satismeter-automation
by ComposioHQsatismeter-automation helps agents automate Satismeter operations through Composio Rube MCP by discovering current tool schemas first, verifying an ACTIVE Satismeter connection, and then running feedback, survey, or NPS workflows with less guesswork.
This skill scores 68/100, which means it is acceptable for listing but should be presented as a lightweight MCP workflow guide rather than a full Satismeter playbook. Directory users get enough evidence to understand when to use it, how to connect Rube MCP, and how an agent should discover current Satismeter tools before acting, but they should expect limited task-specific examples and little offline documentation.
- Valid frontmatter clearly declares the skill name, Satismeter automation purpose, and required Rube MCP dependency.
- Prerequisites and setup steps explain that Rube MCP must be connected, Satismeter must be authorized through RUBE_MANAGE_CONNECTIONS, and connection status should be ACTIVE before workflows run.
- The workflow pattern instructs agents to call RUBE_SEARCH_TOOLS first for current schemas, which reduces schema guesswork and helps keep execution aligned with live Composio tools.
- No support files, scripts, examples, or local README are included; the skill relies on live Rube tool discovery rather than documented Satismeter-specific operations.
- Install/setup guidance is limited to adding the Rube MCP endpoint and managing the Satismeter connection; there is no explicit install command in the skill file.
Overview of satismeter-automation skill
What satismeter-automation is for
satismeter-automation is a Claude skill for automating Satismeter work through Composio’s Rube MCP server. It is designed for agents that need to discover the current Satismeter tool schema, verify an active Satismeter connection, and then run customer feedback, survey, or NPS-related operations without guessing tool names or payload formats.
The practical value is not just “use Satismeter from chat.” The skill enforces a safer workflow: search available Rube tools first, confirm the Satismeter connection, then execute with the schema returned by MCP.
Best-fit users and workflows
This satismeter-automation skill is most useful for teams already using Satismeter and Claude-compatible MCP clients. It fits workflow automation tasks such as pulling customer feedback data, checking survey responses, coordinating follow-up operations, or building repeatable assistant-driven Satismeter processes.
It is a good fit if you want the agent to handle Satismeter through live tool discovery instead of relying on outdated hardcoded examples. It is less useful if you only need to read static Satismeter documentation or if your MCP client cannot connect to Rube.
Key differentiator: search tools first
The important design choice in satismeter-automation is the instruction to call RUBE_SEARCH_TOOLS before execution. Rube tool schemas can change, and the skill tells the agent to request current tool slugs, fields, execution plans, and pitfalls before calling any Satismeter operation.
That makes it more reliable than a generic “use the Satismeter API” prompt, especially when the user does not know the latest Composio tool names or required parameters.
How to Use satismeter-automation skill
satismeter-automation install and prerequisites
Install the skill from the Composio skills repository:
npx skills add ComposioHQ/awesome-claude-skills --skill satismeter-automation
Before expecting useful output, confirm three things:
- Your client supports MCP skills.
- Rube MCP is configured with
https://rube.app/mcp. - Satismeter is connected through Rube using
RUBE_MANAGE_CONNECTIONSwith toolkitsatismeter.
The upstream skill does not include helper scripts or extra reference folders, so the main file to inspect is composio-skills/satismeter-automation/SKILL.md. Read it first if you need the exact workflow pattern.
Inputs the skill needs from you
For strong satismeter-automation usage, give the agent a specific Satismeter job, not just “check Satismeter.” Include the object or workflow you care about, the time range, identifiers you already know, and the desired output format.
Weak prompt:
Use Satismeter and tell me what is going on.
Stronger prompt:
Use satismeter-automation for Workflow Automation. First discover the current Satismeter tools with Rube. Confirm the Satismeter connection is active. Then find recent NPS or survey feedback from the last 30 days, summarize common negative themes, and return a table with customer identifier, score or sentiment if available, feedback text, and suggested follow-up action. Do not call any execution tool until you have the current schema.
