home / skills / composiohq / awesome-claude-skills / anthropic-administrator-automation
/anthropic-administrator-automation
This skill automates Anthropic Admin operations via Rube MCP, always discovering current tool schemas before execution to ensure accurate, up-to-date workflows.
npx playbooks add skill composiohq/awesome-claude-skills --skill anthropic-administrator-automationReview the files below or copy the command above to add this skill to your agents.
---
name: anthropic-administrator-automation
description: "Automate Anthropic Admin tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
mcp: [rube]
---
# Anthropic Admin Automation via Rube MCP
Automate Anthropic Admin operations through Composio's Anthropic Admin toolkit via Rube MCP.
**Toolkit docs**: [composio.dev/toolkits/anthropic_administrator](https://composio.dev/toolkits/anthropic_administrator)
## Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Anthropic Admin connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `anthropic_administrator`
- 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 `anthropic_administrator`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows
## Tool Discovery
Always discover available tools before executing workflows:
```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Anthropic Admin operations", known_fields: ""}]
session: {generate_id: true}
```
This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.
## Core Workflow Pattern
### Step 1: Discover Available Tools
```
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Anthropic Admin task"}]
session: {id: "existing_session_id"}
```
### Step 2: Check Connection
```
RUBE_MANAGE_CONNECTIONS
toolkits: ["anthropic_administrator"]
session_id: "your_session_id"
```
### Step 3: Execute Tools
```
RUBE_MULTI_EXECUTE_TOOL
tools: [{
tool_slug: "TOOL_SLUG_FROM_SEARCH",
arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
```
## Known Pitfalls
- **Always search first**: Tool schemas change. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`
- **Check connection**: Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools
- **Schema compliance**: Use exact field names and types from the search results
- **Memory parameter**: Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty (`{}`)
- **Session reuse**: Reuse session IDs within a workflow. Generate new ones for new workflows
- **Pagination**: Check responses for pagination tokens and continue fetching until complete
## Quick Reference
| Operation | Approach |
|-----------|----------|
| Find tools | `RUBE_SEARCH_TOOLS` with Anthropic Admin-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `anthropic_administrator` |
| Execute | `RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs |
| Bulk ops | `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` |
| Full schema | `RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef` |
---
*Powered by [Composio](https://composio.dev)*
This skill automates Anthropic Admin tasks by driving Composio's Anthropic Administrator toolkit through Rube MCP. It provides a repeatable workflow: discover tools, verify connection, and execute schema-compliant operations reliably. The skill emphasizes always searching for current tool schemas before acting.
The skill uses RUBE_SEARCH_TOOLS to discover available Anthropic Admin tool slugs, input schemas, and execution plans. It verifies an active Anthropic Admin connection via RUBE_MANAGE_CONNECTIONS, then runs operations through RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk work), always including a memory block and session id. It checks for pagination and schema references using RUBE_GET_TOOL_SCHEMAS when needed.
What must I do before executing any tool?
Always run RUBE_SEARCH_TOOLS to fetch the current tool list and schemas, then confirm the toolkit connection is ACTIVE via RUBE_MANAGE_CONNECTIONS.
Can I hardcode tool argument shapes?
No. Tool schemas change; always use the field names and types returned by RUBE_SEARCH_TOOLS or RUBE_GET_TOOL_SCHEMAS.