agent tool_use skill risk: medium
Docsbot AI Rube MCP Automation Guide
The prompt provides instructions for automating Docsbot AI operations using Composio's toolkit via Rube MCP, including prerequisites, connection setup, tool discovery with RUBE_SEA…
- External action: medium
SKILL 1 file
SKILL.md
---
name: docsbot-ai-automation
description: "Automate Docsbot AI tasks via Rube MCP (Composio). Always search tools first for current schemas."
---
# Docsbot AI Automation via Rube MCP
Automate Docsbot AI operations through Composio's Docsbot AI toolkit via Rube MCP.
**Toolkit docs**: [composio.dev/toolkits/docsbot_ai](https://composio.dev/toolkits/docsbot_ai)
## Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Docsbot AI connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `docsbot_ai`
- 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 `docsbot_ai`
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: "Docsbot AI 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 Docsbot AI task"}]
session: {id: "existing_session_id"}
```
### Step 2: Check Connection
```
RUBE_MANAGE_CONNECTIONS
toolkits: ["docsbot_ai"]
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 Docsbot AI-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `docsbot_ai` |
| 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)*
REQUIRED CONTEXT
- Rube MCP connection
- Docsbot AI toolkit connection status
OPTIONAL CONTEXT
- specific use case for tool search
- existing session_id
TOOLS REQUIRED
- RUBE_SEARCH_TOOLS
- RUBE_MANAGE_CONNECTIONS
- RUBE_MULTI_EXECUTE_TOOL
- RUBE_GET_TOOL_SCHEMAS
- RUBE_REMOTE_WORKBENCH
ROLES & RULES
- Always search tools first for current schemas
- Always call RUBE_SEARCH_TOOLS first to get current tool schemas
- Always discover available tools before executing workflows
- Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
- Confirm connection status shows ACTIVE before running any workflows
- Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
- Use exact field names and types from the search results
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
- Reuse session IDs within a workflow
- Generate new session IDs for new workflows
- Check responses for pagination tokens and continue fetching until complete
EXPECTED OUTPUT
- Format
- markdown
- Constraints
-
- always call RUBE_SEARCH_TOOLS first
- verify ACTIVE connection before execution
- use exact schemas from search results
- include memory parameter even if empty
SUCCESS CRITERIA
- Verify Rube MCP connection before use
- Maintain ACTIVE Docsbot AI connection
- Discover tools via RUBE_SEARCH_TOOLS before execution
- Follow exact schema from search results
- Reuse session IDs within workflows
FAILURE MODES
- Hardcoding tool slugs without searching first
- Executing without verifying ACTIVE connection status
- Using incorrect field names or argument types
- Omitting the memory parameter in execution calls
- Failing to handle pagination in responses
EXAMPLES
Includes multiple example RUBE_* tool calls with arguments for search, connection management, and execution workflows.
CAVEATS
- Dependencies
-
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Docsbot AI connection via RUBE_MANAGE_CONNECTIONS
- Session ID from prior RUBE_SEARCH_TOOLS call
- Missing context
-
- Target MCP client or environment
- Example of a concrete Docsbot AI task to illustrate the workflow
- Ambiguities
-
- Placeholder 'your specific Docsbot AI task' is not replaced with an example
- 'generate_id: true' syntax is shown without explaining how the ID is produced or used
QUALITY
- OVERALL
- 0.76
- CLARITY
- 0.78
- SPECIFICITY
- 0.82
- REUSABILITY
- 0.68
- COMPLETENESS
- 0.75
IMPROVEMENT SUGGESTIONS
- Replace the placeholder use_case with a realistic example such as 'create a new Docsbot AI bot'
- Add a short 'Example Session' block showing a complete end-to-end call sequence with realistic IDs and outputs
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Xcode MCP Usage Guidelines for Agents agent tool_use
- Xcode MCP Usage Guidelines agent tool_use
- Xquik X/Twitter API Integration Skill agent tool_use
- Filesystem Agent Context Engineering agent tool_use
- Agent Tool Design Principles agent tool_use
- Conventional Git Commit Creator agent tool_use
- GitHub Trending Dashboard Generator agent tool_use
- Hosted Background Agent Infrastructure agent tool_use
- AudioCraft Text-to-Music Generation Guide agent tool_use
- Trello Boards Lists Cards Integrator agent tool_use
- Git Commit Push PR Automator agent tool_use
- GitHub Starred Projects Fetcher via Agent Browser agent tool_use
- 2chat Rube MCP Automation Guide agent tool_use
- Rube MCP Autom Task Automation agent tool_use
- Botbaba Automation via Rube MCP agent tool_use
- Aero Workflow Rube MCP Automation agent tool_use
- Boldsign Automation via Rube MCP agent tool_use
- API Sports Rube MCP Automation Guide agent tool_use
- Bolt IoT Rube MCP Automation Guide agent tool_use
- Booqable Automation via Rube MCP agent tool_use
- Coassemble Automation via Rube MCP agent tool_use
- D2L Brightspace Rube MCP Automation Guide agent tool_use
- Codacy Automation via Rube MCP agent tool_use
- Conversion Tools Rube MCP Automation agent tool_use
- Codereadr Automation via Rube MCP agent tool_use