sensibo-automation
by ComposioHQsensibo-automation helps agents control Sensibo devices through Composio Rube MCP by discovering current tool schemas, checking the Sensibo connection, and executing safer workflow automation.
This skill scores 68/100, which makes it acceptable but limited for directory listing. Directory users get enough evidence to understand that it helps agents operate Sensibo through Rube MCP with less guesswork than a generic prompt, especially by enforcing tool discovery and connection checks, but they should expect a thin wrapper around Composio/Rube rather than a richly documented Sensibo automation playbook.
- Clear trigger and scope: it is specifically for automating Sensibo operations through Composio's Sensibo toolkit via Rube MCP.
- Operational prerequisites are explicit, including RUBE_SEARCH_TOOLS availability, an active Sensibo connection, and use of RUBE_MANAGE_CONNECTIONS.
- The skill gives a repeatable agent pattern: discover tools first, check the Sensibo connection, then execute workflows using current schemas.
- No support files, scripts, or reference examples are included; the skill depends on live Rube tool discovery rather than documented Sensibo tool schemas.
- Install/adoption guidance is partial: it explains adding the Rube MCP endpoint and connecting Sensibo, but there is no repository README or install command.
Overview of sensibo-automation skill
What sensibo-automation does
sensibo-automation is a Claude skill for controlling Sensibo devices through Composio’s Rube MCP server. It is designed for workflows such as checking available Sensibo tools, confirming account connection status, and running Sensibo operations only after retrieving the current tool schemas from Rube.
Best fit for Sensibo and Rube MCP users
This skill is a good fit if you already use Sensibo for climate control and want an AI agent to help automate actions through the Composio Sensibo toolkit. It is especially useful for users who prefer MCP-based workflow automation instead of writing direct API integrations.
Main adoption requirement
The key requirement is not a local script or package dependency; it is a working Rube MCP connection. Your client must have https://rube.app/mcp configured as an MCP server, RUBE_SEARCH_TOOLS must be available, and the Sensibo toolkit connection must be active through RUBE_MANAGE_CONNECTIONS.
What makes this skill different
The important differentiator is its “search tools first” pattern. Instead of assuming static Sensibo API fields, the sensibo-automation skill tells the agent to discover current tool slugs, schemas, plans, and pitfalls before taking action. That reduces failures caused by stale parameters or changed tool definitions.
How to Use sensibo-automation skill
sensibo-automation install and setup path
Install the skill from the Composio skill collection with:
npx skills add ComposioHQ/awesome-claude-skills --skill sensibo-automation
Then configure Rube MCP in your AI client by adding https://rube.app/mcp as an MCP server. After that, verify that RUBE_SEARCH_TOOLS responds. Use RUBE_MANAGE_CONNECTIONS with toolkit sensibo and complete the returned authentication flow if the connection is not marked ACTIVE.
What to read before first use
Start with composio-skills/sensibo-automation/SKILL.md. There are no extra README.md, scripts/, resources/, or rules/ folders in this skill, so the main file is the authoritative guide. Pay particular attention to the prerequisites, setup, tool discovery, and core workflow pattern sections.
Inputs the skill needs from you
For strong sensibo-automation usage, give the agent a concrete Sensibo goal, not just “automate my AC.” Include the target room or device if you know it, the desired operation, any timing or comfort constraints, and whether the agent should only inspect status or actually change settings.
Weak prompt:
Use Sensibo to fix the temperature.
Stronger prompt:
Use sensibo-automation for Workflow Automation. First discover current Sensibo tools with RUBE_SEARCH_TOOLS, confirm my Sensibo connection is ACTIVE, then find available devices and set the living room unit to cooling at 23°C if the schema supports that action. Ask before making changes if multiple devices match.
Practical workflow for safer execution
A reliable sensibo-automation guide follows this sequence: discover tools, check connection, inspect available devices or capabilities, then execute the chosen action using the returned schema. Do not skip discovery, because Rube may return updated tool names, required fields, or execution plans. If the task affects comfort or energy use, ask the agent to summarize the intended action before execution.
sensibo-automation skill FAQ
Is sensibo-automation only for advanced users?
Not necessarily, but beginners must be comfortable connecting an MCP server and completing an OAuth-style toolkit connection. If you have never configured MCP tools before, the main learning curve is setup, not Sensibo logic.
Can I use ordinary prompts instead of this skill?
You can ask a model for general Sensibo automation ideas, but ordinary prompts will not reliably know the current Composio Sensibo tool schemas. The sensibo-automation skill is better when the agent must call real Rube MCP tools and adapt to live schemas before executing.
What can block sensibo-automation from working?
The most common blockers are no Rube MCP server configured, RUBE_SEARCH_TOOLS unavailable, the Sensibo toolkit not connected, or a connection that is not ACTIVE. Another blocker is asking for an action that the currently discovered Sensibo tools do not support.
When should I not use this skill?
Do not use it if you need a standalone Sensibo API library, Home Assistant automation, embedded firmware control, or a no-MCP workflow. The skill is specifically built around Composio’s Sensibo toolkit via Rube MCP.
How to Improve sensibo-automation skill
Make sensibo-automation prompts schema-aware
The best improvement is to instruct the agent to treat RUBE_SEARCH_TOOLS output as the source of truth. Ask it to quote or summarize the discovered tool slug, required fields, and planned arguments before execution. This makes errors easier to catch before a device state changes.
Provide device and policy context
Better inputs produce safer automation. Include room names, acceptable temperature ranges, whether changes should be reversible, and whether the agent should prefer status checks over direct changes. For example: Do not change any setting unless the current temperature is above 26°C and the matching device is the bedroom unit.
Handle common failure modes explicitly
Tell the agent what to do if multiple devices match, no device matches, the connection is inactive, or the schema does not include the requested field. A good fallback instruction is: If the Sensibo tool schema does not support the requested operation, stop and explain the closest supported alternatives.
Iterate after the first run
After the first output, refine the workflow based on the discovered tools. If the agent found a better execution plan, reuse the same Rube session where appropriate. If the result was ambiguous, add exact device names, preferred units, and confirmation rules before running the next sensibo-automation step.