desktime-automation
by ComposioHQdesktime-automation helps agents automate DeskTime workflows through Composio Rube MCP, with tool discovery first, connection checks, and schema-aware execution.
This skill scores 66/100, which means it is acceptable for directory listing but should be presented as a lightweight MCP workflow wrapper rather than a fully developed Desktime automation playbook. Directory users get enough evidence to understand the required Rube MCP setup and when to invoke it, but should expect to rely on live tool discovery for task-specific details.
- Valid skill frontmatter with a clear trigger: automate Desktime tasks through Composio/Rube MCP, with `requires: mcp: [rube]`.
- Provides concrete prerequisites and setup steps, including adding `https://rube.app/mcp`, checking `RUBE_SEARCH_TOOLS`, and activating a Desktime connection via `RUBE_MANAGE_CONNECTIONS`.
- Emphasizes searching tools first for current schemas, which helps agents avoid stale API assumptions and execute through available Rube tools.
- No support files, scripts, references, or README are present beyond SKILL.md, so adoption depends entirely on the embedded instructions and live Rube tool discovery.
- Workflow guidance is mostly generic MCP/tool-discovery pattern rather than Desktime-specific recipes, so users may still need to infer exact actions from returned schemas.
Overview of desktime-automation skill
What desktime-automation does
desktime-automation is a Claude skill for automating DeskTime tasks through Composio’s Rube MCP server. It is designed to help an AI agent discover the current DeskTime tool schemas, verify your DeskTime connection, and execute DeskTime-related operations without relying on stale hard-coded API assumptions.
Best-fit users and workflows
This skill is a good fit if you already use DeskTime and want an assistant to help with Workflow Automation around time tracking, employee productivity data, attendance-style checks, project time review, or operational reporting. It is especially useful for teams that prefer MCP-based tool access instead of writing custom DeskTime API scripts from scratch.
What makes this skill different
The most important behavior in the desktime-automation skill is tool discovery first. The upstream skill explicitly requires the agent to call RUBE_SEARCH_TOOLS before execution so it can retrieve current tool slugs, schemas, execution plans, and pitfalls. That matters because Composio tool schemas can change, and a generic prompt may guess outdated field names.
Adoption considerations
This is not a standalone DeskTime client. It depends on Rube MCP and an active DeskTime connection managed through Composio. The repository path contains only SKILL.md, so the value is in the workflow instructions rather than helper scripts, examples, or local code. Install it when you want a repeatable agent procedure for DeskTime operations, not when you need a complete packaged app.
How to Use desktime-automation skill
desktime-automation install context
Install the skill from the Composio skill collection in a client that supports Claude skills and MCP tools. A typical install command is:
npx skills add ComposioHQ/awesome-claude-skills --skill desktime-automation
Then configure Rube MCP by adding https://rube.app/mcp as an MCP server in your client. The source skill says no API keys are needed for the MCP endpoint itself, but you still need to authorize the DeskTime connection through Composio.
Required connection setup
Before asking the agent to perform DeskTime work, confirm these conditions:
RUBE_SEARCH_TOOLSis available.RUBE_MANAGE_CONNECTIONScan be called.- The
desktimetoolkit connection isACTIVE. - If it is not active, follow the auth link returned by
RUBE_MANAGE_CONNECTIONS. - Only run DeskTime workflows after the connection status is confirmed.
The practical blocker is usually authorization, not prompting. If the DeskTime connection is inactive, the skill cannot complete actions no matter how well the request is written.
Prompt pattern for strong desktime-automation usage
A weak prompt is: “Check DeskTime for my team.”
A stronger prompt gives the agent a specific use case and tells it to discover schemas first:
Use the desktime-automation skill. First call
RUBE_SEARCH_TOOLSfor current DeskTime tools and schemas. Then check whether thedesktimeconnection is active. I need a summary of DeskTime activity for the engineering team for last week, grouped by user and project if the available tools support those fields. If a required field or filter is unavailable, tell me before executing.
This improves output quality because it defines the business goal, date range, grouping needs, fallback behavior, and required discovery step.
Files to inspect before relying on it
Read composio-skills/desktime-automation/SKILL.md first. It contains the full workflow: prerequisites, Rube MCP setup, tool discovery, connection checking, and the core execution pattern. There are no companion scripts/, resources/, references/, or README.md files in the current tree, so do not expect extra examples beyond the skill document.
desktime-automation skill FAQ
Is desktime-automation for beginners?
Yes, if your AI client already supports MCP tools and you can follow an OAuth-style connection flow. It is less beginner-friendly if you have never configured an MCP server, because the skill assumes Rube MCP is reachable and that the agent can call RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS.
How is it better than an ordinary prompt?
An ordinary prompt may invent DeskTime API fields or skip connection validation. The desktime-automation skill gives the agent a safer order of operations: discover tools, inspect schemas, check the DeskTime connection, then execute. That structure reduces failures caused by outdated assumptions.
What DeskTime tasks can it automate?
The exact operations depend on the current Composio DeskTime toolkit exposed through Rube MCP. The skill is suitable for DeskTime operations such as retrieving time-tracking information, checking available project or user data, and building reporting workflows, but you should let RUBE_SEARCH_TOOLS determine the available actions before promising a result.
When should I not use this skill?
Do not use it if you need offline processing, direct DeskTime API code, or a workflow that cannot depend on Composio/Rube. It is also a poor fit when your organization has not approved connecting DeskTime to third-party automation tooling.
How to Improve desktime-automation skill
Improve inputs before running desktime-automation
Give the agent the operational shape of the request: date range, users or teams, projects, output format, whether actions are read-only or write-capable, and what to do if the schema lacks a desired field. For example: “Export-style summary, read-only, last calendar month, grouped by project, include only active users if supported.”
Prevent common failure modes
The most common failure is skipping discovery. Insist that the agent calls RUBE_SEARCH_TOOLS with your specific use case, not just a generic “Desktime operations” query. Another failure is running before the connection is active; require a connection check through RUBE_MANAGE_CONNECTIONS before any DeskTime operation.
Iterate after the first result
Treat the first run as schema discovery plus a draft workflow. If the output is incomplete, ask the agent to report which fields were available, which filters were unsupported, and what alternative execution plan Rube recommended. Then refine the prompt around supported fields instead of asking for unavailable data.
Add local guidance for team-specific use
To improve the desktime-automation skill for repeated use, maintain your own notes alongside the installed skill: approved DeskTime workspaces, standard reporting periods, team names, privacy limits, and preferred output formats. This turns a generic desktime-automation guide into a safer team workflow while still preserving the required Rube tool-discovery step.