wakatime-automation
by ComposioHQwakatime-automation helps agents run WakaTime workflows through Composio Rube MCP by discovering current tools, checking the wakatime connection, and executing schema-safe actions.
This skill scores 66/100, which makes it an acceptable but limited listing candidate. Directory users get enough evidence to understand that it is for Wakatime automation through Composio's Rube MCP and how an agent should begin safely, but they should expect a lightweight wrapper around tool discovery rather than a detailed, self-contained Wakatime workflow library.
- Frontmatter is valid and clearly declares the trigger intent: automate Wakatime tasks via Rube MCP, with an MCP requirement on `rube`.
- Includes essential prerequisites and setup checks: verify `RUBE_SEARCH_TOOLS`, manage the `wakatime` connection, and confirm ACTIVE status before workflows.
- Repeatedly instructs agents to call `RUBE_SEARCH_TOOLS` first, which reduces schema drift risk and helps agents use current Composio/Wakatime tool definitions.
- No support files, scripts, metadata, or install command are provided; adoption depends on already knowing how to add the Rube MCP endpoint in the user's client.
- Workflow guidance is mostly a generic Rube discovery pattern rather than concrete Wakatime task recipes, so agents may still need to infer task-specific execution details from live tool search results.
Overview of wakatime-automation skill
What wakatime-automation does
wakatime-automation is a Claude skill for running WakaTime-related workflows through Composio’s Rube MCP server. Instead of hard-coding WakaTime API calls, the skill tells the agent to discover the current Rube tool schemas first, verify the WakaTime connection, then execute the appropriate toolkit action.
This matters because Rube tool names, fields, and execution plans can change. The main value of the wakatime-automation skill is not a long library of static commands; it is a safer operating pattern for live WakaTime automation.
Best-fit users and jobs to be done
This skill is a good fit if you want an AI agent to help with WakaTime tasks such as checking coding activity, retrieving summaries, exploring project or language stats, or building reports from WakaTime data. It is especially useful for users already working in a Claude or MCP-enabled environment where Rube MCP can be connected.
The strongest use case is workflow automation: “find the right WakaTime tool, confirm my account connection, run the task, and return a structured result.” That makes wakatime-automation for Workflow Automation more reliable than asking a model to guess WakaTime API details from memory.
Important differentiators
The skill’s key differentiator is its tool-discovery-first rule: always call RUBE_SEARCH_TOOLS before execution. This reduces failures caused by stale schemas, wrong parameter names, or unsupported assumptions.
It also separates setup from execution. Before running a WakaTime operation, the agent should confirm that Rube MCP is available and that the wakatime toolkit connection is ACTIVE through RUBE_MANAGE_CONNECTIONS.
Adoption constraints to know first
wakatime-automation depends on Rube MCP. If your client cannot add https://rube.app/mcp as an MCP server, the skill will not be useful as-is. You also need an active WakaTime connection authorized through Rube.
The repository path currently contains a single main file, composio-skills/wakatime-automation/SKILL.md. There are no extra scripts, references, or rule folders to inspect, so your install decision should focus on whether the MCP-driven workflow matches your environment.
How to Use wakatime-automation skill
wakatime-automation install context
If your skill manager supports GitHub skill installation, install from the repository path:
npx skills add ComposioHQ/awesome-claude-skills --skill wakatime-automation
Then configure Rube MCP in your AI client by adding:
https://rube.app/mcp
After that, confirm the agent can access RUBE_SEARCH_TOOLS. The skill’s own setup flow expects three checks: Rube MCP is reachable, RUBE_MANAGE_CONNECTIONS can manage the wakatime toolkit, and the WakaTime connection is ACTIVE.
Inputs the skill needs
A weak prompt is: “Get my WakaTime stats.”
