everhour-automation
by ComposioHQeverhour-automation helps agents automate Everhour via Rube MCP by discovering current Composio tool schemas, checking connection status, and running safer time tracking or reporting workflows.
This skill scores 67/100, which makes it acceptable but limited for directory listing. Directory users get a credible, triggerable guide for using Everhour through Composio/Rube MCP, especially around connection setup and tool discovery, but should not expect detailed Everhour-specific automation playbooks or bundled support assets.
- Valid skill frontmatter declares the required `rube` MCP dependency and a clear Everhour automation description.
- Prerequisites and setup are explicit: verify `RUBE_SEARCH_TOOLS`, manage an Everhour connection with `RUBE_MANAGE_CONNECTIONS`, and confirm ACTIVE status before workflows.
- The skill repeatedly instructs agents to call `RUBE_SEARCH_TOOLS` first, which should reduce schema drift and improve correct tool triggering.
- No support files, scripts, README, or install command are present; adoption depends on knowing how to add the Rube MCP endpoint in the client.
- Workflow guidance is mostly generic Rube MCP discovery/execution rather than concrete Everhour task recipes, so agents still need to infer task-specific steps from discovered tool schemas.
Overview of everhour-automation skill
What everhour-automation is for
The everhour-automation skill helps an AI agent automate Everhour operations through Composio’s Everhour toolkit using Rube MCP. It is best for users who already use Everhour for time tracking, project budgeting, task reporting, or team workload review and want Claude or another MCP-capable agent to discover and call the right Everhour tools instead of guessing API shapes.
Best-fit users and workflows
This skill is a strong fit for workflow automation teams, operations managers, project leads, and developers who need repeatable Everhour actions such as retrieving time entries, checking project or task data, preparing reporting flows, or updating records through an authenticated Everhour connection. The main job-to-be-done is not “write a generic Everhour prompt”; it is to make the agent follow a safe MCP workflow: discover current tools, verify connection status, then execute with the latest schema.
Key differentiator: search tools first
The most important design choice in everhour-automation is its requirement to call RUBE_SEARCH_TOOLS before running Everhour actions. That matters because Composio tool names, fields, and execution plans can change. The skill pushes the agent to fetch current schemas and pitfalls at runtime, which reduces brittle prompts and failed calls compared with hardcoding assumed Everhour API parameters.
Adoption considerations
Before installing the everhour-automation skill, confirm that your client supports MCP and that you can add https://rube.app/mcp as an MCP server. You also need an active Everhour connection through RUBE_MANAGE_CONNECTIONS with toolkit everhour. The repository is intentionally minimal and centers on SKILL.md, so users should expect a workflow instruction skill rather than a package with scripts, tests, or helper files.
How to Use everhour-automation skill
everhour-automation install context
Install the skill from the Composio skills repository with:
npx skills add ComposioHQ/awesome-claude-skills --skill everhour-automation
Then add Rube MCP to your AI client using:
https://rube.app/mcp
After installation, verify that the MCP tool RUBE_SEARCH_TOOLS is available. Next, use RUBE_MANAGE_CONNECTIONS with toolkit everhour. If the connection is not ACTIVE, follow the returned authentication link and confirm the status before asking the agent to run Everhour workflows.
Inputs the skill needs from you
For reliable everhour-automation usage, provide the business goal, target Everhour objects, date range, filters, and desired output format. A weak request is: “Get Everhour hours.” A stronger request is: “Use everhour-automation to find total billable hours in Everhour for Project Alpha from 2025-01-01 to 2025-01-31, grouped by user, and return a table plus any tasks with missing notes.”
This helps the agent form a precise RUBE_SEARCH_TOOLS query, inspect the returned schema, and choose the right execution plan instead of making assumptions about fields such as project ID, user ID, task ID, date format, or billable status.
Practical workflow for agents
A good everhour-automation guide follows this sequence:
- Search for tools using
RUBE_SEARCH_TOOLSwith the specific Everhour use case. - Keep the session ID so follow-up tool discovery and execution stay coherent.
- Check the Everhour connection with
RUBE_MANAGE_CONNECTIONS. - Read the returned tool schemas, required fields, and pitfalls.
- Ask the user for missing identifiers or filters before execution.
- Run the selected Everhour tool only after the schema is known.
- Summarize what was changed or retrieved, including assumptions and records affected.
This pattern is especially useful for everhour-automation for Workflow Automation because it separates planning from execution and lowers the risk of running the wrong action.
Repository files to read first
Start with composio-skills/everhour-automation/SKILL.md. It contains the complete workflow: prerequisites, setup, tool discovery, and the core execution pattern. There are no visible support directories such as scripts/, references/, or rules/, so do not look for hidden automation logic. Treat the skill as a compact instruction layer that depends on live Rube MCP tool discovery.
everhour-automation skill FAQ
Is everhour-automation useful without Rube MCP?
No. The skill explicitly requires Rube MCP and depends on RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS. If your AI client cannot connect to MCP servers, this skill will not provide its intended automation value. You can still read it as a workflow reference, but the operational benefit comes from live MCP tool access.
How is this better than a normal Everhour prompt?
A normal prompt may ask the model to infer Everhour API behavior from memory. The everhour-automation skill instructs the agent to discover available Composio Everhour tools and current input schemas before acting. That makes it better for real operations where field names, required parameters, authentication state, and supported actions must be verified at runtime.
Is this skill beginner-friendly?
It is beginner-friendly if you are comfortable adding an MCP server and completing an OAuth-style connection flow. It is less suitable for users who expect a one-click Everhour dashboard or a standalone command-line app. The main learning curve is understanding that you prompt the agent with a goal, then the agent uses Rube MCP tools to discover and execute the correct Everhour operation.
When should I not use this skill?
Do not use everhour-automation for unauthenticated Everhour access, bulk changes you cannot review, or workflows where you do not know the project, task, user, or date constraints. Also avoid it when you need a fully audited integration with custom code, retries, and logging; this skill provides an agent workflow pattern, not a production integration framework.
How to Improve everhour-automation skill
Improve prompts with concrete Everhour context
The fastest way to improve everhour-automation results is to include the missing business context up front. Specify whether you want to read, create, update, or report on Everhour data. Include date ranges, project names, task names, users, billing status, grouping, and output format. For changes, state whether the agent should preview the intended action before execution.
Reduce common failure modes
Common failures include skipping RUBE_SEARCH_TOOLS, using stale assumed schemas, running before the Everhour connection is active, and asking for broad actions such as “clean up time entries” without criteria. Prevent these by requiring the agent to show the discovered tool name, required fields, and unresolved inputs before calling any write-capable tool.
Iterate after the first output
After the first result, refine with narrow follow-ups: “filter to billable entries only,” “separate internal admin time,” “show entries missing task links,” or “prepare the same report weekly.” This turns the everhour-automation skill from a one-off query helper into a repeatable workflow assistant while keeping each execution tied to discovered tool schemas.
Strengthen the skill for team use
Teams can improve adoption by documenting approved Everhour workflows, naming conventions, safe date ranges, and review rules before write operations. If you maintain a local fork, add examples for your common use cases, such as weekly time summaries, project budget checks, or missing timesheet reviews. Keep the “search tools first” rule intact; it is the core safeguard that makes everhour-automation reliable.