This works better because it gives the agent a concrete use case for RUBE_SEARCH_TOOLS and a clear final shape for the answer.
Recommended execution pattern
A reliable satismeter-automation guide should follow this sequence:
- Call
RUBE_SEARCH_TOOLSwith the specific Satismeter use case. - Reuse the returned session ID for related discovery or execution steps.
- Call
RUBE_MANAGE_CONNECTIONSif the connection status is unknown. - If the Satismeter connection is not
ACTIVE, stop and ask the user to complete the auth link. - Use only the tool slugs and input fields returned by Rube.
- After execution, summarize what was done, what data was returned, and what remains uncertain.
This matters because the skill’s core constraint is schema freshness. Hardcoding guessed fields defeats the purpose of using Rube MCP.
Repository files to read first
The repository path is:
composio-skills/satismeter-automation/SKILL.md
There are no visible scripts/, resources/, references/, rules/, or README.md files in the provided tree, so do not look for a large framework around this skill. The install decision should be based on whether its single workflow instruction matches your environment: Rube MCP plus an active Satismeter connection.
satismeter-automation skill FAQ
Is satismeter-automation only for Composio users?
It is specifically built around Composio’s Rube MCP and the Satismeter toolkit exposed there. You do not need to manually manage a Satismeter API integration inside the skill, but you do need Rube MCP available in your client and an active Satismeter connection.
How is this better than an ordinary prompt?
An ordinary prompt may hallucinate Satismeter endpoints, assume stale field names, or skip authentication checks. The satismeter-automation skill tells the agent to discover tools first through RUBE_SEARCH_TOOLS, verify connection state, and follow the current schema returned by MCP. That reduces guesswork in live workflow automation.
Can beginners use this skill?
Yes, if they can configure an MCP server and follow an auth link. The main beginner hurdle is not Satismeter knowledge; it is MCP setup. Once Rube is connected and Satismeter shows ACTIVE, users can describe the business task in plain language and let the skill guide tool discovery.
When should I not use it?
Do not use satismeter-automation if you need offline analysis without a Satismeter connection, if your client does not support MCP, or if your organization does not allow third-party automation tools to access customer feedback systems. Also avoid it for tasks where you need a custom Satismeter API integration with strict internal controls rather than agent-mediated tool calls.
How to Improve satismeter-automation skill
Make satismeter-automation prompts more specific
The biggest quality improvement is to describe the Satismeter outcome, not just the tool. Include the segment, time window, action type, and output format.
Better input:
Discover current Satismeter tools, verify connection status, then retrieve feedback related to enterprise accounts from this quarter if available. Group results by complaint theme, identify high-priority follow-ups, and show which fields came directly from Satismeter versus inferred analysis.
This helps the agent choose the right discovery query and avoid overbroad tool calls.
Avoid common failure modes
Common problems include skipping RUBE_SEARCH_TOOLS, assuming the connection is active, using guessed schemas, and continuing after an auth failure. A good workflow should stop when Satismeter is not connected, ask for confirmation before risky changes, and state when Rube did not expose a suitable tool for the requested task.
For read-heavy analysis, ask the agent to separate raw returned data from interpretation. For write or update actions, ask for a plan preview before execution.
Iterate after the first output
After the first run, refine by asking for narrower filters, different grouping, or a follow-up action list. For example:
Re-run only if needed. Narrow the results to detractor feedback, exclude already-contacted customers if that field is available, and produce a follow-up queue with owner, reason, and suggested message.
This turns the skill from a one-off query helper into a practical Satismeter workflow automation layer.
Improve the skill itself if you fork it
If you maintain a fork, useful additions would be examples for common Satismeter tasks, safe read-versus-write patterns, sample prompts, and explicit confirmation rules for customer-facing updates. Keep the “search tools first” behavior central, because that is the main reason satismeter-automation stays resilient as Rube’s Satismeter schemas evolve.