A better prompt for wakatime-automation usage includes the target outcome, date range, grouping, output format, and any constraints:
Use the wakatime-automation skill. Discover current WakaTime tools first with
RUBE_SEARCH_TOOLS, verify mywakatimeconnection is active, then retrieve my coding activity for the last 7 days grouped by project and language. Return a concise Markdown table plus any schema limitations you encountered.
This gives the agent enough context to search for the right Rube tool, choose parameters, and avoid inventing unsupported fields.
Recommended workflow
Start every task with tool discovery:
RUBE_SEARCH_TOOLS with a specific use case such as “WakaTime weekly coding summary by project.”
Then check the connection:
RUBE_MANAGE_CONNECTIONS with toolkit wakatime.
Only after the connection is active should the agent execute the selected WakaTime tool. Ask the agent to preserve the discovered tool slug and input schema in its reasoning summary or final notes when useful, especially if you are building a repeatable workflow.
Files to read before relying on it
Read SKILL.md first and focus on these sections: Prerequisites, Setup, Tool Discovery, and Core Workflow Pattern. There are no bundled helper scripts or examples beyond the skill file, so users should treat the file as an operating protocol rather than a complete WakaTime report generator.
For deeper capability boundaries, check the live toolkit docs linked from the skill: https://composio.dev/toolkits/wakatime. The live Rube discovery response is still the source of truth for schemas.
wakatime-automation skill FAQ
Is wakatime-automation only for WakaTime?
Yes. The skill is scoped to WakaTime operations through Composio’s WakaTime toolkit. It does not automate arbitrary time tracking services unless those services are exposed separately through Rube MCP and another skill or toolkit.
How is this better than an ordinary prompt?
An ordinary prompt may ask the model to remember WakaTime API fields or guess endpoint behavior. The wakatime-automation skill instead instructs the agent to search Rube tools first and use current schemas. That makes it better for live automation where tool availability and required inputs matter.
Is it beginner-friendly?
It is beginner-friendly if your AI client already supports MCP servers. The conceptual flow is simple: connect Rube, authorize WakaTime, search tools, run the task. It is less beginner-friendly if you have never configured MCP or OAuth-style tool connections before.
When should I not use this skill?
Do not use it if you only need a static explanation of WakaTime, a manual dashboard walkthrough, or offline analysis of exported CSV files. Also avoid it when your organization cannot authorize third-party MCP connections or when WakaTime data access is restricted by policy.
How to Improve wakatime-automation skill
Improve prompts for wakatime-automation
Better prompts produce better tool discovery. Include the reporting period, metric, grouping, and destination format:
Use wakatime-automation to create a month-to-date engineering activity summary. Search current WakaTime tools first, confirm my connection, then return totals by project, top languages, and daily trend notes. If the toolkit lacks one of these fields, explain the gap instead of fabricating it.
This prevents the agent from treating a broad analytics request as a single vague “stats” call.
Common failure modes
The most common failure is skipping RUBE_SEARCH_TOOLS and calling a stale or guessed tool schema. Another common blocker is an inactive WakaTime connection; the agent should stop and ask you to complete the returned auth link rather than continuing.
A subtler failure is asking for dashboard-style insights without specifying the source period or grouping. WakaTime data can be sliced many ways, so the prompt should define what “summary,” “productivity,” or “activity” means.
Iterate after the first output
After the first result, ask the agent to refine based on the returned fields rather than your assumptions. For example: “Use only fields available in the discovered schema and add a comparison to the previous 7-day period if supported.”
For repeatable automation, save the successful discovered tool slug, required parameters, and output format in your own workflow notes. Because the skill intentionally relies on live discovery, this record helps you compare future schema changes.
What would make the skill stronger
The upstream wakatime-automation skill would be stronger with concrete example prompts, sample Rube discovery responses, and a few validated workflows such as weekly project summaries, language breakdowns, and team reporting if supported by the toolkit.
Until those examples exist, users can improve results by being explicit about the WakaTime task, letting Rube discovery drive execution, and treating unsupported fields as constraints rather than reasons for the agent to guess.