Key parameters:
cohort_id (from list results)cohort_id: Target cohort IDmemberships: Object with add and/or remove arrays of user IDsrequest_id from update responsePitfalls:
request_id from the update response is needed for status checkingWhen to use: User wants to discover available event types and categories in Amplitude
Tool sequence:
AMPLITUDE_GET_EVENT_CATEGORIES - List all event categories [Required]Key parameters:
Pitfalls:
Application user_id -> Amplitude internal ID:
1. Call AMPLITUDE_FIND_USER with user=your_user_id
2. Extract Amplitude's internal user ID from response
3. Use internal ID for GET_USER_ACTIVITY
Cohort name -> Cohort ID:
1. Call AMPLITUDE_LIST_COHORTS
2. Find cohort by name in results
3. Extract id for cohort operations
Amplitude IDENTIFY supports these property operations:
$set: Set property value (overwrites existing)$setOnce: Set only if property not already set$add: Increment numeric property$append: Append to list property$unset: Remove property entirelyExample structure:
{
"user_properties": {
"$set": {"plan": "premium", "company": "Acme"},
"$add": {"login_count": 1}
}
}
For cohort membership updates:
1. Call AMPLITUDE_UPDATE_COHORT_MEMBERSHIP -> get request_id
2. Call AMPLITUDE_CHECK_COHORT_STATUS with request_id
3. Repeat step 2 until status is 'complete' or 'error'
User IDs:
Event Timestamps:
Rate Limits:
Response Parsing:
data key| Task | Tool Slug | Key Params | |------|-----------|------------| | Send events | AMPLITUDE_SEND_EVENTS | events (array) | | Find user | AMPLITUDE_FIND_USER | user | | Get user activity | AMPLITUDE_GET_USER_ACTIVITY | user, offset, limit | | Identify user | AMPLITUDE_IDENTIFY | user_id, user_properties | | List cohorts | AMPLITUDE_LIST_COHORTS | (none) | | Get cohort | AMPLITUDE_GET_COHORT | cohort_id | | Update cohort members | AMPLITUDE_UPDATE_COHORT_MEMBERSHIP | cohort_id, memberships | | Check cohort status | AMPLITUDE_CHECK_COHORT_STATUS | request_id | | List event categories | AMPLITUDE_GET_EVENT_CATEGORIES | (none) |
development
Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user mentions Pinecone, wants to index documents for semantic search, build a retrieval-augmented generation system, store agent memory across sessions, implement hybrid search, or connect an LLM to a searchable knowledge base — even if they don't say "Pinecone" explicitly. Also use when the user asks about vector databases for RAG, namespace isolation for multi-tenant agents, embedding pipelines, or scaling a knowledge base beyond what local storage can handle. DO NOT use for local-only vector stores (Chroma, FAISS, pgvector) or pure keyword search with no semantic component.
development
Perform an AWS Well-Architected Framework review of the current workload IaC and architecture, generating findings and GitHub issues for improvements.
devops
Query AWS resources using natural language. Covers EC2, S3, RDS, Lambda, ECS, EKS, Secrets Manager, IAM, VPC, networking, messaging, and more. Strictly read-only — no writes, deletes, or mutations.
devops
Analyze AWS resource health, diagnose issues from CloudWatch logs and metrics, and create a remediation plan for identified problems.