emelia-automation
by ComposioHQemelia-automation helps agents run Emelia sales outreach through Rube MCP by discovering current tool schemas, checking the Emelia connection, and executing safer workflows.
This skill scores 66/100, which means it is acceptable for listing but should be presented as a lightweight connector-oriented skill rather than a fully worked Emelia automation playbook. Directory users get enough information to know they need Rube MCP and an active Emelia connection, and agents get a useful tool-discovery pattern, but concrete task examples and operational detail are limited.
- Valid frontmatter declares the required MCP dependency (`rube`) and a clear purpose: automating Emelia tasks through Composio/Rube MCP.
- Prerequisites and setup steps explain how to verify `RUBE_SEARCH_TOOLS`, manage the Emelia connection, and confirm ACTIVE status before execution.
- The skill gives a repeatable discovery-first pattern using `RUBE_SEARCH_TOOLS` and `RUBE_MANAGE_CONNECTIONS`, which reduces schema guesswork for agents.
- No support files, scripts, references, or README are present beyond SKILL.md, so adoption depends entirely on the brief inline instructions.
- The workflow remains generic because it tells agents to discover current Emelia tool schemas rather than documenting concrete Emelia actions or example end-to-end automations.
Overview of emelia-automation skill
What emelia-automation does
emelia-automation is a Claude skill for running Emelia sales outreach operations through Composio’s Rube MCP. It is not a standalone Emelia client; it teaches the agent to discover the current Emelia tool schemas, verify the Emelia connection, and execute actions through the Rube tool layer instead of guessing API parameters.
Best fit for Sales Outreach operators
The emelia-automation skill is most useful for teams already using Emelia for outbound sales sequences, contact management, campaign work, or inbox/outreach operations and who want an AI assistant to drive those tasks safely. It fits users who need repeatable execution inside an MCP-enabled assistant, especially when Emelia tool names or schemas may change over time.
Main differentiator: search tools first
The key value is the “discover before execute” pattern. The upstream skill explicitly requires RUBE_SEARCH_TOOLS before running Emelia workflows, so the agent retrieves current tool slugs, schemas, execution plans, and pitfalls instead of relying on stale examples. That makes emelia-automation more reliable than a generic prompt asking an assistant to “use Emelia.”
What to verify before installing
Adoption depends on having Rube MCP available in your client and an active Emelia connection through RUBE_MANAGE_CONNECTIONS. The repository contains a single SKILL.md and no helper scripts, examples folder, or local test harness, so expect a lightweight operational guide rather than a full automation package.
How to Use emelia-automation skill
emelia-automation install and setup context
Install the skill from the Composio skills repository with:
npx skills add ComposioHQ/awesome-claude-skills --skill emelia-automation
Then add Rube MCP as an MCP server using https://rube.app/mcp in your AI client configuration. The skill assumes the MCP server exposes RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS. After installation, ask the assistant to verify that Rube is reachable, manage connections for toolkit emelia, and confirm the connection status is ACTIVE before attempting any outreach workflow.
Inputs the skill needs from you
For strong emelia-automation usage, provide the task, the relevant Emelia object, the business rule, and the safety boundary. A weak prompt is: “Update my Emelia campaign.” A stronger prompt is: “Use emelia-automation for Sales Outreach. First discover the current Emelia tools, confirm the Emelia connection is active, then find the campaign named Q1 SaaS CFO outbound and pause only prospects in step 2 whose company size is under 50 employees. Show the tool plan before executing.”
Useful inputs include campaign names, contact or prospect identifiers, sequence step numbers, filtering criteria, message intent, date ranges, and whether the assistant should execute immediately or ask for confirmation first.
Practical workflow for first run
Start with a low-risk read operation. Ask the assistant to call RUBE_SEARCH_TOOLS for your specific use case, such as “list Emelia campaigns” or “find prospects in a campaign,” then inspect the returned schema. Next, have it call RUBE_MANAGE_CONNECTIONS for toolkit emelia. Only after the connection is active should it execute the discovered Emelia tool.
A good first-run pattern is: discover tools, summarize available actions, select the safest matching action, map your inputs to the returned schema, request confirmation for write operations, then execute. This protects against wrong campaign edits, outdated parameter names, or accidental outreach changes.
Repository files to read first
Read composio-skills/emelia-automation/SKILL.md first; it contains the prerequisites, Rube setup, tool discovery pattern, and core workflow. There are no listed README.md, metadata.json, rules/, resources/, references/, or scripts/ files for this skill, so the decision point is simple: if your client supports Rube MCP and your Emelia connection can be activated, the skill is usable; if not, installation will not help.
emelia-automation skill FAQ
Is emelia-automation only for Sales Outreach?
Its clearest fit is emelia-automation for Sales Outreach because Emelia is commonly used for outbound workflows. The skill can support whatever Emelia operations Composio exposes through Rube, but the exact capabilities should be discovered at runtime with RUBE_SEARCH_TOOLS, not assumed from the skill text.
How is this better than an ordinary prompt?
A normal prompt may produce plausible but invalid Emelia API steps. The emelia-automation skill tells the agent to search the live Rube MCP tool catalog first, check the Emelia connection, and use current schemas. That reduces guesswork and makes the assistant’s plan easier to audit before it performs campaign or contact actions.
Can beginners use this skill?
Yes, if they are comfortable connecting an MCP server and completing an Emelia authorization flow. Beginners should ask for confirmation before any write action, start with read-only discovery, and require the assistant to show the selected tool name and input payload before execution.
When should I not use emelia-automation?
Do not use it if you do not have Emelia, cannot connect Rube MCP, or need a local script that runs without an AI client. It is also a poor fit for bulk destructive changes unless you can provide exact filters, review the plan, and test on a small segment first.
How to Improve emelia-automation skill
Give emelia-automation precise operating constraints
The biggest output-quality improvement is clearer boundaries. Specify whether the assistant may create, update, pause, delete, or only read. For outreach work, include exclusions such as “do not contact existing customers,” “do not modify active campaigns,” or “only apply to prospects tagged webinar-leads.” These constraints help the agent choose safer tools after discovery.
Prevent common failure modes
Common failures include skipping tool discovery, using stale parameter names, acting before the Emelia connection is active, or applying broad filters to the wrong campaign. Counter this by requiring: “Call RUBE_SEARCH_TOOLS first, use the returned schema exactly, check RUBE_MANAGE_CONNECTIONS, and ask me before any write operation affecting more than 10 records.”
Improve prompts with schema-aware details
After the first RUBE_SEARCH_TOOLS response, refine your request using the actual fields the tool exposes. If the schema includes campaign IDs rather than campaign names, ask the assistant to resolve the name to an ID first. If a tool supports pagination or status filters, include those controls. Schema-aware prompting turns emelia-automation from a broad instruction into an executable workflow.
Iterate after the first output
For the first run, ask for a dry-run style summary: intended tool, input payload, affected records, and rollback or correction plan if available. After execution, request a concise result audit: what changed, what failed, and what needs manual review in Emelia. This iteration is especially important for Sales Outreach workflows where small targeting mistakes can affect deliverability, personalization, or prospect experience.